https://public.kitware.com/Wiki/api.php?action=feedcontributions&user=Ccagataybilgin&feedformat=atomKitwarePublic - User contributions [en]2024-03-28T22:26:01ZUser contributionsMediaWiki 1.38.6https://public.kitware.com/Wiki/index.php?title=ITK/Job_Opportunities&diff=56337ITK/Job Opportunities2014-05-16T19:13:51Z<p>Ccagataybilgin: /* Multiple Software Engineer Positions at Intel */</p>
<hr />
<div>Please feel free to post announcements for jobs and positions that are related to ITK and applicants with ITK experience. Once the position has been fulfilled, please update the entry accordingly.<br />
<br />
Please note that they are '''listed according to their post date''', and not their deadline, as this information is missing in some cases. Past positions are kept for the sake of maintaining a small history of them.<br />
<br />
= Current positions (2014) =<br />
<br />
== Multiple Software Engineer Positions at Intel ==<br />
Posted: May. 16th 2014<br />
<br />
'''Description''':<br />
The individual will participate in the development of next generation computational lithography tools, which are an important contributor to Intel's march along Moore's Law. The job role includes research and development work for creating new numerical models and algorithms that enable extracting even more resolution out of existing 193nm steppers. The duties also include image analysis, software performance optimization, parallel programming, computational geometry as well as supporting mission critical software in a production environment. The position requires working in a team with other developers, and interfacing with a large technology development organization. Good communication skills with demonstrated attention to detail and results orientation are required.<br />
<br />
'''Minimum Qualifications''':<br />
* PhD degree in Computer Science, Physics, Electrical Engineering, Mechanical Engineering, or a related engineering discipline <br />
Note: due to the multi-disciplinary nature of the work our team is comprised of world leading experts in fields ranging from Optics/Electromagnetism to Chemical Engineering and Robotics<br />
* Demonstrated coding proficiency, preferably in C++<br />
<br />
'''Preferred Qualifications''':<br />
Background in one or more of the following areas:<br />
* Computer Vision & Machine Learning<br />
* Optics & Electromagnetics Theory<br />
* Parallel Programming and algorithms<br />
* Numerical modeling<br />
* Computational geometry<br />
* Computational lithography methods<br />
* Linear/Non-linear optimization<br />
* Big data, Database Systems, UI <br />
<br />
'''Job Location''':<br />
Hillsboro, Oregon. Located in the beautiful Portland Metro Area, 15 miles west of downtown Portland, Intel Oregon is the largest and most complex site in the world, a global center of semiconductor research and manufacturing, and the largest private employer in the state.<br />
<br />
'''About Our Team''':<br />
We are a highly motivated multi-disciplinary team whose expertise range from computer engineering to physics, electrical engineering to chemical engineering. Our team produces world class solutions for computational lithography systems and has won several Intel achievement awards as well as software quality awards. <br />
<br />
Interested individuals should forward their resumes to cemal.c.bilgin@intel.com<br />
<br />
= Past positions =<br />
<br />
<br />
== Year 2013 ==<br />
<br />
<br />
=== Internship position for developing a MR CAD tool ===<br />
Posted: Oct. 29th 2013<br />
<br />
Eigen is making a difference in patient outcomes and care with our innovative medical imaging products, and we’re looking for a software engineer to join our team.<br />
ProFuse, our MRI image fusion product, is being used on patients daily to provide accurate, repeatable biopsies, with the assistance of Eigen’s mechanical guidance. We have a list of improvements in mind to make the system even better, and that’s where you can help us. We need a quality-focused software intern who’s familiar with C++ - if you know the QT framework, so much the better. You’ll be working with our existing team to add features, and lay the foundation for our next generation of products.<br />
<br />
Requirements:<br />
-In progress degree in Computer Science, Mathematics, Physics, Engineering, Medical Imaging or related discipline.<br />
-UI/UX programming experience.<br />
-Strong interpersonal and communication skills.<br />
-Knowledgeable and experienced with C++ language.<br />
<br />
Desirable but not required:<br />
-Experience with medical devices, avionics, or other regulated technical products.<br />
-Familiarity with ITK and VTK libraries.<br />
-Experience with CMake build system.<br />
-Image processing background strongly preferred.<br />
-Strong mathematics background.<br />
-GPU programming experience (CUDA).<br />
<br />
This is a 6 month internship, on-site at our Grass Valley, CA location, but could lead to a full time W2 position.<br />
<br />
Please send your resumes to hr@eigen.com.<br />
<br />
=== PhD position in multi-modal image processing, b<>com Brest, France ===<br />
<br />
Posted: Oct. 28th 2013<br />
<br />
It is increasingly common to combine multiple methods of treatment, i.e., treatment modalities, with the intention to improve patient outcomes and reduce complications. Each treatment modality may consist of (1) multiple images acquired by one or more modalities (e.g. PET and CT) and (2) contextual information (e.g. clinical reports). To improve patient outcome, one approach is to unify the imaging information and the context information so that the therapy planning, therapy guidance and post-treatment evaluation are simplified. In practice, whereas Picture Archive and Communication Systems (PACS), employed in hospital, store multi-modal images and contextual information, simultaneous re-use of both information cannot be done in a simple fashion.<br />
<br />
This Ph.D. will focus on the integration of multi-modal imaging information accrued by contextual information extracted from a PACS.<br />
<br />
A first problem to address is the analysis of multi-modal images (e.g., PET/CT). This analysis requires, for example, image processing (image quality improvement or image artifact reduction) followed by image analysis (segmentation or biomarker extraction). A second problem to investigate is the association of quantitative parameters extracted from multi-modal images with other contextual information. This also involves the automatic generation of clinical reports both associating results of multi-parameter image analysis and contextual information, with the goal of assisting physicians with clinical decisions. It is intended that this Ph.D. will lead to a Clinical Decision Support System demonstrator dedicated to a specific context/pathology (e.g. oncology or neurology).<br />
<br />
The PhD fellowship is funded by b<>com (http://b-com.com) which is a Technology Research Institute located in Brest, Rennes and Lannion (France). This Ph.D thesis will be carried out under the supervision of M. Hatt (research associate, INSERM) and G. Coatrieux, Assistant Professor (Telecom Bretagne) and located at b<>com on the Brest-Iroise Science and Technology Park.<br />
<br />
Expected qualifications:<br />
- Minimum MSc degree (Computer Science)<br />
- Experience in developing medical imaging applications is desirable<br />
- Prior experience in image analysis, pattern recognition and computer vision<br />
- Programming experience in C++<br />
<br />
Contact: Please send your resume to job@b-com.com<br />
<br />
== Year 2012 ==<br />
<br />
=== Technology Officer in Biomedical Image Computing & Modelling, University of Sheffield, UK ===<br />
<br />
''' Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Sheffield, UK ''' <br />
<br />
Posted: Nov 5th 2012 \<br />
Closes: Nov 21st 2012<br />
<br />
''* About Sheffield ''<br />
<br />
Mechanical Engineering has been a major discipline in the University of Sheffield since its foundation in 1905. In the most recent Research Assessment Exercise the Department came second in the country in the league table of Mechanical Engineering departments, and achieved an "Excellent" rating in the last Teaching Quality Assessment. The Department currently has 41 members of academic staff who support the learning and development of an ever-growing undergraduate and postgraduate student body. For more information on the Department please see our web site http://www.shef.ac.uk/mecheng/.<br />
<br />
The INSIGNEO Institute for in silico Medicine is an initiative between the Faculty of Engineering and the Faculty of Medicine at the University of Sheffield and the Sheffield Teaching Hospitals Foundation Trust. INSIGNEO will realise the scientific ambition behind the Virtual Physiological Human (VPH), producing a transformational impact on healthcare. INSIGNEO performs cutting edge research in areas of fundamental and applied biomedical modelling, imaging and informatics. It will pursue the research agenda of the VPH initiative; in particular, in the first five years it will focus on the Digital Patient, In Silico Clinical Trials, and Personal Health Forecasting. It will achieve transformational impact on healthcare through multidisciplinary collaboration in strategic areas, which initially will include personalised treatments and independent, active and healthy ageing.<br />
<br />
The Computational Imaging and Simulation Technologies in Biomedicine (CISTIB) Group at the University of Sheffield is part of INSIGNEO. CISTIB focuses on algorithmic and applied research in the areas of computational imaging, modeling and simulation. CISTIB is working in different areas of medical image segmentation, statistical shape analysis, pattern recognition and image-based personalized computational electro-mechanics and fluid dynamics, and modeling of virtual interventions with endovascular and cardiac rhythm management devices. The centre hosts academic members from the University of Sheffield as well as research fellows, research associates, PhD Students and scientific software developers forming a cross-disciplinary team of biomedical engineers, computer scientists, electrical engineers, mechanical engineers, physicists, and mathematicians. <br />
<br />
The main objective of CISTIB is to contribute to the development of technologies for advanced screening, diagnostics, interventional guidance and therapy planning of cardio- and neurovascular diseases as well as growing activity in the musculo-skeletal system. Converging technologies such as computational imaging, computational physiology and virtual implantation of medical devices are integrated with state of the art multimodal acquisition systems to achieve an enhanced interpretation of human physiology and pathology and supply integrative approaches for in silico medical device customization, optimization and image-based efficacy assessment. Core technologies include spatial and temporal image segmentation, non-rigid image registration, multimodal image fusion, pattern recognition, statistical shape analysis, multi-view geometry, image-based tissue property estimation, tissue deformation quantification, computational geometry, image-based mesh generation, computational fluid dynamics and electro-mechanical simulation.<br />
<br />
CISTIB fosters basic and applied research and promotes technology transfer to industry. It participates to a number of national and international research projects funded by the European Commission, and holds collaborations with several national and international companies. CISTIB also very close cooperation with clinical centers at the local level and worldwide and has a strong clinically-oriented translational vision.<br />
<br />
'' * Open positions ''<br />
<br />
You will lead and coordinate a team of Scientific Software Developers that will produce prototypes for applied research projects, clinical translation projects, and technology assessment studies. Your work will also support the research program within CISTIB by enabling its researchers to effectively implement new methods and algorithms. Those prototype technologies that are found to be effective will be translated into commercially available products and services, by means of IPR exploitation agreements with existing companies, or by creating dedicated spin-off companies. The ideal candidate has a considerable experience in managing Technical teams. Previous experience in the area of software development related to the Virtual Physiological Human initiative would be an advantage. Your skill set should be properly balanced between experience on research projects and software management to act as an interface between the needs of the technological and clinical researchers of the centre, and the software developers. All development activities should be steered toward the establishment of a portfolio of methods and technologies (i.e. libraries, software frameworks, etc.). You will play a key role in attracting significant research and technological development funding, in collaboration with other CISTIB members, both from public and private sources.<br />
<br />
We are interested in individuals with excellent communication and leadership skills, able to work in a multidisciplinary and international team and contribute to the visibility of the centre in the international scientific community. The ability to interact with other disciplines is essential. The candidate will cooperate with members of the lab working on related topics as well as with our collaborators at several academic institutions in UK and across Europe.<br />
<br />
'' * How to apply ''<br />
<br />
More information and application through http://sheffield.ac.uk/jobs reference UOS005565.<br />
<br />
=== Job - Software Engineer in medical image processing (medInria) - INRIA Rennes - France ===<br />
<br />
Posted June 26, 2012<br />
<br />
R&D Experienced software engineer / Good knowledge of ITK, VTK and Qt<br />
<br />
As part of the development of medInria ([http://med.inria.fr med.inria.fr]), we are proposing a new position for an experienced engineer at Inria Rennes, France (Visages team), starting from october 2012. The recruited person will work among the national team developing medInria, to develop core features and specific medical image processing plugins from the Visages team. More details on the position are available on [https://www.irisa.fr/visages/_media/positions/position_medinria_nt_2012.pdf the position sheet].<br />
<br />
<br />
=== Job - Software Engineer / Research Specialist Lead - Emory University / Georgia Tech ===<br />
<br />
Posted June 8, 2012<br />
<br />
Research Specialist Lead / Software Engineer<br />
<br />
This position offers great opportunities to work in a high-quality academic environment at Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA. The joint Department of Biomedical Engineering (BME) of Emory University and Georgia Institute of Technology provides one of the top BME programs to foster the next generation of leaders in biomedical engineering worldwide. The Department of Radiology and Imaging Sciences at Emory University School of Medicine provides one of the best education, training and research programs in the country. Successful applicant would work under the supervision of the principal investigator and will collaborate with other faculty members, clinicians, researchers, post-doctoral fellows, graduate and undergraduate students in a research team. This person would be involved in projects focused on multimodality medical imaging (ultrasound, PET/CT, and MRI) with emphasis on medical image analysis and image-guided interventions. As a regular staff of Emory University, this person and her/his family would be eligible for a full range of Emory benefits including health and dental insurance, tuition, and other benefits. <br />
<br />
JOB DESCRIPTION: Under minimal supervision, modifies and writes software programs for image processing and analysis. Develops requirements and specifications and implements computer algorithms in software programs. Performs image quantification using commercial software systems or home-made software programs. Uses independent judgment in applying or adapting scientific techniques. Assists in planning and scheduling research procedures. Performs a variety of laboratory tests and procedures. Analyzes and interprets results of studies. Reviews literature for related research developments and techniques and compiles findings. Monitors laboratory processes to maintain quality assurance standards. Records results of studies, compiles and analyzes data and prepares charts and graphs. Performs related responsibilities as required. <br />
<br />
MINIMUM QUALIFICATIONS: Bachelor's or Master’s degree in computer science, mathematics, electrical engineering, biomedical engineering, or other related fields, and two years of working experience, or equivalent combination of experience, education, and training. Two years of experience in software programming is required. Programming experience with IDL, C++, and MATLAB is preferred. Basic knowledge in medical image processing and analysis is required. Knowledge in medical imaging such as MRI, PET, CT, and ultrasound is a plus but not required. <br />
<br />
CONTACT:<br />
Baowei Fei, PhD, EngD,<br />
Georgia Cancer Coalition Distinguished Scholar<br />
Director of Quantitative BioImaging Laboratory (QBIL)<br />
Emory University and Georgia Institute of Technology<br />
1841 Clifton Road NE, Atlanta, GA 30329, USA<br />
Email: bfei@gatech.edu<br />
<br />
<br />
To apply for the position, send CV and Personal Statement to bfei@gatech.edu <br />
<br />
<br />
== Year 2011 ==<br />
<br />
=== ITK-SNAP Software Developer - University of Pennsylvania ===<br />
<br />
Posted Dec 5, 2011<br />
<br />
The Penn Image Computing and Science Laboratory (PICSL) seeks a qualified C++ programmer to support the development of ITK-SNAP, an interactive software application for biomedical image segmentation. The programmer will work with the principal investigator on an NIH-funded grant to develop the next-generation GUI for ITK-SNAP, accelerate the tool=92s performance, and incorporate multi-modality image segmentation algorithms. Applicants must have a Bachelors degree in computer science or related field. Minimal qualifications are<br />
<br />
* C++ programming (4 years experience)<br />
* Experience with user interface programming, preferably Qt<br />
* Strong interpersonal and communication skills, and ability to work<br />
independently<br />
<br />
Applicants with expertise in the following ares are particularly encouraged to apply:<br />
<br />
* Familiarity with ITK and VTK libraries, and CMake build system<br />
* Image processing, computer vision, and computer graphics<br />
* Strong mathematics background<br />
* GPU programming experience (CUDA, OpenCL)<br />
* Experience working in a research environment<br />
* Advanced degree in related field<br />
<br />
PICSL is a dynamic and growing research group involved in many exciting biomedical imaging projects, including development of novel analysis methodologies; application of the state-of-the-art techniques to clinical studies; and translational research. PICSL is located in Philadelphia, a vibrant city that offers many professional and cultural opportunities. PICSL fosters a friendly, noncompetitive, collaborative environment where each individual member of the laboratory is able to thrive, while also effectively contributing to the group=92s overall programmatic aims.<br />
<br />
The position is funded by a federal grant. Continued employment is subject to performance and availability of grant funding. PICSL has an excellent track record of obtaining research funding and personnel retention. The position features a competitive compensation package with generous fringe benefits.<br />
<br />
The University of Pennsylvania is an equal opportunity, affirmative action employer. Women and minority candidates are strongly encouraged to apply.<br />
<br />
Interested candidates should send an email to the address below. Please include the words =93snap developer=94 on the subject line. Include a brief statement of qualifications relevant to the project, a CV or resume, and a list of 3 references.<br />
<br />
Paul Yushkevich, Ph.D.<br />
Assistant Professor<br />
Penn Image Computing and Science Laboratory (PICSL)<br />
Department of Radiology<br />
University of Pennsylvania<br />
<br />
Email: pauly2 [at] mail [.] med [.] upenn [.] edu<br />
http://picsl.upenn.edu<br />
http://itksnap.org<br />
<br />
<br />
=== Software Engineer(s)-Electrical Geodesics, Inc. ===<br />
<br />
Electrical Geodesics, Inc. (www.egi.com), an international medical device company in the neurology/neuroscience field, is seeking to fill “three” software engineer position. The Software Engineer is responsible for software related product development, product engineering activities, and grant support.<br />
<br />
Opening 1Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• C++ (Objective-C a plus)<br />
Make, CMake, and other build environment expertise.<br />
<br />
• VTK, ITK, Tcl/Tk<br />
<br />
Desired Experiences:<br />
<br />
• MRI Processing<br />
• Cross platform development (Mac, Linux, Windows) experience a plus.<br />
<br />
Opening 2 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java, C, C++ (Objective-C a plus).<br />
<br />
Opening 3 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java (principle), C, C++ (Objective-C a plus)<br />
• Strong knowledge of application server environments.<br />
• Strong profiency in database engineering, and demonstrable knowledge of SQL.<br />
• Experience with Netbeans or Eclipse (and comfortable to use either).<br />
<br />
Full Time, exempt, salary position with benefits.<br />
<br />
To apply for any of the above openings, resume and cover letter should be sent to dmarquez@egi.com<br />
<br />
<br />
=== Master training position, INRIA Sophia Antipolis, France: Prediction of Cardiac Electrophysiology Signal Characteristics from Image Features ===<br />
<br />
<br />
The aim of this project is to analyse both cardiac images and electrophysiology signals in order to explore correlations. Developped features will be mapped on a 3D mesh and overlaid on anatomical images of the heart in order to guide interventions. This project will require image analysis, registration for correlating anatomical and functional information, and machine learning. This project will be in collaboration with Bordeaux University Hospital.<br />
<br />
More information can be found in the detailed job description: <br />
<br />
http://www-sop.inria.fr/asclepios/recrutement/MasterTrainingINRIA2011.pdf<br />
<br />
<br />
== Year 2010 ==<br />
<br />
=== Postdoctoral Position: MIT/Harvard Medical School, Cambridge/Boston, MA ===<br />
<br />
* Posted on December 3rd 2010<br />
<br />
Location: Cambridge/Boston, MA<br />
Type: Postdoctoral position in Medical Robotics<br />
Expires:January 01, 2011<br />
<br />
Job description: We are currently seeking an engineer/computer scientist to join our dynamic team that is developing image-guided robots for accurate and efficient tumor ablation. The person will ideally have medical image processing experience and will be developing user interfaces for controlling robots using information in the medical imaging data.<br />
<br />
Our group involves a collaboration between the Massachusetts Institute of Technology, Massachusetts General Hospital and Brigham and Women's Hospital and has a large amount of technical and clinical expertise in this area.<br />
<br />
Information regarding the open positions and desired qualifications can be provided upon request. Graduate students, post-doc and recent graduates will all be considered. Interested candidates should send a CV and a brief paragraph along to Dr. Conor Walsh at walshcj@mit.edu.<br />
<br />
<br />
=== Two Postdoctoral Positions: Harvard Medical School, Boston, MA ===<br />
<br />
* Posted on November 30th 2010<br />
<br />
Website:http://http://vcp.med.harvard<br />
Location: Boston, MA<br />
Type: Postdoctoral<br />
Expires:January 22, 2011<br />
<br />
Job description: Applications are invited for two postdoctoral-level positions on a collaborative project funded by the European Human Frontiers Programme between the laboratories of Alfonso Martinez-Arias in the Department of Genetics at the University of Cambridge, UK, Kat Hadjantonakis in the Developmental Biology Program at Memorial Sloan Kettering Cancer Center in New York and Jeremy Gunawardena in the Department of Systems Biology at Harvard Medical School in Boston. The project centres on analysing signalling and gene regulation networks in the pre-implantation mouse embryo and in mouse embryonic stem cells, using quantitative measurements, 4D whole-embryo imaging, microfluidic devices and mathematical modelling. The first position is with Hadjantonakis in New York to develop a quantitative image analysis platform for 4D mouse embryo imaging. The successful applicant will need strong technical capabilities in live-cell image analysis, familiarity with software tool development with a focus on usability and the desire to work in close collaboration with experimentalists. The second position is with Gunawardena in Boston to analyse mouse ES cells using microfluidic devices and modelling. The successful applicant will have experience studying mammalian cells in culture using quantitative experimental methods, an interest in exploiting microfluidic technologies and an ability to work with mathematical models of molecular networks. Both positions will require occasional travel between the sites and an annual visit to Cambridge, UK. Interested candidates are asked to send a CV and the contact details of two referees to one of the two addresses below, along with a cover letter stating clearly why his or her background is appropriate for the corresponding position. The deadline for applications is 31 December 2010.<br />
<br />
Kat Hadjantonakis<br />
Developmental Biology Program<br />
Sloan-Kettering Institute<br />
New York, NY 10065,<br />
USA<br />
http://www.ski.edu/hadjantonakis<br />
<br />
Jeremy Gunawardena<br />
Department of Systems Biology<br />
Harvard Medical School<br />
200 Longwood Avenue<br />
Boston, MA 02115<br />
USA<br />
<br />
By e-mail to Nicole Wong, Nicole_Wong@hms.harvard.edu<br />
<br />
http://vcp.med.harvard.edu/<br />
<br />
=== Research Scientist (Junior) - Image and Signal Processing - Rennes,France ===<br />
<br />
* Posted on September 14th 2010<br />
<br />
Bruce Junior Chair position<br />
<br />
http://www.rbucewest.ueb.eu/<br />
<br />
R-Buce Junior Chair position in Biomedical Engineering.<br />
<br />
The UEB - UR1 seeks research scientist applicants working in the broad field of biomedical engineering, with particular focus on themes at the frontiers of ICT and health. Of special interest are the following topics: model-based bio-signal / bio-imaging processing and interpretation, integrative modeling, knowledge-based information representation and interpretation.<br />
<br />
The UEB - UR 1 laboratories involved in biomedical engineering have strong clinical partnerships with a number of medical institutions, including the Rennes University Hospital and the Centre of Cancer Eugène Marquis at Rennes.<br />
<br />
Qualified candidates working in the broad area of biomedical engineering, developing computational tools or multiscale systems-based techniques are encouraged to apply. Required qualifications include a doctorate in engineering or a related field with an outstanding record of publications in internationally recognized journals.<br />
<br />
Interested persons should submit detailed curriculum vitae including academic and professional experience, a list of peer-reviewed publications and any other technical documents relevant to the application.<br />
<br />
salary range : ~40kE/year + relocation<br />
<br />
Please send cover letter and resume to Oscar Acosta / Lotfi Senhadji <br />
(Oscar.Acosta@univ-rennes1.fr, Lotfi.Senhadji@univ-rennes1.fr) <br />
<br />
<br />
== Year 2009 ==<br />
<br />
=== Software Engineer (Junior) - Harvard Medical School ===<br />
<br />
* Posted on August 14th 2009<br />
<br />
The Megason Laboratory in the Department of Systems Biology at Harvard Medical School seeks to hire a Software Engineer for participating in the continued development of GoFigure. The lab’s goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology (www.digitalfish.org). The Software Engineer will be responsible for participating in the continued development of the principle software application for this endeavor called GoFigure. GoFigure recognizes and tracks cells in extremely large 4-dimensional (xyzt) image sets and digitizes that data into a database. GoFigure is written in C++, is cross-platform and uses Qt, MySQL, VTK (the Visualization Toolkit), ITK (Insight Segmentation and Registration Toolkit), CMake. The project is managed using Subversion, Doxygen for documentation generation, CTest and CDash for testing. The successful applicant should have a strong background in programming and work well in an academic environment. Interests in application development, image processing, microscopy, and systems biology are also a plus.<br />
<br />
'''Job Duties'''<br />
<br />
* Participate in software development project for GoFigure. GoFigure is developed by a team of ~4 which is lead by a Senior Research Engineer<br />
* Responsible for the development and testing of code as specified by management (senior software engineer and lab director). Incumbent will write code and will assist management in integration of code into GoFigure<br />
* Performs ongoing modifications and solution alternatives to accomplish research requirements of GoFigure software<br />
* Collaborates with researchers to define new strategies, approaches, methods and techniques to enhance research efforts<br />
* Participate in regular lab meetings, journal club presentations, and retreats<br />
* Other duties as assigned<br />
<br />
Please send cover letter and resume to Sean Megason<br />
(megason@hms.harvard.edu) <br />
<br />
=== Computer Programming - Image Guided Intervention ===<br />
<br />
* Posted Aug 2009,<br />
<br />
Department of Medicine at Harvard Medical School and Beth Israel Deaconess Medical Center is looking to hire a full time software engineer with strong background in computer vision and ITK/VTK. Intrested applicant should send a CV to :<br />
<br />
Reza Nezafat, Ph.D. rnezafat@bidmc.harvard.edu<br />
<br />
<br />
== Year 2008 ==<br />
<br />
=== Staff Scientist - Medical Image Processing ===<br />
<br />
* Posted: November, 2008<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 4 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service <br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Radiology and Imaging Sciences<br />
National Institutes of Health Clinical Center<br />
Building 10 Room 1C368X MSC 1182<br />
Bethesda, MD 20892-1182<br />
E-mail: rms@nih.gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== Research Developer - Medical Imaging ===<br />
<br />
'''About Calgary Scientific'''<br />
<br />
Calgary Scientific Inc. (CSI) is a software and intellectual property (IP) development company specializing in sophisticated digital signal, image processing and analysis technology. Our current product line includes customer focused applications for medical imaging and seismic data imaging. These applications offer innovative tools to help professionals to better interpret and analyze data through core innovations around which CSI applications are developed.<br />
<br />
Calgary Scientific is a privately held company with offices in Calgary, Alberta, Canada. The company was formed in 2003 to commercialize leading edge intellectual property into market leading software applications.<br />
<br />
Calgary Scientific works with research teams and individuals across multiple Universities to generate, refine, test, and commercialize breakthrough innovation into market driven commercial applications.<br />
<br />
'''Research Developer – Medical Imaging Role'''<br />
<br />
We are looking for several full-time Research Developers with Medical Image Processing skills who are willing to relocate to Calgary, Alberta, Canada. Duties will include:<br />
<br />
* Incorporating cutting edge research code from around the world into our production quality, C++ core technologies<br />
<br />
* Working with Research Scientists and Research Associates on various medical image processing algorithms<br />
<br />
* Working with QA to design and develop unit and validation tests that meet our ISO 13485 and ISO 14971 requirements<br />
<br />
* Working directly with Agile Product Teams to ensure the rapid integration of new technologies into various medical applications<br />
<br />
This is an excellent opportunity to contribute to the commercialization of market-driven medical imaging applications.<br />
<br />
'''Required Experience/Skills:'''<br />
<br />
* Degree in Engineering, Physics, Computer Science, or related fields<br />
<br />
* 5 or more years of experience in C++ development<br />
<br />
* 1 or more years of matlab and OpenGL experience<br />
<br />
* Applied or advanced math training, particularly in medical image processing or artificial intelligence<br />
<br />
* Demonstrated ability to learn new technologies<br />
<br />
* Desire to contribute to the successful commercialization of leading-edge technology<br />
<br />
'''Beneficial Experience/Skills:'''<br />
<br />
* Algorithm development using ITK<br />
<br />
* Working within an ISO certified environment<br />
<br />
Applications can be sent to careers@calgaryscientific.com<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
=== Post-doctoral Research Openings at Rensselaer Polytechnic Institute ===<br />
<br />
The FARSIGHT project has openings for several post-doctoral associates (or experienced individuals with a Masters degree), starting May 1, 2008. This project is developing an open-source 4-D/5-D image analysis toolkit for advanced biological microscopy of brain tissue, tumors, and immune system components. The required skills include <br />
<br />
* High-quality C++ programming, <br />
* 3-D image processing (segmentation, classification, registration), and <br />
* 3-D graphics programming. <br />
<br />
Prior exposure to ITK and/or VTK, and disciplined software development processes is highly desirable. <br />
<br />
These positions are renewable annually. <br />
<br />
Please contact <br />
Prof. Roysam <br />
by email: Roysam@ecse.rpi.edu.<br />
<br />
Badri Roysam<br />
Professor, Department of Electrical, Computer and Systems Engineering<br />
Associate Director, NSF Center for Subsurface Sensing & Imaging Systems (CenSSIS ERC)<br />
Rensselaer Polytechnic Institute<br />
110 8th Street, Troy, New York 12180-3590.<br />
Office(JEC 7010): 518-276-8067, Lab(JEC 6308): 518-276-8207, Fax: 518-276-8715<br />
Web: http://www.ecse.rpi.edu/~roysam<br />
<br />
=== Senior Developer - Medical Image Processing ===<br />
<br />
Status: Filled<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
<br />
=== Software Engineer, Intuitive Surgical Inc., Sunnyvale California ===<br />
<br />
The da Vinci(r) Surgical system includes six manipulator arms with a total of 41 degrees of freedom, along with a stereo endoscope and 3D video display, with over 600 installations worldwide. Surgeons use it to perform tens of thousands of minimally invasive surgeries per year. da Vinci represents an outstanding platform for the development and application of new technologies to surgery. This position offers an opportunity for a candidate with exceptional software development skills to work on projects ranging from blue-sky research to those ready for transition to product development groups. A successful candidate will be equally comfortable leading architecture development and producing high-quality implementations that lend themselves to re-use, testing, and productization. He or she must excel in a high energy team, must have excellent communication skills and must be able to balance independent production of results with the need to collaborate during planning, system integration, and testing of larger projects. This engineer will work closely with other members of the Applied Research Group and several product development groups on algorithm development, implementation, and systems integration.<br />
<br />
For more details, as well as to upload a resume, please visit our OpenHire listing:<br />
* Position: Software Engineer<br />
* Tracking Code: 220333-609<br />
* Posted: November, 2007<br />
* URL: http://hostedjobs.openhire.com/epostings/jobs/submit.cfm?fuseaction=dspjob&id=23&jobid=220333&company_id=15609&version=1&source=ONLINE&JobOwner=956377&level=levelid1&levelid1=10630&parent=Engineering&startflag=2&CFID=8647986&CFTOKEN=46344848<br />
<br />
<br />
=== Research Scientist Position in Medical Imaging in Brisbane, Australia ===<br />
<br />
CSIRO ICT centre is seeking to fill several positions at the scientist and post-doctoral level to work on neuro-degenerative diseases and brain tumour characterization.<br />
The Biomedical Imaging team part of the Australian e-Health Research centre is a leading Australian medical imaging research group, with a well developed expertise in image registration, extraction of quantitative information (shape, volume, texture), morphometry, soft-tissue modelling (3D meshing, visual and haptic interaction) and data classification. The successful applicants will be involved in activities focused on the development and application of novel techniques for segmentation, registration and analysis of PET and MR images. These positions offer the opportunity to work in a high quality research environment, with strong clinical collaboration. The research scientists and post-doctoral fellows will join a large team (>20 scientists, post-doctoral fellows, and students) in an exciting working environment ideally located in one of the fastest growing city in Australia close to many attractions and beautiful beaches.<br />
More details can be found on the CSIRO career website: <br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F487<br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F9<br />
For further information please contact <br />
Olivier Salvado, PhD<br />
Team Leader Biomedical Imaging<br />
olivier.salvado@csiro.au<br />
<br />
CSIRO ICT Centre<br />
Australian e-Health Research Centre (AEHRC)<br />
Phone: +61 7 3024 1658<br />
Fax: +61 7 3024 1690<br />
Mobile: +61 4 0388 2249<br />
web: http://www.aehrc.net/<br />
<br />
== Year 2007 ==<br />
<br />
=== Summer 2007: National Institutes of Health Postdoc ===<br />
<br />
Post-doctoral fellowships are available in clinical image processing. Specific interest areas are image processing (virtual endoscopy, volumetric visualization, image segmentation, registration, fusion, and algorithm development) and computer-aided diagnosis (feature extraction, classification, and databases). Fellows have access to state-of-the-art whole body MRI, multi-row detector CT and advanced graphics workstations. Candidates must have or soon expect to receive doctorates in applied mathematics or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on image processing or computer visualization and having strong software development and C++ skills are encouraged to apply. Initial appointment is for two years and is renewable thereafter on a periodic basis. NIH is an equal opportunity employer.<br />
<br />
Address applications to: <br />
Jianhua Yao, Ph.D. <br />
Clinical Image Processing Service <br />
Department of Radiology <br />
National Institutes of Health <br />
10 Center Drive Bethesda, MD 20892-1182 <br />
E-mail: jyao@cc.nih.gov <br />
<br />
<br />
=== August 2007 to sept. 2008: Caltech & Harvard Medical School ===<br />
<br />
The Caltech Center of Excellence in Genomic Science (CEGS) is a newly funded initiative that’s driven to digitize life. Our goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology. Our approach called “in toto imaging” is to use confocal/2-photon imaging to image all the cells in developing transgenic zebrafish embryos and special software we are developing called GoFigure to extract complete cell lineages and gene expression patterns.<br />
<br />
We are looking for people with strong experience in C++ programming and VTK/ITK to join our GoFigure development team. There are a number of significant image analysis problems we are addressing including: segmenting cells in space, across time, and across cell division; quantitating protein expression patterns and subcellular localization; developing a standard, cell-based, 4-d atlas of embryonic development; and registering molecular data from thousands of different embryos onto this atlas.<br />
<br />
There are opportunities at the graduate, post-doc, and staff levels. The successful applicant would join our team at Caltech in Pasadena/LA soon and then move with us to my new lab in the Department of Systems Biology at Harvard Medical School in Boston in summer 2008. To apply, please send a cover letter, CV, and letters of reference to me by email (megason@caltech.edu).<br />
<br />
For more information please see below:<br />
www.digitalfish.org <http://www.digitalfish.org/> <br />
or talk to Alexandre Gouaillard or myself at the upcoming NAMIC meeting in Boston ( june 2007 ).<br />
http://www.na-mic.org/Wiki/index.php/NA-MIC_NCBC_Collaboration:3D%2Bt_Cells_Lineage:GoFigure<br />
<br />
Sean Megason<br />
<br />
=== Spring 2007: University of Texas - M. D. Anderson Cancer Center ===<br />
<br />
The Image Processing & Visualization Laboratory (IPVL) has opened positions for a Programmer Analyst, Post Doctorate and Research Scientist to support its core mission in America’s largest cancer center.<br />
<br />
Images handled by the IPVL span the full spectrum of human and animal (small to large) imaging instrumentation for applications that range from research to clinic, all in direct and close interaction with departments and investigators throughout the institution. Computer equipment includes high-end clinical workstations and software, as well as high-end platforms under Windows, Linux or OSX for developments with OpenSource toolkits, IDL or MatLab. Other available equipment include database and compute servers (Windows, Unix/Solaris/Linux), as well as a state-of-the-art 512 CPUs cluster and 32 CPUs SMP, both shared with the institution and entirely dedicated to research.<br />
<br />
The successful candidates will need to demonstrate – in various capacities that depend on the targeted position - expertise and interest in the design, development, implementation or exploitation of advanced imaging applications, ideally in a biomedical setting and with multidimensional, multimodality and quantitative imaging for clinical and research applications. Topics of particular interests are 3D+ imaging (e.g., rendering, segmentation, navigation), non-rigid registration, parametric and quantitative imaging, kinetic modeling, etc. Expertise in modern and relevant languages and toolkits (e.g., C/C++, VTK, ITK, IGSTK) as well as in matching development tools and environments is considered an asset.<br />
<br />
If you believe your experience matches any of these profiles, please send your CV and other relevant information (e.g., three references, statement of interest/qualification for the specific position) to:<br />
<br />
Dr. Luc Bidaut, Ph.D.<br />
Director of the IPVL<br />
E-mail: lbidaut at mdanderson dot org<br />
<br />
== Year 2006 ==<br />
<br />
=== May 2006: National Institutes of Health Staff Scientist Position ===<br />
<br />
'''Staff Scientist'''<br />
Medical Image Processing<br />
Warren G. Magnuson Clinical Center Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applicati!<br />
ons should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html <br />
<br />
=== Spring 2006: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing – Computer-Aided Detection<br />
Warren G. Magnuson Clinical Center <br />
Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
A post-doctoral fellowship is available in three-dimensional radiology image processing. Specific interest areas are virtual endoscopy, volumetric visualization, image segmentation, registration and computer-aided detection (including feature extraction, classification, image databases and observer performance analysis [ROC]). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. Fellows have access to state-of-the-art whole body MRI, multi-detector helical CT, advanced graphics workstations (Windows PC) and Beowulf massively parallel processing cluster. Candidates must have or soon expect to receive doctorates in physics, biophysics, mathematics, statistics, biomedical engineering or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of computer visualization and image processing and having advanced mathematical and computer skills are encouraged to apply. Initial appointment is for one to two years and is renewable thereafter on a periodic basis. Applications should include a CV, brief statement of research interests and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
== Year 2005 ==<br />
<br />
=== Spring/Summer 2005: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing<br />
Department of Radiology<br />
National Institutes of Health<br />
Department of Health and Human Services<br />
<br />
A Post-doctoral fellowship is available in three-dimensional medical<br />
imaging. Specific interest areas are image processing (virtual endoscopy,<br />
volumetric visualization, image segmentation, registration, fusion, and<br />
algorithm development) and computer-aided diagnosis (feature extraction,<br />
classification, and databases). Fellows have access to state-of-the-art<br />
whole body MRI, 16-row detector CT+PET and advanced graphics workstations (PC and Beowulf cluster). Candidates must have or soon expect to receive<br />
doctorates in applied mathematics or computer science. Applicants with a<br />
proven track record as evidenced by peer-reviewed publications on image <br />
processing and having strong software development and C++ skills are encouraged to apply. GPU shader programming experience is a plus. Applications should include a CV and a brief statement of research interests. NIH is an equal opportunity employer. If a US work permit is not available, then the only visa the NIH can provide for this position is a J visa.<br />
<br />
* Address applications to:<br />
<br />
Ingmar Bitter, Ph.D.<br />
Clinical Image Processing Services<br />
Diagnostic Radiology Department<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: ibitter at nih dot gov<br />
<br />
<br />
== Year 2004 ==<br />
<br />
=== November 2004: Kitware ===<br />
<br />
Kitware is seeking to fill positions immediately. We are looking for people who will relocate to the Albany, NY USA area, are willing to work in a small company, and show flexibility in work assignments. Important skills include proficiency in C++, scientific software development, medical image analysis, and/or ITK. Individuals demonstrating expertise in areas that significantly extend Kitware's software skill base are particularly favored. Please send your resume to kitware at kitware.com.<br />
<br />
Will<br />
<br />
William J. Schroeder, Ph.D.<br />
Kitware, Inc.<br />
28 Corporate Drive, Suite 204<br />
Clifton Park, NY 12065<br />
will.schroeder at kitware.com<br />
1-518-371-3971 x102 (phone)<br />
1-518-371-3971 (fax) <br />
<br />
([http://public.kitware.com/pipermail/insight-users/2004-July/009562.html Original post])<br />
<br />
<br />
=== Nov 2004: National Institutes of Health Staff Scientist ===<br />
<br />
Warren G. Magnuson Clinical Center<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
'''Staff Scientist'''<br />
'''Medical Image Processing'''<br />
<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Electrical or Biomedical Engineering, Computer Science, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: RobertsonS at cc dot nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== June 2004: Computer Vision Research Position ===<br />
<br />
'''Computer Vision Research Positions at GE Global Research'''<br />
Visualization and Computer Vision Lab<br />
<br />
We are seeking highly qualified candidates to innovate and develop computer vision technology for commercial and government applications. We are particularly interested in recruiting candidates with expertise in one of the following areas:<br />
<br />
* Machine Learning - applying semantic knowledge to practical vision problems <br />
* Deformable Registration / Deformable Modeling<br />
* Segmentation<br />
* Object Detection and Tracking<br />
<br />
The Visualization & Computer Vision Lab at GE Global Research in Niskayuna, NY conducts basic and applied research in computer vision and closely related areas. With 30 Staff Researchers (most holding a PhD) the lab develops advanced technologies for GE businesses, including GE Security, GE Healthcare, GE Aircraft Engines, GE Power Systems and NBC Universal; Lockheed Martin; and US Government agencies including NIH, DARPA, FBI, AFRL and NIMA. Areas of active research include image segmentation, deformable registration, perceptual organization, texture classification, object detection, event recognition, tracking, camera calibration, optical metrology, video content extraction, change detection, and superresolution.<br />
<br />
We are active users and contributors to ITK and VXL; experience with either of these toolkits is desired. Strong C++ skills along with a superior ability to work in a team environment are essential qualities for successful candidates.<br />
<br />
Interested? Please contact Jim Miller at `millerjv at research.ge.com`<br />
<br />
Visualization & Computer Vision<br />
GE Research<br />
Bldg. KW, Room C218B<br />
P.O. Box 8, Schenectady NY 12301<br />
<br />
<br />
{{ITK/Template/Footer}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Job_Opportunities&diff=56336ITK/Job Opportunities2014-05-16T19:13:16Z<p>Ccagataybilgin: /* Multiple Software Engineer Positions at Intel */</p>
<hr />
<div>Please feel free to post announcements for jobs and positions that are related to ITK and applicants with ITK experience. Once the position has been fulfilled, please update the entry accordingly.<br />
<br />
Please note that they are '''listed according to their post date''', and not their deadline, as this information is missing in some cases. Past positions are kept for the sake of maintaining a small history of them.<br />
<br />
= Current positions (2014) =<br />
<br />
== Multiple Software Engineer Positions at Intel ==<br />
Posted: May. 16th 2014<br />
'''Description''':<br />
The individual will participate in the development of next generation computational lithography tools, which are an important contributor to Intel's march along Moore's Law. The job role includes research and development work for creating new numerical models and algorithms that enable extracting even more resolution out of existing 193nm steppers. The duties also include image analysis, software performance optimization, parallel programming, computational geometry as well as supporting mission critical software in a production environment. The position requires working in a team with other developers, and interfacing with a large technology development organization. Good communication skills with demonstrated attention to detail and results orientation are required.<br />
<br />
'''Minimum Qualifications''':<br />
* PhD degree in Computer Science, Physics, Electrical Engineering, Mechanical Engineering, or a related engineering discipline <br />
Note: due to the multi-disciplinary nature of the work our team is comprised of world leading experts in fields ranging from Optics/Electromagnetism to Chemical Engineering and Robotics<br />
* Demonstrated coding proficiency, preferably in C++<br />
<br />
'''Preferred Qualifications''':<br />
Background in one or more of the following areas:<br />
* Computer Vision & Machine Learning<br />
* Optics & Electromagnetics Theory<br />
* Parallel Programming and algorithms<br />
* Numerical modeling<br />
* Computational geometry<br />
* Computational lithography methods<br />
* Linear/Non-linear optimization<br />
* Big data, Database Systems, UI <br />
<br />
'''Job Location''':<br />
Hillsboro, Oregon. Located in the beautiful Portland Metro Area, 15 miles west of downtown Portland, Intel Oregon is the largest and most complex site in the world, a global center of semiconductor research and manufacturing, and the largest private employer in the state.<br />
<br />
'''About Our Team''':<br />
We are a highly motivated multi-disciplinary team whose expertise range from computer engineering to physics, electrical engineering to chemical engineering. Our team produces world class solutions for computational lithography systems and has won several Intel achievement awards as well as software quality awards. <br />
<br />
Interested individuals should forward their resumes to cemal.c.bilgin@intel.com<br />
<br />
= Past positions =<br />
<br />
<br />
== Year 2013 ==<br />
<br />
<br />
=== Internship position for developing a MR CAD tool ===<br />
Posted: Oct. 29th 2013<br />
<br />
Eigen is making a difference in patient outcomes and care with our innovative medical imaging products, and we’re looking for a software engineer to join our team.<br />
ProFuse, our MRI image fusion product, is being used on patients daily to provide accurate, repeatable biopsies, with the assistance of Eigen’s mechanical guidance. We have a list of improvements in mind to make the system even better, and that’s where you can help us. We need a quality-focused software intern who’s familiar with C++ - if you know the QT framework, so much the better. You’ll be working with our existing team to add features, and lay the foundation for our next generation of products.<br />
<br />
Requirements:<br />
-In progress degree in Computer Science, Mathematics, Physics, Engineering, Medical Imaging or related discipline.<br />
-UI/UX programming experience.<br />
-Strong interpersonal and communication skills.<br />
-Knowledgeable and experienced with C++ language.<br />
<br />
Desirable but not required:<br />
-Experience with medical devices, avionics, or other regulated technical products.<br />
-Familiarity with ITK and VTK libraries.<br />
-Experience with CMake build system.<br />
-Image processing background strongly preferred.<br />
-Strong mathematics background.<br />
-GPU programming experience (CUDA).<br />
<br />
This is a 6 month internship, on-site at our Grass Valley, CA location, but could lead to a full time W2 position.<br />
<br />
Please send your resumes to hr@eigen.com.<br />
<br />
=== PhD position in multi-modal image processing, b<>com Brest, France ===<br />
<br />
Posted: Oct. 28th 2013<br />
<br />
It is increasingly common to combine multiple methods of treatment, i.e., treatment modalities, with the intention to improve patient outcomes and reduce complications. Each treatment modality may consist of (1) multiple images acquired by one or more modalities (e.g. PET and CT) and (2) contextual information (e.g. clinical reports). To improve patient outcome, one approach is to unify the imaging information and the context information so that the therapy planning, therapy guidance and post-treatment evaluation are simplified. In practice, whereas Picture Archive and Communication Systems (PACS), employed in hospital, store multi-modal images and contextual information, simultaneous re-use of both information cannot be done in a simple fashion.<br />
<br />
This Ph.D. will focus on the integration of multi-modal imaging information accrued by contextual information extracted from a PACS.<br />
<br />
A first problem to address is the analysis of multi-modal images (e.g., PET/CT). This analysis requires, for example, image processing (image quality improvement or image artifact reduction) followed by image analysis (segmentation or biomarker extraction). A second problem to investigate is the association of quantitative parameters extracted from multi-modal images with other contextual information. This also involves the automatic generation of clinical reports both associating results of multi-parameter image analysis and contextual information, with the goal of assisting physicians with clinical decisions. It is intended that this Ph.D. will lead to a Clinical Decision Support System demonstrator dedicated to a specific context/pathology (e.g. oncology or neurology).<br />
<br />
The PhD fellowship is funded by b<>com (http://b-com.com) which is a Technology Research Institute located in Brest, Rennes and Lannion (France). This Ph.D thesis will be carried out under the supervision of M. Hatt (research associate, INSERM) and G. Coatrieux, Assistant Professor (Telecom Bretagne) and located at b<>com on the Brest-Iroise Science and Technology Park.<br />
<br />
Expected qualifications:<br />
- Minimum MSc degree (Computer Science)<br />
- Experience in developing medical imaging applications is desirable<br />
- Prior experience in image analysis, pattern recognition and computer vision<br />
- Programming experience in C++<br />
<br />
Contact: Please send your resume to job@b-com.com<br />
<br />
== Year 2012 ==<br />
<br />
=== Technology Officer in Biomedical Image Computing & Modelling, University of Sheffield, UK ===<br />
<br />
''' Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Sheffield, UK ''' <br />
<br />
Posted: Nov 5th 2012 \<br />
Closes: Nov 21st 2012<br />
<br />
''* About Sheffield ''<br />
<br />
Mechanical Engineering has been a major discipline in the University of Sheffield since its foundation in 1905. In the most recent Research Assessment Exercise the Department came second in the country in the league table of Mechanical Engineering departments, and achieved an "Excellent" rating in the last Teaching Quality Assessment. The Department currently has 41 members of academic staff who support the learning and development of an ever-growing undergraduate and postgraduate student body. For more information on the Department please see our web site http://www.shef.ac.uk/mecheng/.<br />
<br />
The INSIGNEO Institute for in silico Medicine is an initiative between the Faculty of Engineering and the Faculty of Medicine at the University of Sheffield and the Sheffield Teaching Hospitals Foundation Trust. INSIGNEO will realise the scientific ambition behind the Virtual Physiological Human (VPH), producing a transformational impact on healthcare. INSIGNEO performs cutting edge research in areas of fundamental and applied biomedical modelling, imaging and informatics. It will pursue the research agenda of the VPH initiative; in particular, in the first five years it will focus on the Digital Patient, In Silico Clinical Trials, and Personal Health Forecasting. It will achieve transformational impact on healthcare through multidisciplinary collaboration in strategic areas, which initially will include personalised treatments and independent, active and healthy ageing.<br />
<br />
The Computational Imaging and Simulation Technologies in Biomedicine (CISTIB) Group at the University of Sheffield is part of INSIGNEO. CISTIB focuses on algorithmic and applied research in the areas of computational imaging, modeling and simulation. CISTIB is working in different areas of medical image segmentation, statistical shape analysis, pattern recognition and image-based personalized computational electro-mechanics and fluid dynamics, and modeling of virtual interventions with endovascular and cardiac rhythm management devices. The centre hosts academic members from the University of Sheffield as well as research fellows, research associates, PhD Students and scientific software developers forming a cross-disciplinary team of biomedical engineers, computer scientists, electrical engineers, mechanical engineers, physicists, and mathematicians. <br />
<br />
The main objective of CISTIB is to contribute to the development of technologies for advanced screening, diagnostics, interventional guidance and therapy planning of cardio- and neurovascular diseases as well as growing activity in the musculo-skeletal system. Converging technologies such as computational imaging, computational physiology and virtual implantation of medical devices are integrated with state of the art multimodal acquisition systems to achieve an enhanced interpretation of human physiology and pathology and supply integrative approaches for in silico medical device customization, optimization and image-based efficacy assessment. Core technologies include spatial and temporal image segmentation, non-rigid image registration, multimodal image fusion, pattern recognition, statistical shape analysis, multi-view geometry, image-based tissue property estimation, tissue deformation quantification, computational geometry, image-based mesh generation, computational fluid dynamics and electro-mechanical simulation.<br />
<br />
CISTIB fosters basic and applied research and promotes technology transfer to industry. It participates to a number of national and international research projects funded by the European Commission, and holds collaborations with several national and international companies. CISTIB also very close cooperation with clinical centers at the local level and worldwide and has a strong clinically-oriented translational vision.<br />
<br />
'' * Open positions ''<br />
<br />
You will lead and coordinate a team of Scientific Software Developers that will produce prototypes for applied research projects, clinical translation projects, and technology assessment studies. Your work will also support the research program within CISTIB by enabling its researchers to effectively implement new methods and algorithms. Those prototype technologies that are found to be effective will be translated into commercially available products and services, by means of IPR exploitation agreements with existing companies, or by creating dedicated spin-off companies. The ideal candidate has a considerable experience in managing Technical teams. Previous experience in the area of software development related to the Virtual Physiological Human initiative would be an advantage. Your skill set should be properly balanced between experience on research projects and software management to act as an interface between the needs of the technological and clinical researchers of the centre, and the software developers. All development activities should be steered toward the establishment of a portfolio of methods and technologies (i.e. libraries, software frameworks, etc.). You will play a key role in attracting significant research and technological development funding, in collaboration with other CISTIB members, both from public and private sources.<br />
<br />
We are interested in individuals with excellent communication and leadership skills, able to work in a multidisciplinary and international team and contribute to the visibility of the centre in the international scientific community. The ability to interact with other disciplines is essential. The candidate will cooperate with members of the lab working on related topics as well as with our collaborators at several academic institutions in UK and across Europe.<br />
<br />
'' * How to apply ''<br />
<br />
More information and application through http://sheffield.ac.uk/jobs reference UOS005565.<br />
<br />
=== Job - Software Engineer in medical image processing (medInria) - INRIA Rennes - France ===<br />
<br />
Posted June 26, 2012<br />
<br />
R&D Experienced software engineer / Good knowledge of ITK, VTK and Qt<br />
<br />
As part of the development of medInria ([http://med.inria.fr med.inria.fr]), we are proposing a new position for an experienced engineer at Inria Rennes, France (Visages team), starting from october 2012. The recruited person will work among the national team developing medInria, to develop core features and specific medical image processing plugins from the Visages team. More details on the position are available on [https://www.irisa.fr/visages/_media/positions/position_medinria_nt_2012.pdf the position sheet].<br />
<br />
<br />
=== Job - Software Engineer / Research Specialist Lead - Emory University / Georgia Tech ===<br />
<br />
Posted June 8, 2012<br />
<br />
Research Specialist Lead / Software Engineer<br />
<br />
This position offers great opportunities to work in a high-quality academic environment at Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA. The joint Department of Biomedical Engineering (BME) of Emory University and Georgia Institute of Technology provides one of the top BME programs to foster the next generation of leaders in biomedical engineering worldwide. The Department of Radiology and Imaging Sciences at Emory University School of Medicine provides one of the best education, training and research programs in the country. Successful applicant would work under the supervision of the principal investigator and will collaborate with other faculty members, clinicians, researchers, post-doctoral fellows, graduate and undergraduate students in a research team. This person would be involved in projects focused on multimodality medical imaging (ultrasound, PET/CT, and MRI) with emphasis on medical image analysis and image-guided interventions. As a regular staff of Emory University, this person and her/his family would be eligible for a full range of Emory benefits including health and dental insurance, tuition, and other benefits. <br />
<br />
JOB DESCRIPTION: Under minimal supervision, modifies and writes software programs for image processing and analysis. Develops requirements and specifications and implements computer algorithms in software programs. Performs image quantification using commercial software systems or home-made software programs. Uses independent judgment in applying or adapting scientific techniques. Assists in planning and scheduling research procedures. Performs a variety of laboratory tests and procedures. Analyzes and interprets results of studies. Reviews literature for related research developments and techniques and compiles findings. Monitors laboratory processes to maintain quality assurance standards. Records results of studies, compiles and analyzes data and prepares charts and graphs. Performs related responsibilities as required. <br />
<br />
MINIMUM QUALIFICATIONS: Bachelor's or Master’s degree in computer science, mathematics, electrical engineering, biomedical engineering, or other related fields, and two years of working experience, or equivalent combination of experience, education, and training. Two years of experience in software programming is required. Programming experience with IDL, C++, and MATLAB is preferred. Basic knowledge in medical image processing and analysis is required. Knowledge in medical imaging such as MRI, PET, CT, and ultrasound is a plus but not required. <br />
<br />
CONTACT:<br />
Baowei Fei, PhD, EngD,<br />
Georgia Cancer Coalition Distinguished Scholar<br />
Director of Quantitative BioImaging Laboratory (QBIL)<br />
Emory University and Georgia Institute of Technology<br />
1841 Clifton Road NE, Atlanta, GA 30329, USA<br />
Email: bfei@gatech.edu<br />
<br />
<br />
To apply for the position, send CV and Personal Statement to bfei@gatech.edu <br />
<br />
<br />
== Year 2011 ==<br />
<br />
=== ITK-SNAP Software Developer - University of Pennsylvania ===<br />
<br />
Posted Dec 5, 2011<br />
<br />
The Penn Image Computing and Science Laboratory (PICSL) seeks a qualified C++ programmer to support the development of ITK-SNAP, an interactive software application for biomedical image segmentation. The programmer will work with the principal investigator on an NIH-funded grant to develop the next-generation GUI for ITK-SNAP, accelerate the tool=92s performance, and incorporate multi-modality image segmentation algorithms. Applicants must have a Bachelors degree in computer science or related field. Minimal qualifications are<br />
<br />
* C++ programming (4 years experience)<br />
* Experience with user interface programming, preferably Qt<br />
* Strong interpersonal and communication skills, and ability to work<br />
independently<br />
<br />
Applicants with expertise in the following ares are particularly encouraged to apply:<br />
<br />
* Familiarity with ITK and VTK libraries, and CMake build system<br />
* Image processing, computer vision, and computer graphics<br />
* Strong mathematics background<br />
* GPU programming experience (CUDA, OpenCL)<br />
* Experience working in a research environment<br />
* Advanced degree in related field<br />
<br />
PICSL is a dynamic and growing research group involved in many exciting biomedical imaging projects, including development of novel analysis methodologies; application of the state-of-the-art techniques to clinical studies; and translational research. PICSL is located in Philadelphia, a vibrant city that offers many professional and cultural opportunities. PICSL fosters a friendly, noncompetitive, collaborative environment where each individual member of the laboratory is able to thrive, while also effectively contributing to the group=92s overall programmatic aims.<br />
<br />
The position is funded by a federal grant. Continued employment is subject to performance and availability of grant funding. PICSL has an excellent track record of obtaining research funding and personnel retention. The position features a competitive compensation package with generous fringe benefits.<br />
<br />
The University of Pennsylvania is an equal opportunity, affirmative action employer. Women and minority candidates are strongly encouraged to apply.<br />
<br />
Interested candidates should send an email to the address below. Please include the words =93snap developer=94 on the subject line. Include a brief statement of qualifications relevant to the project, a CV or resume, and a list of 3 references.<br />
<br />
Paul Yushkevich, Ph.D.<br />
Assistant Professor<br />
Penn Image Computing and Science Laboratory (PICSL)<br />
Department of Radiology<br />
University of Pennsylvania<br />
<br />
Email: pauly2 [at] mail [.] med [.] upenn [.] edu<br />
http://picsl.upenn.edu<br />
http://itksnap.org<br />
<br />
<br />
=== Software Engineer(s)-Electrical Geodesics, Inc. ===<br />
<br />
Electrical Geodesics, Inc. (www.egi.com), an international medical device company in the neurology/neuroscience field, is seeking to fill “three” software engineer position. The Software Engineer is responsible for software related product development, product engineering activities, and grant support.<br />
<br />
Opening 1Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• C++ (Objective-C a plus)<br />
Make, CMake, and other build environment expertise.<br />
<br />
• VTK, ITK, Tcl/Tk<br />
<br />
Desired Experiences:<br />
<br />
• MRI Processing<br />
• Cross platform development (Mac, Linux, Windows) experience a plus.<br />
<br />
Opening 2 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java, C, C++ (Objective-C a plus).<br />
<br />
Opening 3 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java (principle), C, C++ (Objective-C a plus)<br />
• Strong knowledge of application server environments.<br />
• Strong profiency in database engineering, and demonstrable knowledge of SQL.<br />
• Experience with Netbeans or Eclipse (and comfortable to use either).<br />
<br />
Full Time, exempt, salary position with benefits.<br />
<br />
To apply for any of the above openings, resume and cover letter should be sent to dmarquez@egi.com<br />
<br />
<br />
=== Master training position, INRIA Sophia Antipolis, France: Prediction of Cardiac Electrophysiology Signal Characteristics from Image Features ===<br />
<br />
<br />
The aim of this project is to analyse both cardiac images and electrophysiology signals in order to explore correlations. Developped features will be mapped on a 3D mesh and overlaid on anatomical images of the heart in order to guide interventions. This project will require image analysis, registration for correlating anatomical and functional information, and machine learning. This project will be in collaboration with Bordeaux University Hospital.<br />
<br />
More information can be found in the detailed job description: <br />
<br />
http://www-sop.inria.fr/asclepios/recrutement/MasterTrainingINRIA2011.pdf<br />
<br />
<br />
== Year 2010 ==<br />
<br />
=== Postdoctoral Position: MIT/Harvard Medical School, Cambridge/Boston, MA ===<br />
<br />
* Posted on December 3rd 2010<br />
<br />
Location: Cambridge/Boston, MA<br />
Type: Postdoctoral position in Medical Robotics<br />
Expires:January 01, 2011<br />
<br />
Job description: We are currently seeking an engineer/computer scientist to join our dynamic team that is developing image-guided robots for accurate and efficient tumor ablation. The person will ideally have medical image processing experience and will be developing user interfaces for controlling robots using information in the medical imaging data.<br />
<br />
Our group involves a collaboration between the Massachusetts Institute of Technology, Massachusetts General Hospital and Brigham and Women's Hospital and has a large amount of technical and clinical expertise in this area.<br />
<br />
Information regarding the open positions and desired qualifications can be provided upon request. Graduate students, post-doc and recent graduates will all be considered. Interested candidates should send a CV and a brief paragraph along to Dr. Conor Walsh at walshcj@mit.edu.<br />
<br />
<br />
=== Two Postdoctoral Positions: Harvard Medical School, Boston, MA ===<br />
<br />
* Posted on November 30th 2010<br />
<br />
Website:http://http://vcp.med.harvard<br />
Location: Boston, MA<br />
Type: Postdoctoral<br />
Expires:January 22, 2011<br />
<br />
Job description: Applications are invited for two postdoctoral-level positions on a collaborative project funded by the European Human Frontiers Programme between the laboratories of Alfonso Martinez-Arias in the Department of Genetics at the University of Cambridge, UK, Kat Hadjantonakis in the Developmental Biology Program at Memorial Sloan Kettering Cancer Center in New York and Jeremy Gunawardena in the Department of Systems Biology at Harvard Medical School in Boston. The project centres on analysing signalling and gene regulation networks in the pre-implantation mouse embryo and in mouse embryonic stem cells, using quantitative measurements, 4D whole-embryo imaging, microfluidic devices and mathematical modelling. The first position is with Hadjantonakis in New York to develop a quantitative image analysis platform for 4D mouse embryo imaging. The successful applicant will need strong technical capabilities in live-cell image analysis, familiarity with software tool development with a focus on usability and the desire to work in close collaboration with experimentalists. The second position is with Gunawardena in Boston to analyse mouse ES cells using microfluidic devices and modelling. The successful applicant will have experience studying mammalian cells in culture using quantitative experimental methods, an interest in exploiting microfluidic technologies and an ability to work with mathematical models of molecular networks. Both positions will require occasional travel between the sites and an annual visit to Cambridge, UK. Interested candidates are asked to send a CV and the contact details of two referees to one of the two addresses below, along with a cover letter stating clearly why his or her background is appropriate for the corresponding position. The deadline for applications is 31 December 2010.<br />
<br />
Kat Hadjantonakis<br />
Developmental Biology Program<br />
Sloan-Kettering Institute<br />
New York, NY 10065,<br />
USA<br />
http://www.ski.edu/hadjantonakis<br />
<br />
Jeremy Gunawardena<br />
Department of Systems Biology<br />
Harvard Medical School<br />
200 Longwood Avenue<br />
Boston, MA 02115<br />
USA<br />
<br />
By e-mail to Nicole Wong, Nicole_Wong@hms.harvard.edu<br />
<br />
http://vcp.med.harvard.edu/<br />
<br />
=== Research Scientist (Junior) - Image and Signal Processing - Rennes,France ===<br />
<br />
* Posted on September 14th 2010<br />
<br />
Bruce Junior Chair position<br />
<br />
http://www.rbucewest.ueb.eu/<br />
<br />
R-Buce Junior Chair position in Biomedical Engineering.<br />
<br />
The UEB - UR1 seeks research scientist applicants working in the broad field of biomedical engineering, with particular focus on themes at the frontiers of ICT and health. Of special interest are the following topics: model-based bio-signal / bio-imaging processing and interpretation, integrative modeling, knowledge-based information representation and interpretation.<br />
<br />
The UEB - UR 1 laboratories involved in biomedical engineering have strong clinical partnerships with a number of medical institutions, including the Rennes University Hospital and the Centre of Cancer Eugène Marquis at Rennes.<br />
<br />
Qualified candidates working in the broad area of biomedical engineering, developing computational tools or multiscale systems-based techniques are encouraged to apply. Required qualifications include a doctorate in engineering or a related field with an outstanding record of publications in internationally recognized journals.<br />
<br />
Interested persons should submit detailed curriculum vitae including academic and professional experience, a list of peer-reviewed publications and any other technical documents relevant to the application.<br />
<br />
salary range : ~40kE/year + relocation<br />
<br />
Please send cover letter and resume to Oscar Acosta / Lotfi Senhadji <br />
(Oscar.Acosta@univ-rennes1.fr, Lotfi.Senhadji@univ-rennes1.fr) <br />
<br />
<br />
== Year 2009 ==<br />
<br />
=== Software Engineer (Junior) - Harvard Medical School ===<br />
<br />
* Posted on August 14th 2009<br />
<br />
The Megason Laboratory in the Department of Systems Biology at Harvard Medical School seeks to hire a Software Engineer for participating in the continued development of GoFigure. The lab’s goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology (www.digitalfish.org). The Software Engineer will be responsible for participating in the continued development of the principle software application for this endeavor called GoFigure. GoFigure recognizes and tracks cells in extremely large 4-dimensional (xyzt) image sets and digitizes that data into a database. GoFigure is written in C++, is cross-platform and uses Qt, MySQL, VTK (the Visualization Toolkit), ITK (Insight Segmentation and Registration Toolkit), CMake. The project is managed using Subversion, Doxygen for documentation generation, CTest and CDash for testing. The successful applicant should have a strong background in programming and work well in an academic environment. Interests in application development, image processing, microscopy, and systems biology are also a plus.<br />
<br />
'''Job Duties'''<br />
<br />
* Participate in software development project for GoFigure. GoFigure is developed by a team of ~4 which is lead by a Senior Research Engineer<br />
* Responsible for the development and testing of code as specified by management (senior software engineer and lab director). Incumbent will write code and will assist management in integration of code into GoFigure<br />
* Performs ongoing modifications and solution alternatives to accomplish research requirements of GoFigure software<br />
* Collaborates with researchers to define new strategies, approaches, methods and techniques to enhance research efforts<br />
* Participate in regular lab meetings, journal club presentations, and retreats<br />
* Other duties as assigned<br />
<br />
Please send cover letter and resume to Sean Megason<br />
(megason@hms.harvard.edu) <br />
<br />
=== Computer Programming - Image Guided Intervention ===<br />
<br />
* Posted Aug 2009,<br />
<br />
Department of Medicine at Harvard Medical School and Beth Israel Deaconess Medical Center is looking to hire a full time software engineer with strong background in computer vision and ITK/VTK. Intrested applicant should send a CV to :<br />
<br />
Reza Nezafat, Ph.D. rnezafat@bidmc.harvard.edu<br />
<br />
<br />
== Year 2008 ==<br />
<br />
=== Staff Scientist - Medical Image Processing ===<br />
<br />
* Posted: November, 2008<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 4 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service <br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Radiology and Imaging Sciences<br />
National Institutes of Health Clinical Center<br />
Building 10 Room 1C368X MSC 1182<br />
Bethesda, MD 20892-1182<br />
E-mail: rms@nih.gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== Research Developer - Medical Imaging ===<br />
<br />
'''About Calgary Scientific'''<br />
<br />
Calgary Scientific Inc. (CSI) is a software and intellectual property (IP) development company specializing in sophisticated digital signal, image processing and analysis technology. Our current product line includes customer focused applications for medical imaging and seismic data imaging. These applications offer innovative tools to help professionals to better interpret and analyze data through core innovations around which CSI applications are developed.<br />
<br />
Calgary Scientific is a privately held company with offices in Calgary, Alberta, Canada. The company was formed in 2003 to commercialize leading edge intellectual property into market leading software applications.<br />
<br />
Calgary Scientific works with research teams and individuals across multiple Universities to generate, refine, test, and commercialize breakthrough innovation into market driven commercial applications.<br />
<br />
'''Research Developer – Medical Imaging Role'''<br />
<br />
We are looking for several full-time Research Developers with Medical Image Processing skills who are willing to relocate to Calgary, Alberta, Canada. Duties will include:<br />
<br />
* Incorporating cutting edge research code from around the world into our production quality, C++ core technologies<br />
<br />
* Working with Research Scientists and Research Associates on various medical image processing algorithms<br />
<br />
* Working with QA to design and develop unit and validation tests that meet our ISO 13485 and ISO 14971 requirements<br />
<br />
* Working directly with Agile Product Teams to ensure the rapid integration of new technologies into various medical applications<br />
<br />
This is an excellent opportunity to contribute to the commercialization of market-driven medical imaging applications.<br />
<br />
'''Required Experience/Skills:'''<br />
<br />
* Degree in Engineering, Physics, Computer Science, or related fields<br />
<br />
* 5 or more years of experience in C++ development<br />
<br />
* 1 or more years of matlab and OpenGL experience<br />
<br />
* Applied or advanced math training, particularly in medical image processing or artificial intelligence<br />
<br />
* Demonstrated ability to learn new technologies<br />
<br />
* Desire to contribute to the successful commercialization of leading-edge technology<br />
<br />
'''Beneficial Experience/Skills:'''<br />
<br />
* Algorithm development using ITK<br />
<br />
* Working within an ISO certified environment<br />
<br />
Applications can be sent to careers@calgaryscientific.com<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
=== Post-doctoral Research Openings at Rensselaer Polytechnic Institute ===<br />
<br />
The FARSIGHT project has openings for several post-doctoral associates (or experienced individuals with a Masters degree), starting May 1, 2008. This project is developing an open-source 4-D/5-D image analysis toolkit for advanced biological microscopy of brain tissue, tumors, and immune system components. The required skills include <br />
<br />
* High-quality C++ programming, <br />
* 3-D image processing (segmentation, classification, registration), and <br />
* 3-D graphics programming. <br />
<br />
Prior exposure to ITK and/or VTK, and disciplined software development processes is highly desirable. <br />
<br />
These positions are renewable annually. <br />
<br />
Please contact <br />
Prof. Roysam <br />
by email: Roysam@ecse.rpi.edu.<br />
<br />
Badri Roysam<br />
Professor, Department of Electrical, Computer and Systems Engineering<br />
Associate Director, NSF Center for Subsurface Sensing & Imaging Systems (CenSSIS ERC)<br />
Rensselaer Polytechnic Institute<br />
110 8th Street, Troy, New York 12180-3590.<br />
Office(JEC 7010): 518-276-8067, Lab(JEC 6308): 518-276-8207, Fax: 518-276-8715<br />
Web: http://www.ecse.rpi.edu/~roysam<br />
<br />
=== Senior Developer - Medical Image Processing ===<br />
<br />
Status: Filled<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
<br />
=== Software Engineer, Intuitive Surgical Inc., Sunnyvale California ===<br />
<br />
The da Vinci(r) Surgical system includes six manipulator arms with a total of 41 degrees of freedom, along with a stereo endoscope and 3D video display, with over 600 installations worldwide. Surgeons use it to perform tens of thousands of minimally invasive surgeries per year. da Vinci represents an outstanding platform for the development and application of new technologies to surgery. This position offers an opportunity for a candidate with exceptional software development skills to work on projects ranging from blue-sky research to those ready for transition to product development groups. A successful candidate will be equally comfortable leading architecture development and producing high-quality implementations that lend themselves to re-use, testing, and productization. He or she must excel in a high energy team, must have excellent communication skills and must be able to balance independent production of results with the need to collaborate during planning, system integration, and testing of larger projects. This engineer will work closely with other members of the Applied Research Group and several product development groups on algorithm development, implementation, and systems integration.<br />
<br />
For more details, as well as to upload a resume, please visit our OpenHire listing:<br />
* Position: Software Engineer<br />
* Tracking Code: 220333-609<br />
* Posted: November, 2007<br />
* URL: http://hostedjobs.openhire.com/epostings/jobs/submit.cfm?fuseaction=dspjob&id=23&jobid=220333&company_id=15609&version=1&source=ONLINE&JobOwner=956377&level=levelid1&levelid1=10630&parent=Engineering&startflag=2&CFID=8647986&CFTOKEN=46344848<br />
<br />
<br />
=== Research Scientist Position in Medical Imaging in Brisbane, Australia ===<br />
<br />
CSIRO ICT centre is seeking to fill several positions at the scientist and post-doctoral level to work on neuro-degenerative diseases and brain tumour characterization.<br />
The Biomedical Imaging team part of the Australian e-Health Research centre is a leading Australian medical imaging research group, with a well developed expertise in image registration, extraction of quantitative information (shape, volume, texture), morphometry, soft-tissue modelling (3D meshing, visual and haptic interaction) and data classification. The successful applicants will be involved in activities focused on the development and application of novel techniques for segmentation, registration and analysis of PET and MR images. These positions offer the opportunity to work in a high quality research environment, with strong clinical collaboration. The research scientists and post-doctoral fellows will join a large team (>20 scientists, post-doctoral fellows, and students) in an exciting working environment ideally located in one of the fastest growing city in Australia close to many attractions and beautiful beaches.<br />
More details can be found on the CSIRO career website: <br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F487<br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F9<br />
For further information please contact <br />
Olivier Salvado, PhD<br />
Team Leader Biomedical Imaging<br />
olivier.salvado@csiro.au<br />
<br />
CSIRO ICT Centre<br />
Australian e-Health Research Centre (AEHRC)<br />
Phone: +61 7 3024 1658<br />
Fax: +61 7 3024 1690<br />
Mobile: +61 4 0388 2249<br />
web: http://www.aehrc.net/<br />
<br />
== Year 2007 ==<br />
<br />
=== Summer 2007: National Institutes of Health Postdoc ===<br />
<br />
Post-doctoral fellowships are available in clinical image processing. Specific interest areas are image processing (virtual endoscopy, volumetric visualization, image segmentation, registration, fusion, and algorithm development) and computer-aided diagnosis (feature extraction, classification, and databases). Fellows have access to state-of-the-art whole body MRI, multi-row detector CT and advanced graphics workstations. Candidates must have or soon expect to receive doctorates in applied mathematics or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on image processing or computer visualization and having strong software development and C++ skills are encouraged to apply. Initial appointment is for two years and is renewable thereafter on a periodic basis. NIH is an equal opportunity employer.<br />
<br />
Address applications to: <br />
Jianhua Yao, Ph.D. <br />
Clinical Image Processing Service <br />
Department of Radiology <br />
National Institutes of Health <br />
10 Center Drive Bethesda, MD 20892-1182 <br />
E-mail: jyao@cc.nih.gov <br />
<br />
<br />
=== August 2007 to sept. 2008: Caltech & Harvard Medical School ===<br />
<br />
The Caltech Center of Excellence in Genomic Science (CEGS) is a newly funded initiative that’s driven to digitize life. Our goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology. Our approach called “in toto imaging” is to use confocal/2-photon imaging to image all the cells in developing transgenic zebrafish embryos and special software we are developing called GoFigure to extract complete cell lineages and gene expression patterns.<br />
<br />
We are looking for people with strong experience in C++ programming and VTK/ITK to join our GoFigure development team. There are a number of significant image analysis problems we are addressing including: segmenting cells in space, across time, and across cell division; quantitating protein expression patterns and subcellular localization; developing a standard, cell-based, 4-d atlas of embryonic development; and registering molecular data from thousands of different embryos onto this atlas.<br />
<br />
There are opportunities at the graduate, post-doc, and staff levels. The successful applicant would join our team at Caltech in Pasadena/LA soon and then move with us to my new lab in the Department of Systems Biology at Harvard Medical School in Boston in summer 2008. To apply, please send a cover letter, CV, and letters of reference to me by email (megason@caltech.edu).<br />
<br />
For more information please see below:<br />
www.digitalfish.org <http://www.digitalfish.org/> <br />
or talk to Alexandre Gouaillard or myself at the upcoming NAMIC meeting in Boston ( june 2007 ).<br />
http://www.na-mic.org/Wiki/index.php/NA-MIC_NCBC_Collaboration:3D%2Bt_Cells_Lineage:GoFigure<br />
<br />
Sean Megason<br />
<br />
=== Spring 2007: University of Texas - M. D. Anderson Cancer Center ===<br />
<br />
The Image Processing & Visualization Laboratory (IPVL) has opened positions for a Programmer Analyst, Post Doctorate and Research Scientist to support its core mission in America’s largest cancer center.<br />
<br />
Images handled by the IPVL span the full spectrum of human and animal (small to large) imaging instrumentation for applications that range from research to clinic, all in direct and close interaction with departments and investigators throughout the institution. Computer equipment includes high-end clinical workstations and software, as well as high-end platforms under Windows, Linux or OSX for developments with OpenSource toolkits, IDL or MatLab. Other available equipment include database and compute servers (Windows, Unix/Solaris/Linux), as well as a state-of-the-art 512 CPUs cluster and 32 CPUs SMP, both shared with the institution and entirely dedicated to research.<br />
<br />
The successful candidates will need to demonstrate – in various capacities that depend on the targeted position - expertise and interest in the design, development, implementation or exploitation of advanced imaging applications, ideally in a biomedical setting and with multidimensional, multimodality and quantitative imaging for clinical and research applications. Topics of particular interests are 3D+ imaging (e.g., rendering, segmentation, navigation), non-rigid registration, parametric and quantitative imaging, kinetic modeling, etc. Expertise in modern and relevant languages and toolkits (e.g., C/C++, VTK, ITK, IGSTK) as well as in matching development tools and environments is considered an asset.<br />
<br />
If you believe your experience matches any of these profiles, please send your CV and other relevant information (e.g., three references, statement of interest/qualification for the specific position) to:<br />
<br />
Dr. Luc Bidaut, Ph.D.<br />
Director of the IPVL<br />
E-mail: lbidaut at mdanderson dot org<br />
<br />
== Year 2006 ==<br />
<br />
=== May 2006: National Institutes of Health Staff Scientist Position ===<br />
<br />
'''Staff Scientist'''<br />
Medical Image Processing<br />
Warren G. Magnuson Clinical Center Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applicati!<br />
ons should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html <br />
<br />
=== Spring 2006: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing – Computer-Aided Detection<br />
Warren G. Magnuson Clinical Center <br />
Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
A post-doctoral fellowship is available in three-dimensional radiology image processing. Specific interest areas are virtual endoscopy, volumetric visualization, image segmentation, registration and computer-aided detection (including feature extraction, classification, image databases and observer performance analysis [ROC]). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. Fellows have access to state-of-the-art whole body MRI, multi-detector helical CT, advanced graphics workstations (Windows PC) and Beowulf massively parallel processing cluster. Candidates must have or soon expect to receive doctorates in physics, biophysics, mathematics, statistics, biomedical engineering or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of computer visualization and image processing and having advanced mathematical and computer skills are encouraged to apply. Initial appointment is for one to two years and is renewable thereafter on a periodic basis. Applications should include a CV, brief statement of research interests and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
== Year 2005 ==<br />
<br />
=== Spring/Summer 2005: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing<br />
Department of Radiology<br />
National Institutes of Health<br />
Department of Health and Human Services<br />
<br />
A Post-doctoral fellowship is available in three-dimensional medical<br />
imaging. Specific interest areas are image processing (virtual endoscopy,<br />
volumetric visualization, image segmentation, registration, fusion, and<br />
algorithm development) and computer-aided diagnosis (feature extraction,<br />
classification, and databases). Fellows have access to state-of-the-art<br />
whole body MRI, 16-row detector CT+PET and advanced graphics workstations (PC and Beowulf cluster). Candidates must have or soon expect to receive<br />
doctorates in applied mathematics or computer science. Applicants with a<br />
proven track record as evidenced by peer-reviewed publications on image <br />
processing and having strong software development and C++ skills are encouraged to apply. GPU shader programming experience is a plus. Applications should include a CV and a brief statement of research interests. NIH is an equal opportunity employer. If a US work permit is not available, then the only visa the NIH can provide for this position is a J visa.<br />
<br />
* Address applications to:<br />
<br />
Ingmar Bitter, Ph.D.<br />
Clinical Image Processing Services<br />
Diagnostic Radiology Department<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: ibitter at nih dot gov<br />
<br />
<br />
== Year 2004 ==<br />
<br />
=== November 2004: Kitware ===<br />
<br />
Kitware is seeking to fill positions immediately. We are looking for people who will relocate to the Albany, NY USA area, are willing to work in a small company, and show flexibility in work assignments. Important skills include proficiency in C++, scientific software development, medical image analysis, and/or ITK. Individuals demonstrating expertise in areas that significantly extend Kitware's software skill base are particularly favored. Please send your resume to kitware at kitware.com.<br />
<br />
Will<br />
<br />
William J. Schroeder, Ph.D.<br />
Kitware, Inc.<br />
28 Corporate Drive, Suite 204<br />
Clifton Park, NY 12065<br />
will.schroeder at kitware.com<br />
1-518-371-3971 x102 (phone)<br />
1-518-371-3971 (fax) <br />
<br />
([http://public.kitware.com/pipermail/insight-users/2004-July/009562.html Original post])<br />
<br />
<br />
=== Nov 2004: National Institutes of Health Staff Scientist ===<br />
<br />
Warren G. Magnuson Clinical Center<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
'''Staff Scientist'''<br />
'''Medical Image Processing'''<br />
<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Electrical or Biomedical Engineering, Computer Science, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: RobertsonS at cc dot nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== June 2004: Computer Vision Research Position ===<br />
<br />
'''Computer Vision Research Positions at GE Global Research'''<br />
Visualization and Computer Vision Lab<br />
<br />
We are seeking highly qualified candidates to innovate and develop computer vision technology for commercial and government applications. We are particularly interested in recruiting candidates with expertise in one of the following areas:<br />
<br />
* Machine Learning - applying semantic knowledge to practical vision problems <br />
* Deformable Registration / Deformable Modeling<br />
* Segmentation<br />
* Object Detection and Tracking<br />
<br />
The Visualization & Computer Vision Lab at GE Global Research in Niskayuna, NY conducts basic and applied research in computer vision and closely related areas. With 30 Staff Researchers (most holding a PhD) the lab develops advanced technologies for GE businesses, including GE Security, GE Healthcare, GE Aircraft Engines, GE Power Systems and NBC Universal; Lockheed Martin; and US Government agencies including NIH, DARPA, FBI, AFRL and NIMA. Areas of active research include image segmentation, deformable registration, perceptual organization, texture classification, object detection, event recognition, tracking, camera calibration, optical metrology, video content extraction, change detection, and superresolution.<br />
<br />
We are active users and contributors to ITK and VXL; experience with either of these toolkits is desired. Strong C++ skills along with a superior ability to work in a team environment are essential qualities for successful candidates.<br />
<br />
Interested? Please contact Jim Miller at `millerjv at research.ge.com`<br />
<br />
Visualization & Computer Vision<br />
GE Research<br />
Bldg. KW, Room C218B<br />
P.O. Box 8, Schenectady NY 12301<br />
<br />
<br />
{{ITK/Template/Footer}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Job_Opportunities&diff=56335ITK/Job Opportunities2014-05-16T19:12:53Z<p>Ccagataybilgin: /* Current positions (2014) */</p>
<hr />
<div>Please feel free to post announcements for jobs and positions that are related to ITK and applicants with ITK experience. Once the position has been fulfilled, please update the entry accordingly.<br />
<br />
Please note that they are '''listed according to their post date''', and not their deadline, as this information is missing in some cases. Past positions are kept for the sake of maintaining a small history of them.<br />
<br />
= Current positions (2014) =<br />
<br />
== Multiple Software Engineer Positions at Intel ==<br />
Posted: Oct. 29th 2013<br />
'''Description''':<br />
The individual will participate in the development of next generation computational lithography tools, which are an important contributor to Intel's march along Moore's Law. The job role includes research and development work for creating new numerical models and algorithms that enable extracting even more resolution out of existing 193nm steppers. The duties also include image analysis, software performance optimization, parallel programming, computational geometry as well as supporting mission critical software in a production environment. The position requires working in a team with other developers, and interfacing with a large technology development organization. Good communication skills with demonstrated attention to detail and results orientation are required.<br />
<br />
'''Minimum Qualifications''':<br />
* PhD degree in Computer Science, Physics, Electrical Engineering, Mechanical Engineering, or a related engineering discipline <br />
Note: due to the multi-disciplinary nature of the work our team is comprised of world leading experts in fields ranging from Optics/Electromagnetism to Chemical Engineering and Robotics<br />
* Demonstrated coding proficiency, preferably in C++<br />
<br />
'''Preferred Qualifications''':<br />
Background in one or more of the following areas:<br />
* Computer Vision & Machine Learning<br />
* Optics & Electromagnetics Theory<br />
* Parallel Programming and algorithms<br />
* Numerical modeling<br />
* Computational geometry<br />
* Computational lithography methods<br />
* Linear/Non-linear optimization<br />
* Big data, Database Systems, UI <br />
<br />
'''Job Location''':<br />
Hillsboro, Oregon. Located in the beautiful Portland Metro Area, 15 miles west of downtown Portland, Intel Oregon is the largest and most complex site in the world, a global center of semiconductor research and manufacturing, and the largest private employer in the state.<br />
<br />
'''About Our Team''':<br />
We are a highly motivated multi-disciplinary team whose expertise range from computer engineering to physics, electrical engineering to chemical engineering. Our team produces world class solutions for computational lithography systems and has won several Intel achievement awards as well as software quality awards. <br />
<br />
Interested individuals should forward their resumes to cemal.c.bilgin@intel.com<br />
<br />
= Past positions =<br />
<br />
<br />
== Year 2013 ==<br />
<br />
<br />
=== Internship position for developing a MR CAD tool ===<br />
Posted: Oct. 29th 2013<br />
<br />
Eigen is making a difference in patient outcomes and care with our innovative medical imaging products, and we’re looking for a software engineer to join our team.<br />
ProFuse, our MRI image fusion product, is being used on patients daily to provide accurate, repeatable biopsies, with the assistance of Eigen’s mechanical guidance. We have a list of improvements in mind to make the system even better, and that’s where you can help us. We need a quality-focused software intern who’s familiar with C++ - if you know the QT framework, so much the better. You’ll be working with our existing team to add features, and lay the foundation for our next generation of products.<br />
<br />
Requirements:<br />
-In progress degree in Computer Science, Mathematics, Physics, Engineering, Medical Imaging or related discipline.<br />
-UI/UX programming experience.<br />
-Strong interpersonal and communication skills.<br />
-Knowledgeable and experienced with C++ language.<br />
<br />
Desirable but not required:<br />
-Experience with medical devices, avionics, or other regulated technical products.<br />
-Familiarity with ITK and VTK libraries.<br />
-Experience with CMake build system.<br />
-Image processing background strongly preferred.<br />
-Strong mathematics background.<br />
-GPU programming experience (CUDA).<br />
<br />
This is a 6 month internship, on-site at our Grass Valley, CA location, but could lead to a full time W2 position.<br />
<br />
Please send your resumes to hr@eigen.com.<br />
<br />
=== PhD position in multi-modal image processing, b<>com Brest, France ===<br />
<br />
Posted: Oct. 28th 2013<br />
<br />
It is increasingly common to combine multiple methods of treatment, i.e., treatment modalities, with the intention to improve patient outcomes and reduce complications. Each treatment modality may consist of (1) multiple images acquired by one or more modalities (e.g. PET and CT) and (2) contextual information (e.g. clinical reports). To improve patient outcome, one approach is to unify the imaging information and the context information so that the therapy planning, therapy guidance and post-treatment evaluation are simplified. In practice, whereas Picture Archive and Communication Systems (PACS), employed in hospital, store multi-modal images and contextual information, simultaneous re-use of both information cannot be done in a simple fashion.<br />
<br />
This Ph.D. will focus on the integration of multi-modal imaging information accrued by contextual information extracted from a PACS.<br />
<br />
A first problem to address is the analysis of multi-modal images (e.g., PET/CT). This analysis requires, for example, image processing (image quality improvement or image artifact reduction) followed by image analysis (segmentation or biomarker extraction). A second problem to investigate is the association of quantitative parameters extracted from multi-modal images with other contextual information. This also involves the automatic generation of clinical reports both associating results of multi-parameter image analysis and contextual information, with the goal of assisting physicians with clinical decisions. It is intended that this Ph.D. will lead to a Clinical Decision Support System demonstrator dedicated to a specific context/pathology (e.g. oncology or neurology).<br />
<br />
The PhD fellowship is funded by b<>com (http://b-com.com) which is a Technology Research Institute located in Brest, Rennes and Lannion (France). This Ph.D thesis will be carried out under the supervision of M. Hatt (research associate, INSERM) and G. Coatrieux, Assistant Professor (Telecom Bretagne) and located at b<>com on the Brest-Iroise Science and Technology Park.<br />
<br />
Expected qualifications:<br />
- Minimum MSc degree (Computer Science)<br />
- Experience in developing medical imaging applications is desirable<br />
- Prior experience in image analysis, pattern recognition and computer vision<br />
- Programming experience in C++<br />
<br />
Contact: Please send your resume to job@b-com.com<br />
<br />
== Year 2012 ==<br />
<br />
=== Technology Officer in Biomedical Image Computing & Modelling, University of Sheffield, UK ===<br />
<br />
''' Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Sheffield, UK ''' <br />
<br />
Posted: Nov 5th 2012 \<br />
Closes: Nov 21st 2012<br />
<br />
''* About Sheffield ''<br />
<br />
Mechanical Engineering has been a major discipline in the University of Sheffield since its foundation in 1905. In the most recent Research Assessment Exercise the Department came second in the country in the league table of Mechanical Engineering departments, and achieved an "Excellent" rating in the last Teaching Quality Assessment. The Department currently has 41 members of academic staff who support the learning and development of an ever-growing undergraduate and postgraduate student body. For more information on the Department please see our web site http://www.shef.ac.uk/mecheng/.<br />
<br />
The INSIGNEO Institute for in silico Medicine is an initiative between the Faculty of Engineering and the Faculty of Medicine at the University of Sheffield and the Sheffield Teaching Hospitals Foundation Trust. INSIGNEO will realise the scientific ambition behind the Virtual Physiological Human (VPH), producing a transformational impact on healthcare. INSIGNEO performs cutting edge research in areas of fundamental and applied biomedical modelling, imaging and informatics. It will pursue the research agenda of the VPH initiative; in particular, in the first five years it will focus on the Digital Patient, In Silico Clinical Trials, and Personal Health Forecasting. It will achieve transformational impact on healthcare through multidisciplinary collaboration in strategic areas, which initially will include personalised treatments and independent, active and healthy ageing.<br />
<br />
The Computational Imaging and Simulation Technologies in Biomedicine (CISTIB) Group at the University of Sheffield is part of INSIGNEO. CISTIB focuses on algorithmic and applied research in the areas of computational imaging, modeling and simulation. CISTIB is working in different areas of medical image segmentation, statistical shape analysis, pattern recognition and image-based personalized computational electro-mechanics and fluid dynamics, and modeling of virtual interventions with endovascular and cardiac rhythm management devices. The centre hosts academic members from the University of Sheffield as well as research fellows, research associates, PhD Students and scientific software developers forming a cross-disciplinary team of biomedical engineers, computer scientists, electrical engineers, mechanical engineers, physicists, and mathematicians. <br />
<br />
The main objective of CISTIB is to contribute to the development of technologies for advanced screening, diagnostics, interventional guidance and therapy planning of cardio- and neurovascular diseases as well as growing activity in the musculo-skeletal system. Converging technologies such as computational imaging, computational physiology and virtual implantation of medical devices are integrated with state of the art multimodal acquisition systems to achieve an enhanced interpretation of human physiology and pathology and supply integrative approaches for in silico medical device customization, optimization and image-based efficacy assessment. Core technologies include spatial and temporal image segmentation, non-rigid image registration, multimodal image fusion, pattern recognition, statistical shape analysis, multi-view geometry, image-based tissue property estimation, tissue deformation quantification, computational geometry, image-based mesh generation, computational fluid dynamics and electro-mechanical simulation.<br />
<br />
CISTIB fosters basic and applied research and promotes technology transfer to industry. It participates to a number of national and international research projects funded by the European Commission, and holds collaborations with several national and international companies. CISTIB also very close cooperation with clinical centers at the local level and worldwide and has a strong clinically-oriented translational vision.<br />
<br />
'' * Open positions ''<br />
<br />
You will lead and coordinate a team of Scientific Software Developers that will produce prototypes for applied research projects, clinical translation projects, and technology assessment studies. Your work will also support the research program within CISTIB by enabling its researchers to effectively implement new methods and algorithms. Those prototype technologies that are found to be effective will be translated into commercially available products and services, by means of IPR exploitation agreements with existing companies, or by creating dedicated spin-off companies. The ideal candidate has a considerable experience in managing Technical teams. Previous experience in the area of software development related to the Virtual Physiological Human initiative would be an advantage. Your skill set should be properly balanced between experience on research projects and software management to act as an interface between the needs of the technological and clinical researchers of the centre, and the software developers. All development activities should be steered toward the establishment of a portfolio of methods and technologies (i.e. libraries, software frameworks, etc.). You will play a key role in attracting significant research and technological development funding, in collaboration with other CISTIB members, both from public and private sources.<br />
<br />
We are interested in individuals with excellent communication and leadership skills, able to work in a multidisciplinary and international team and contribute to the visibility of the centre in the international scientific community. The ability to interact with other disciplines is essential. The candidate will cooperate with members of the lab working on related topics as well as with our collaborators at several academic institutions in UK and across Europe.<br />
<br />
'' * How to apply ''<br />
<br />
More information and application through http://sheffield.ac.uk/jobs reference UOS005565.<br />
<br />
=== Job - Software Engineer in medical image processing (medInria) - INRIA Rennes - France ===<br />
<br />
Posted June 26, 2012<br />
<br />
R&D Experienced software engineer / Good knowledge of ITK, VTK and Qt<br />
<br />
As part of the development of medInria ([http://med.inria.fr med.inria.fr]), we are proposing a new position for an experienced engineer at Inria Rennes, France (Visages team), starting from october 2012. The recruited person will work among the national team developing medInria, to develop core features and specific medical image processing plugins from the Visages team. More details on the position are available on [https://www.irisa.fr/visages/_media/positions/position_medinria_nt_2012.pdf the position sheet].<br />
<br />
<br />
=== Job - Software Engineer / Research Specialist Lead - Emory University / Georgia Tech ===<br />
<br />
Posted June 8, 2012<br />
<br />
Research Specialist Lead / Software Engineer<br />
<br />
This position offers great opportunities to work in a high-quality academic environment at Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA. The joint Department of Biomedical Engineering (BME) of Emory University and Georgia Institute of Technology provides one of the top BME programs to foster the next generation of leaders in biomedical engineering worldwide. The Department of Radiology and Imaging Sciences at Emory University School of Medicine provides one of the best education, training and research programs in the country. Successful applicant would work under the supervision of the principal investigator and will collaborate with other faculty members, clinicians, researchers, post-doctoral fellows, graduate and undergraduate students in a research team. This person would be involved in projects focused on multimodality medical imaging (ultrasound, PET/CT, and MRI) with emphasis on medical image analysis and image-guided interventions. As a regular staff of Emory University, this person and her/his family would be eligible for a full range of Emory benefits including health and dental insurance, tuition, and other benefits. <br />
<br />
JOB DESCRIPTION: Under minimal supervision, modifies and writes software programs for image processing and analysis. Develops requirements and specifications and implements computer algorithms in software programs. Performs image quantification using commercial software systems or home-made software programs. Uses independent judgment in applying or adapting scientific techniques. Assists in planning and scheduling research procedures. Performs a variety of laboratory tests and procedures. Analyzes and interprets results of studies. Reviews literature for related research developments and techniques and compiles findings. Monitors laboratory processes to maintain quality assurance standards. Records results of studies, compiles and analyzes data and prepares charts and graphs. Performs related responsibilities as required. <br />
<br />
MINIMUM QUALIFICATIONS: Bachelor's or Master’s degree in computer science, mathematics, electrical engineering, biomedical engineering, or other related fields, and two years of working experience, or equivalent combination of experience, education, and training. Two years of experience in software programming is required. Programming experience with IDL, C++, and MATLAB is preferred. Basic knowledge in medical image processing and analysis is required. Knowledge in medical imaging such as MRI, PET, CT, and ultrasound is a plus but not required. <br />
<br />
CONTACT:<br />
Baowei Fei, PhD, EngD,<br />
Georgia Cancer Coalition Distinguished Scholar<br />
Director of Quantitative BioImaging Laboratory (QBIL)<br />
Emory University and Georgia Institute of Technology<br />
1841 Clifton Road NE, Atlanta, GA 30329, USA<br />
Email: bfei@gatech.edu<br />
<br />
<br />
To apply for the position, send CV and Personal Statement to bfei@gatech.edu <br />
<br />
<br />
== Year 2011 ==<br />
<br />
=== ITK-SNAP Software Developer - University of Pennsylvania ===<br />
<br />
Posted Dec 5, 2011<br />
<br />
The Penn Image Computing and Science Laboratory (PICSL) seeks a qualified C++ programmer to support the development of ITK-SNAP, an interactive software application for biomedical image segmentation. The programmer will work with the principal investigator on an NIH-funded grant to develop the next-generation GUI for ITK-SNAP, accelerate the tool=92s performance, and incorporate multi-modality image segmentation algorithms. Applicants must have a Bachelors degree in computer science or related field. Minimal qualifications are<br />
<br />
* C++ programming (4 years experience)<br />
* Experience with user interface programming, preferably Qt<br />
* Strong interpersonal and communication skills, and ability to work<br />
independently<br />
<br />
Applicants with expertise in the following ares are particularly encouraged to apply:<br />
<br />
* Familiarity with ITK and VTK libraries, and CMake build system<br />
* Image processing, computer vision, and computer graphics<br />
* Strong mathematics background<br />
* GPU programming experience (CUDA, OpenCL)<br />
* Experience working in a research environment<br />
* Advanced degree in related field<br />
<br />
PICSL is a dynamic and growing research group involved in many exciting biomedical imaging projects, including development of novel analysis methodologies; application of the state-of-the-art techniques to clinical studies; and translational research. PICSL is located in Philadelphia, a vibrant city that offers many professional and cultural opportunities. PICSL fosters a friendly, noncompetitive, collaborative environment where each individual member of the laboratory is able to thrive, while also effectively contributing to the group=92s overall programmatic aims.<br />
<br />
The position is funded by a federal grant. Continued employment is subject to performance and availability of grant funding. PICSL has an excellent track record of obtaining research funding and personnel retention. The position features a competitive compensation package with generous fringe benefits.<br />
<br />
The University of Pennsylvania is an equal opportunity, affirmative action employer. Women and minority candidates are strongly encouraged to apply.<br />
<br />
Interested candidates should send an email to the address below. Please include the words =93snap developer=94 on the subject line. Include a brief statement of qualifications relevant to the project, a CV or resume, and a list of 3 references.<br />
<br />
Paul Yushkevich, Ph.D.<br />
Assistant Professor<br />
Penn Image Computing and Science Laboratory (PICSL)<br />
Department of Radiology<br />
University of Pennsylvania<br />
<br />
Email: pauly2 [at] mail [.] med [.] upenn [.] edu<br />
http://picsl.upenn.edu<br />
http://itksnap.org<br />
<br />
<br />
=== Software Engineer(s)-Electrical Geodesics, Inc. ===<br />
<br />
Electrical Geodesics, Inc. (www.egi.com), an international medical device company in the neurology/neuroscience field, is seeking to fill “three” software engineer position. The Software Engineer is responsible for software related product development, product engineering activities, and grant support.<br />
<br />
Opening 1Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• C++ (Objective-C a plus)<br />
Make, CMake, and other build environment expertise.<br />
<br />
• VTK, ITK, Tcl/Tk<br />
<br />
Desired Experiences:<br />
<br />
• MRI Processing<br />
• Cross platform development (Mac, Linux, Windows) experience a plus.<br />
<br />
Opening 2 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java, C, C++ (Objective-C a plus).<br />
<br />
Opening 3 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java (principle), C, C++ (Objective-C a plus)<br />
• Strong knowledge of application server environments.<br />
• Strong profiency in database engineering, and demonstrable knowledge of SQL.<br />
• Experience with Netbeans or Eclipse (and comfortable to use either).<br />
<br />
Full Time, exempt, salary position with benefits.<br />
<br />
To apply for any of the above openings, resume and cover letter should be sent to dmarquez@egi.com<br />
<br />
<br />
=== Master training position, INRIA Sophia Antipolis, France: Prediction of Cardiac Electrophysiology Signal Characteristics from Image Features ===<br />
<br />
<br />
The aim of this project is to analyse both cardiac images and electrophysiology signals in order to explore correlations. Developped features will be mapped on a 3D mesh and overlaid on anatomical images of the heart in order to guide interventions. This project will require image analysis, registration for correlating anatomical and functional information, and machine learning. This project will be in collaboration with Bordeaux University Hospital.<br />
<br />
More information can be found in the detailed job description: <br />
<br />
http://www-sop.inria.fr/asclepios/recrutement/MasterTrainingINRIA2011.pdf<br />
<br />
<br />
== Year 2010 ==<br />
<br />
=== Postdoctoral Position: MIT/Harvard Medical School, Cambridge/Boston, MA ===<br />
<br />
* Posted on December 3rd 2010<br />
<br />
Location: Cambridge/Boston, MA<br />
Type: Postdoctoral position in Medical Robotics<br />
Expires:January 01, 2011<br />
<br />
Job description: We are currently seeking an engineer/computer scientist to join our dynamic team that is developing image-guided robots for accurate and efficient tumor ablation. The person will ideally have medical image processing experience and will be developing user interfaces for controlling robots using information in the medical imaging data.<br />
<br />
Our group involves a collaboration between the Massachusetts Institute of Technology, Massachusetts General Hospital and Brigham and Women's Hospital and has a large amount of technical and clinical expertise in this area.<br />
<br />
Information regarding the open positions and desired qualifications can be provided upon request. Graduate students, post-doc and recent graduates will all be considered. Interested candidates should send a CV and a brief paragraph along to Dr. Conor Walsh at walshcj@mit.edu.<br />
<br />
<br />
=== Two Postdoctoral Positions: Harvard Medical School, Boston, MA ===<br />
<br />
* Posted on November 30th 2010<br />
<br />
Website:http://http://vcp.med.harvard<br />
Location: Boston, MA<br />
Type: Postdoctoral<br />
Expires:January 22, 2011<br />
<br />
Job description: Applications are invited for two postdoctoral-level positions on a collaborative project funded by the European Human Frontiers Programme between the laboratories of Alfonso Martinez-Arias in the Department of Genetics at the University of Cambridge, UK, Kat Hadjantonakis in the Developmental Biology Program at Memorial Sloan Kettering Cancer Center in New York and Jeremy Gunawardena in the Department of Systems Biology at Harvard Medical School in Boston. The project centres on analysing signalling and gene regulation networks in the pre-implantation mouse embryo and in mouse embryonic stem cells, using quantitative measurements, 4D whole-embryo imaging, microfluidic devices and mathematical modelling. The first position is with Hadjantonakis in New York to develop a quantitative image analysis platform for 4D mouse embryo imaging. The successful applicant will need strong technical capabilities in live-cell image analysis, familiarity with software tool development with a focus on usability and the desire to work in close collaboration with experimentalists. The second position is with Gunawardena in Boston to analyse mouse ES cells using microfluidic devices and modelling. The successful applicant will have experience studying mammalian cells in culture using quantitative experimental methods, an interest in exploiting microfluidic technologies and an ability to work with mathematical models of molecular networks. Both positions will require occasional travel between the sites and an annual visit to Cambridge, UK. Interested candidates are asked to send a CV and the contact details of two referees to one of the two addresses below, along with a cover letter stating clearly why his or her background is appropriate for the corresponding position. The deadline for applications is 31 December 2010.<br />
<br />
Kat Hadjantonakis<br />
Developmental Biology Program<br />
Sloan-Kettering Institute<br />
New York, NY 10065,<br />
USA<br />
http://www.ski.edu/hadjantonakis<br />
<br />
Jeremy Gunawardena<br />
Department of Systems Biology<br />
Harvard Medical School<br />
200 Longwood Avenue<br />
Boston, MA 02115<br />
USA<br />
<br />
By e-mail to Nicole Wong, Nicole_Wong@hms.harvard.edu<br />
<br />
http://vcp.med.harvard.edu/<br />
<br />
=== Research Scientist (Junior) - Image and Signal Processing - Rennes,France ===<br />
<br />
* Posted on September 14th 2010<br />
<br />
Bruce Junior Chair position<br />
<br />
http://www.rbucewest.ueb.eu/<br />
<br />
R-Buce Junior Chair position in Biomedical Engineering.<br />
<br />
The UEB - UR1 seeks research scientist applicants working in the broad field of biomedical engineering, with particular focus on themes at the frontiers of ICT and health. Of special interest are the following topics: model-based bio-signal / bio-imaging processing and interpretation, integrative modeling, knowledge-based information representation and interpretation.<br />
<br />
The UEB - UR 1 laboratories involved in biomedical engineering have strong clinical partnerships with a number of medical institutions, including the Rennes University Hospital and the Centre of Cancer Eugène Marquis at Rennes.<br />
<br />
Qualified candidates working in the broad area of biomedical engineering, developing computational tools or multiscale systems-based techniques are encouraged to apply. Required qualifications include a doctorate in engineering or a related field with an outstanding record of publications in internationally recognized journals.<br />
<br />
Interested persons should submit detailed curriculum vitae including academic and professional experience, a list of peer-reviewed publications and any other technical documents relevant to the application.<br />
<br />
salary range : ~40kE/year + relocation<br />
<br />
Please send cover letter and resume to Oscar Acosta / Lotfi Senhadji <br />
(Oscar.Acosta@univ-rennes1.fr, Lotfi.Senhadji@univ-rennes1.fr) <br />
<br />
<br />
== Year 2009 ==<br />
<br />
=== Software Engineer (Junior) - Harvard Medical School ===<br />
<br />
* Posted on August 14th 2009<br />
<br />
The Megason Laboratory in the Department of Systems Biology at Harvard Medical School seeks to hire a Software Engineer for participating in the continued development of GoFigure. The lab’s goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology (www.digitalfish.org). The Software Engineer will be responsible for participating in the continued development of the principle software application for this endeavor called GoFigure. GoFigure recognizes and tracks cells in extremely large 4-dimensional (xyzt) image sets and digitizes that data into a database. GoFigure is written in C++, is cross-platform and uses Qt, MySQL, VTK (the Visualization Toolkit), ITK (Insight Segmentation and Registration Toolkit), CMake. The project is managed using Subversion, Doxygen for documentation generation, CTest and CDash for testing. The successful applicant should have a strong background in programming and work well in an academic environment. Interests in application development, image processing, microscopy, and systems biology are also a plus.<br />
<br />
'''Job Duties'''<br />
<br />
* Participate in software development project for GoFigure. GoFigure is developed by a team of ~4 which is lead by a Senior Research Engineer<br />
* Responsible for the development and testing of code as specified by management (senior software engineer and lab director). Incumbent will write code and will assist management in integration of code into GoFigure<br />
* Performs ongoing modifications and solution alternatives to accomplish research requirements of GoFigure software<br />
* Collaborates with researchers to define new strategies, approaches, methods and techniques to enhance research efforts<br />
* Participate in regular lab meetings, journal club presentations, and retreats<br />
* Other duties as assigned<br />
<br />
Please send cover letter and resume to Sean Megason<br />
(megason@hms.harvard.edu) <br />
<br />
=== Computer Programming - Image Guided Intervention ===<br />
<br />
* Posted Aug 2009,<br />
<br />
Department of Medicine at Harvard Medical School and Beth Israel Deaconess Medical Center is looking to hire a full time software engineer with strong background in computer vision and ITK/VTK. Intrested applicant should send a CV to :<br />
<br />
Reza Nezafat, Ph.D. rnezafat@bidmc.harvard.edu<br />
<br />
<br />
== Year 2008 ==<br />
<br />
=== Staff Scientist - Medical Image Processing ===<br />
<br />
* Posted: November, 2008<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 4 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service <br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Radiology and Imaging Sciences<br />
National Institutes of Health Clinical Center<br />
Building 10 Room 1C368X MSC 1182<br />
Bethesda, MD 20892-1182<br />
E-mail: rms@nih.gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== Research Developer - Medical Imaging ===<br />
<br />
'''About Calgary Scientific'''<br />
<br />
Calgary Scientific Inc. (CSI) is a software and intellectual property (IP) development company specializing in sophisticated digital signal, image processing and analysis technology. Our current product line includes customer focused applications for medical imaging and seismic data imaging. These applications offer innovative tools to help professionals to better interpret and analyze data through core innovations around which CSI applications are developed.<br />
<br />
Calgary Scientific is a privately held company with offices in Calgary, Alberta, Canada. The company was formed in 2003 to commercialize leading edge intellectual property into market leading software applications.<br />
<br />
Calgary Scientific works with research teams and individuals across multiple Universities to generate, refine, test, and commercialize breakthrough innovation into market driven commercial applications.<br />
<br />
'''Research Developer – Medical Imaging Role'''<br />
<br />
We are looking for several full-time Research Developers with Medical Image Processing skills who are willing to relocate to Calgary, Alberta, Canada. Duties will include:<br />
<br />
* Incorporating cutting edge research code from around the world into our production quality, C++ core technologies<br />
<br />
* Working with Research Scientists and Research Associates on various medical image processing algorithms<br />
<br />
* Working with QA to design and develop unit and validation tests that meet our ISO 13485 and ISO 14971 requirements<br />
<br />
* Working directly with Agile Product Teams to ensure the rapid integration of new technologies into various medical applications<br />
<br />
This is an excellent opportunity to contribute to the commercialization of market-driven medical imaging applications.<br />
<br />
'''Required Experience/Skills:'''<br />
<br />
* Degree in Engineering, Physics, Computer Science, or related fields<br />
<br />
* 5 or more years of experience in C++ development<br />
<br />
* 1 or more years of matlab and OpenGL experience<br />
<br />
* Applied or advanced math training, particularly in medical image processing or artificial intelligence<br />
<br />
* Demonstrated ability to learn new technologies<br />
<br />
* Desire to contribute to the successful commercialization of leading-edge technology<br />
<br />
'''Beneficial Experience/Skills:'''<br />
<br />
* Algorithm development using ITK<br />
<br />
* Working within an ISO certified environment<br />
<br />
Applications can be sent to careers@calgaryscientific.com<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
=== Post-doctoral Research Openings at Rensselaer Polytechnic Institute ===<br />
<br />
The FARSIGHT project has openings for several post-doctoral associates (or experienced individuals with a Masters degree), starting May 1, 2008. This project is developing an open-source 4-D/5-D image analysis toolkit for advanced biological microscopy of brain tissue, tumors, and immune system components. The required skills include <br />
<br />
* High-quality C++ programming, <br />
* 3-D image processing (segmentation, classification, registration), and <br />
* 3-D graphics programming. <br />
<br />
Prior exposure to ITK and/or VTK, and disciplined software development processes is highly desirable. <br />
<br />
These positions are renewable annually. <br />
<br />
Please contact <br />
Prof. Roysam <br />
by email: Roysam@ecse.rpi.edu.<br />
<br />
Badri Roysam<br />
Professor, Department of Electrical, Computer and Systems Engineering<br />
Associate Director, NSF Center for Subsurface Sensing & Imaging Systems (CenSSIS ERC)<br />
Rensselaer Polytechnic Institute<br />
110 8th Street, Troy, New York 12180-3590.<br />
Office(JEC 7010): 518-276-8067, Lab(JEC 6308): 518-276-8207, Fax: 518-276-8715<br />
Web: http://www.ecse.rpi.edu/~roysam<br />
<br />
=== Senior Developer - Medical Image Processing ===<br />
<br />
Status: Filled<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
<br />
=== Software Engineer, Intuitive Surgical Inc., Sunnyvale California ===<br />
<br />
The da Vinci(r) Surgical system includes six manipulator arms with a total of 41 degrees of freedom, along with a stereo endoscope and 3D video display, with over 600 installations worldwide. Surgeons use it to perform tens of thousands of minimally invasive surgeries per year. da Vinci represents an outstanding platform for the development and application of new technologies to surgery. This position offers an opportunity for a candidate with exceptional software development skills to work on projects ranging from blue-sky research to those ready for transition to product development groups. A successful candidate will be equally comfortable leading architecture development and producing high-quality implementations that lend themselves to re-use, testing, and productization. He or she must excel in a high energy team, must have excellent communication skills and must be able to balance independent production of results with the need to collaborate during planning, system integration, and testing of larger projects. This engineer will work closely with other members of the Applied Research Group and several product development groups on algorithm development, implementation, and systems integration.<br />
<br />
For more details, as well as to upload a resume, please visit our OpenHire listing:<br />
* Position: Software Engineer<br />
* Tracking Code: 220333-609<br />
* Posted: November, 2007<br />
* URL: http://hostedjobs.openhire.com/epostings/jobs/submit.cfm?fuseaction=dspjob&id=23&jobid=220333&company_id=15609&version=1&source=ONLINE&JobOwner=956377&level=levelid1&levelid1=10630&parent=Engineering&startflag=2&CFID=8647986&CFTOKEN=46344848<br />
<br />
<br />
=== Research Scientist Position in Medical Imaging in Brisbane, Australia ===<br />
<br />
CSIRO ICT centre is seeking to fill several positions at the scientist and post-doctoral level to work on neuro-degenerative diseases and brain tumour characterization.<br />
The Biomedical Imaging team part of the Australian e-Health Research centre is a leading Australian medical imaging research group, with a well developed expertise in image registration, extraction of quantitative information (shape, volume, texture), morphometry, soft-tissue modelling (3D meshing, visual and haptic interaction) and data classification. The successful applicants will be involved in activities focused on the development and application of novel techniques for segmentation, registration and analysis of PET and MR images. These positions offer the opportunity to work in a high quality research environment, with strong clinical collaboration. The research scientists and post-doctoral fellows will join a large team (>20 scientists, post-doctoral fellows, and students) in an exciting working environment ideally located in one of the fastest growing city in Australia close to many attractions and beautiful beaches.<br />
More details can be found on the CSIRO career website: <br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F487<br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F9<br />
For further information please contact <br />
Olivier Salvado, PhD<br />
Team Leader Biomedical Imaging<br />
olivier.salvado@csiro.au<br />
<br />
CSIRO ICT Centre<br />
Australian e-Health Research Centre (AEHRC)<br />
Phone: +61 7 3024 1658<br />
Fax: +61 7 3024 1690<br />
Mobile: +61 4 0388 2249<br />
web: http://www.aehrc.net/<br />
<br />
== Year 2007 ==<br />
<br />
=== Summer 2007: National Institutes of Health Postdoc ===<br />
<br />
Post-doctoral fellowships are available in clinical image processing. Specific interest areas are image processing (virtual endoscopy, volumetric visualization, image segmentation, registration, fusion, and algorithm development) and computer-aided diagnosis (feature extraction, classification, and databases). Fellows have access to state-of-the-art whole body MRI, multi-row detector CT and advanced graphics workstations. Candidates must have or soon expect to receive doctorates in applied mathematics or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on image processing or computer visualization and having strong software development and C++ skills are encouraged to apply. Initial appointment is for two years and is renewable thereafter on a periodic basis. NIH is an equal opportunity employer.<br />
<br />
Address applications to: <br />
Jianhua Yao, Ph.D. <br />
Clinical Image Processing Service <br />
Department of Radiology <br />
National Institutes of Health <br />
10 Center Drive Bethesda, MD 20892-1182 <br />
E-mail: jyao@cc.nih.gov <br />
<br />
<br />
=== August 2007 to sept. 2008: Caltech & Harvard Medical School ===<br />
<br />
The Caltech Center of Excellence in Genomic Science (CEGS) is a newly funded initiative that’s driven to digitize life. Our goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology. Our approach called “in toto imaging” is to use confocal/2-photon imaging to image all the cells in developing transgenic zebrafish embryos and special software we are developing called GoFigure to extract complete cell lineages and gene expression patterns.<br />
<br />
We are looking for people with strong experience in C++ programming and VTK/ITK to join our GoFigure development team. There are a number of significant image analysis problems we are addressing including: segmenting cells in space, across time, and across cell division; quantitating protein expression patterns and subcellular localization; developing a standard, cell-based, 4-d atlas of embryonic development; and registering molecular data from thousands of different embryos onto this atlas.<br />
<br />
There are opportunities at the graduate, post-doc, and staff levels. The successful applicant would join our team at Caltech in Pasadena/LA soon and then move with us to my new lab in the Department of Systems Biology at Harvard Medical School in Boston in summer 2008. To apply, please send a cover letter, CV, and letters of reference to me by email (megason@caltech.edu).<br />
<br />
For more information please see below:<br />
www.digitalfish.org <http://www.digitalfish.org/> <br />
or talk to Alexandre Gouaillard or myself at the upcoming NAMIC meeting in Boston ( june 2007 ).<br />
http://www.na-mic.org/Wiki/index.php/NA-MIC_NCBC_Collaboration:3D%2Bt_Cells_Lineage:GoFigure<br />
<br />
Sean Megason<br />
<br />
=== Spring 2007: University of Texas - M. D. Anderson Cancer Center ===<br />
<br />
The Image Processing & Visualization Laboratory (IPVL) has opened positions for a Programmer Analyst, Post Doctorate and Research Scientist to support its core mission in America’s largest cancer center.<br />
<br />
Images handled by the IPVL span the full spectrum of human and animal (small to large) imaging instrumentation for applications that range from research to clinic, all in direct and close interaction with departments and investigators throughout the institution. Computer equipment includes high-end clinical workstations and software, as well as high-end platforms under Windows, Linux or OSX for developments with OpenSource toolkits, IDL or MatLab. Other available equipment include database and compute servers (Windows, Unix/Solaris/Linux), as well as a state-of-the-art 512 CPUs cluster and 32 CPUs SMP, both shared with the institution and entirely dedicated to research.<br />
<br />
The successful candidates will need to demonstrate – in various capacities that depend on the targeted position - expertise and interest in the design, development, implementation or exploitation of advanced imaging applications, ideally in a biomedical setting and with multidimensional, multimodality and quantitative imaging for clinical and research applications. Topics of particular interests are 3D+ imaging (e.g., rendering, segmentation, navigation), non-rigid registration, parametric and quantitative imaging, kinetic modeling, etc. Expertise in modern and relevant languages and toolkits (e.g., C/C++, VTK, ITK, IGSTK) as well as in matching development tools and environments is considered an asset.<br />
<br />
If you believe your experience matches any of these profiles, please send your CV and other relevant information (e.g., three references, statement of interest/qualification for the specific position) to:<br />
<br />
Dr. Luc Bidaut, Ph.D.<br />
Director of the IPVL<br />
E-mail: lbidaut at mdanderson dot org<br />
<br />
== Year 2006 ==<br />
<br />
=== May 2006: National Institutes of Health Staff Scientist Position ===<br />
<br />
'''Staff Scientist'''<br />
Medical Image Processing<br />
Warren G. Magnuson Clinical Center Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applicati!<br />
ons should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html <br />
<br />
=== Spring 2006: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing – Computer-Aided Detection<br />
Warren G. Magnuson Clinical Center <br />
Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
A post-doctoral fellowship is available in three-dimensional radiology image processing. Specific interest areas are virtual endoscopy, volumetric visualization, image segmentation, registration and computer-aided detection (including feature extraction, classification, image databases and observer performance analysis [ROC]). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. Fellows have access to state-of-the-art whole body MRI, multi-detector helical CT, advanced graphics workstations (Windows PC) and Beowulf massively parallel processing cluster. Candidates must have or soon expect to receive doctorates in physics, biophysics, mathematics, statistics, biomedical engineering or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of computer visualization and image processing and having advanced mathematical and computer skills are encouraged to apply. Initial appointment is for one to two years and is renewable thereafter on a periodic basis. Applications should include a CV, brief statement of research interests and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
== Year 2005 ==<br />
<br />
=== Spring/Summer 2005: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing<br />
Department of Radiology<br />
National Institutes of Health<br />
Department of Health and Human Services<br />
<br />
A Post-doctoral fellowship is available in three-dimensional medical<br />
imaging. Specific interest areas are image processing (virtual endoscopy,<br />
volumetric visualization, image segmentation, registration, fusion, and<br />
algorithm development) and computer-aided diagnosis (feature extraction,<br />
classification, and databases). Fellows have access to state-of-the-art<br />
whole body MRI, 16-row detector CT+PET and advanced graphics workstations (PC and Beowulf cluster). Candidates must have or soon expect to receive<br />
doctorates in applied mathematics or computer science. Applicants with a<br />
proven track record as evidenced by peer-reviewed publications on image <br />
processing and having strong software development and C++ skills are encouraged to apply. GPU shader programming experience is a plus. Applications should include a CV and a brief statement of research interests. NIH is an equal opportunity employer. If a US work permit is not available, then the only visa the NIH can provide for this position is a J visa.<br />
<br />
* Address applications to:<br />
<br />
Ingmar Bitter, Ph.D.<br />
Clinical Image Processing Services<br />
Diagnostic Radiology Department<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: ibitter at nih dot gov<br />
<br />
<br />
== Year 2004 ==<br />
<br />
=== November 2004: Kitware ===<br />
<br />
Kitware is seeking to fill positions immediately. We are looking for people who will relocate to the Albany, NY USA area, are willing to work in a small company, and show flexibility in work assignments. Important skills include proficiency in C++, scientific software development, medical image analysis, and/or ITK. Individuals demonstrating expertise in areas that significantly extend Kitware's software skill base are particularly favored. Please send your resume to kitware at kitware.com.<br />
<br />
Will<br />
<br />
William J. Schroeder, Ph.D.<br />
Kitware, Inc.<br />
28 Corporate Drive, Suite 204<br />
Clifton Park, NY 12065<br />
will.schroeder at kitware.com<br />
1-518-371-3971 x102 (phone)<br />
1-518-371-3971 (fax) <br />
<br />
([http://public.kitware.com/pipermail/insight-users/2004-July/009562.html Original post])<br />
<br />
<br />
=== Nov 2004: National Institutes of Health Staff Scientist ===<br />
<br />
Warren G. Magnuson Clinical Center<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
'''Staff Scientist'''<br />
'''Medical Image Processing'''<br />
<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Electrical or Biomedical Engineering, Computer Science, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: RobertsonS at cc dot nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== June 2004: Computer Vision Research Position ===<br />
<br />
'''Computer Vision Research Positions at GE Global Research'''<br />
Visualization and Computer Vision Lab<br />
<br />
We are seeking highly qualified candidates to innovate and develop computer vision technology for commercial and government applications. We are particularly interested in recruiting candidates with expertise in one of the following areas:<br />
<br />
* Machine Learning - applying semantic knowledge to practical vision problems <br />
* Deformable Registration / Deformable Modeling<br />
* Segmentation<br />
* Object Detection and Tracking<br />
<br />
The Visualization & Computer Vision Lab at GE Global Research in Niskayuna, NY conducts basic and applied research in computer vision and closely related areas. With 30 Staff Researchers (most holding a PhD) the lab develops advanced technologies for GE businesses, including GE Security, GE Healthcare, GE Aircraft Engines, GE Power Systems and NBC Universal; Lockheed Martin; and US Government agencies including NIH, DARPA, FBI, AFRL and NIMA. Areas of active research include image segmentation, deformable registration, perceptual organization, texture classification, object detection, event recognition, tracking, camera calibration, optical metrology, video content extraction, change detection, and superresolution.<br />
<br />
We are active users and contributors to ITK and VXL; experience with either of these toolkits is desired. Strong C++ skills along with a superior ability to work in a team environment are essential qualities for successful candidates.<br />
<br />
Interested? Please contact Jim Miller at `millerjv at research.ge.com`<br />
<br />
Visualization & Computer Vision<br />
GE Research<br />
Bldg. KW, Room C218B<br />
P.O. Box 8, Schenectady NY 12301<br />
<br />
<br />
{{ITK/Template/Footer}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Job_Opportunities&diff=56334ITK/Job Opportunities2014-05-16T19:10:22Z<p>Ccagataybilgin: /* Current positions (2014) */</p>
<hr />
<div>Please feel free to post announcements for jobs and positions that are related to ITK and applicants with ITK experience. Once the position has been fulfilled, please update the entry accordingly.<br />
<br />
Please note that they are '''listed according to their post date''', and not their deadline, as this information is missing in some cases. Past positions are kept for the sake of maintaining a small history of them.<br />
<br />
= Current positions (2014) =<br />
'''Description''':<br />
The individual will participate in the development of next generation computational lithography tools, which are an important contributor to Intel's march along Moore's Law. The job role includes research and development work for creating new numerical models and algorithms that enable extracting even more resolution out of existing 193nm steppers. The duties also include image analysis, software performance optimization, parallel programming, computational geometry as well as supporting mission critical software in a production environment. The position requires working in a team with other developers, and interfacing with a large technology development organization. Good communication skills with demonstrated attention to detail and results orientation are required.<br />
<br />
'''Minimum Qualifications''':<br />
* PhD degree in Computer Science, Physics, Electrical Engineering, Mechanical Engineering, or a related engineering discipline <br />
Note: due to the multi-disciplinary nature of the work our team is comprised of world leading experts in fields ranging from Optics/Electromagnetism to Chemical Engineering and Robotics<br />
* Demonstrated coding proficiency, preferably in C++<br />
<br />
'''Preferred Qualifications''':<br />
Background in one or more of the following areas:<br />
* Computer Vision & Machine Learning<br />
* Optics & Electromagnetics Theory<br />
* Parallel Programming and algorithms<br />
* Numerical modeling<br />
* Computational geometry<br />
* Computational lithography methods<br />
* Linear/Non-linear optimization<br />
* Big data, Database Systems, UI <br />
<br />
'''Job Location''':<br />
Hillsboro, Oregon. Located in the beautiful Portland Metro Area, 15 miles west of downtown Portland, Intel Oregon is the largest and most complex site in the world, a global center of semiconductor research and manufacturing, and the largest private employer in the state.<br />
<br />
'''About Our Team''':<br />
We are a highly motivated multi-disciplinary team whose expertise range from computer engineering to physics, electrical engineering to chemical engineering. Our team produces world class solutions for computational lithography systems and has won several Intel achievement awards as well as software quality awards. <br />
<br />
Interested individuals should forward their resumes to cemal.c.bilgin@intel.com<br />
<br />
= Past positions =<br />
<br />
<br />
== Year 2013 ==<br />
<br />
<br />
=== Internship position for developing a MR CAD tool ===<br />
Posted: Oct. 29th 2013<br />
<br />
Eigen is making a difference in patient outcomes and care with our innovative medical imaging products, and we’re looking for a software engineer to join our team.<br />
ProFuse, our MRI image fusion product, is being used on patients daily to provide accurate, repeatable biopsies, with the assistance of Eigen’s mechanical guidance. We have a list of improvements in mind to make the system even better, and that’s where you can help us. We need a quality-focused software intern who’s familiar with C++ - if you know the QT framework, so much the better. You’ll be working with our existing team to add features, and lay the foundation for our next generation of products.<br />
<br />
Requirements:<br />
-In progress degree in Computer Science, Mathematics, Physics, Engineering, Medical Imaging or related discipline.<br />
-UI/UX programming experience.<br />
-Strong interpersonal and communication skills.<br />
-Knowledgeable and experienced with C++ language.<br />
<br />
Desirable but not required:<br />
-Experience with medical devices, avionics, or other regulated technical products.<br />
-Familiarity with ITK and VTK libraries.<br />
-Experience with CMake build system.<br />
-Image processing background strongly preferred.<br />
-Strong mathematics background.<br />
-GPU programming experience (CUDA).<br />
<br />
This is a 6 month internship, on-site at our Grass Valley, CA location, but could lead to a full time W2 position.<br />
<br />
Please send your resumes to hr@eigen.com.<br />
<br />
=== PhD position in multi-modal image processing, b<>com Brest, France ===<br />
<br />
Posted: Oct. 28th 2013<br />
<br />
It is increasingly common to combine multiple methods of treatment, i.e., treatment modalities, with the intention to improve patient outcomes and reduce complications. Each treatment modality may consist of (1) multiple images acquired by one or more modalities (e.g. PET and CT) and (2) contextual information (e.g. clinical reports). To improve patient outcome, one approach is to unify the imaging information and the context information so that the therapy planning, therapy guidance and post-treatment evaluation are simplified. In practice, whereas Picture Archive and Communication Systems (PACS), employed in hospital, store multi-modal images and contextual information, simultaneous re-use of both information cannot be done in a simple fashion.<br />
<br />
This Ph.D. will focus on the integration of multi-modal imaging information accrued by contextual information extracted from a PACS.<br />
<br />
A first problem to address is the analysis of multi-modal images (e.g., PET/CT). This analysis requires, for example, image processing (image quality improvement or image artifact reduction) followed by image analysis (segmentation or biomarker extraction). A second problem to investigate is the association of quantitative parameters extracted from multi-modal images with other contextual information. This also involves the automatic generation of clinical reports both associating results of multi-parameter image analysis and contextual information, with the goal of assisting physicians with clinical decisions. It is intended that this Ph.D. will lead to a Clinical Decision Support System demonstrator dedicated to a specific context/pathology (e.g. oncology or neurology).<br />
<br />
The PhD fellowship is funded by b<>com (http://b-com.com) which is a Technology Research Institute located in Brest, Rennes and Lannion (France). This Ph.D thesis will be carried out under the supervision of M. Hatt (research associate, INSERM) and G. Coatrieux, Assistant Professor (Telecom Bretagne) and located at b<>com on the Brest-Iroise Science and Technology Park.<br />
<br />
Expected qualifications:<br />
- Minimum MSc degree (Computer Science)<br />
- Experience in developing medical imaging applications is desirable<br />
- Prior experience in image analysis, pattern recognition and computer vision<br />
- Programming experience in C++<br />
<br />
Contact: Please send your resume to job@b-com.com<br />
<br />
== Year 2012 ==<br />
<br />
=== Technology Officer in Biomedical Image Computing & Modelling, University of Sheffield, UK ===<br />
<br />
''' Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), University of Sheffield, UK ''' <br />
<br />
Posted: Nov 5th 2012 \<br />
Closes: Nov 21st 2012<br />
<br />
''* About Sheffield ''<br />
<br />
Mechanical Engineering has been a major discipline in the University of Sheffield since its foundation in 1905. In the most recent Research Assessment Exercise the Department came second in the country in the league table of Mechanical Engineering departments, and achieved an "Excellent" rating in the last Teaching Quality Assessment. The Department currently has 41 members of academic staff who support the learning and development of an ever-growing undergraduate and postgraduate student body. For more information on the Department please see our web site http://www.shef.ac.uk/mecheng/.<br />
<br />
The INSIGNEO Institute for in silico Medicine is an initiative between the Faculty of Engineering and the Faculty of Medicine at the University of Sheffield and the Sheffield Teaching Hospitals Foundation Trust. INSIGNEO will realise the scientific ambition behind the Virtual Physiological Human (VPH), producing a transformational impact on healthcare. INSIGNEO performs cutting edge research in areas of fundamental and applied biomedical modelling, imaging and informatics. It will pursue the research agenda of the VPH initiative; in particular, in the first five years it will focus on the Digital Patient, In Silico Clinical Trials, and Personal Health Forecasting. It will achieve transformational impact on healthcare through multidisciplinary collaboration in strategic areas, which initially will include personalised treatments and independent, active and healthy ageing.<br />
<br />
The Computational Imaging and Simulation Technologies in Biomedicine (CISTIB) Group at the University of Sheffield is part of INSIGNEO. CISTIB focuses on algorithmic and applied research in the areas of computational imaging, modeling and simulation. CISTIB is working in different areas of medical image segmentation, statistical shape analysis, pattern recognition and image-based personalized computational electro-mechanics and fluid dynamics, and modeling of virtual interventions with endovascular and cardiac rhythm management devices. The centre hosts academic members from the University of Sheffield as well as research fellows, research associates, PhD Students and scientific software developers forming a cross-disciplinary team of biomedical engineers, computer scientists, electrical engineers, mechanical engineers, physicists, and mathematicians. <br />
<br />
The main objective of CISTIB is to contribute to the development of technologies for advanced screening, diagnostics, interventional guidance and therapy planning of cardio- and neurovascular diseases as well as growing activity in the musculo-skeletal system. Converging technologies such as computational imaging, computational physiology and virtual implantation of medical devices are integrated with state of the art multimodal acquisition systems to achieve an enhanced interpretation of human physiology and pathology and supply integrative approaches for in silico medical device customization, optimization and image-based efficacy assessment. Core technologies include spatial and temporal image segmentation, non-rigid image registration, multimodal image fusion, pattern recognition, statistical shape analysis, multi-view geometry, image-based tissue property estimation, tissue deformation quantification, computational geometry, image-based mesh generation, computational fluid dynamics and electro-mechanical simulation.<br />
<br />
CISTIB fosters basic and applied research and promotes technology transfer to industry. It participates to a number of national and international research projects funded by the European Commission, and holds collaborations with several national and international companies. CISTIB also very close cooperation with clinical centers at the local level and worldwide and has a strong clinically-oriented translational vision.<br />
<br />
'' * Open positions ''<br />
<br />
You will lead and coordinate a team of Scientific Software Developers that will produce prototypes for applied research projects, clinical translation projects, and technology assessment studies. Your work will also support the research program within CISTIB by enabling its researchers to effectively implement new methods and algorithms. Those prototype technologies that are found to be effective will be translated into commercially available products and services, by means of IPR exploitation agreements with existing companies, or by creating dedicated spin-off companies. The ideal candidate has a considerable experience in managing Technical teams. Previous experience in the area of software development related to the Virtual Physiological Human initiative would be an advantage. Your skill set should be properly balanced between experience on research projects and software management to act as an interface between the needs of the technological and clinical researchers of the centre, and the software developers. All development activities should be steered toward the establishment of a portfolio of methods and technologies (i.e. libraries, software frameworks, etc.). You will play a key role in attracting significant research and technological development funding, in collaboration with other CISTIB members, both from public and private sources.<br />
<br />
We are interested in individuals with excellent communication and leadership skills, able to work in a multidisciplinary and international team and contribute to the visibility of the centre in the international scientific community. The ability to interact with other disciplines is essential. The candidate will cooperate with members of the lab working on related topics as well as with our collaborators at several academic institutions in UK and across Europe.<br />
<br />
'' * How to apply ''<br />
<br />
More information and application through http://sheffield.ac.uk/jobs reference UOS005565.<br />
<br />
=== Job - Software Engineer in medical image processing (medInria) - INRIA Rennes - France ===<br />
<br />
Posted June 26, 2012<br />
<br />
R&D Experienced software engineer / Good knowledge of ITK, VTK and Qt<br />
<br />
As part of the development of medInria ([http://med.inria.fr med.inria.fr]), we are proposing a new position for an experienced engineer at Inria Rennes, France (Visages team), starting from october 2012. The recruited person will work among the national team developing medInria, to develop core features and specific medical image processing plugins from the Visages team. More details on the position are available on [https://www.irisa.fr/visages/_media/positions/position_medinria_nt_2012.pdf the position sheet].<br />
<br />
<br />
=== Job - Software Engineer / Research Specialist Lead - Emory University / Georgia Tech ===<br />
<br />
Posted June 8, 2012<br />
<br />
Research Specialist Lead / Software Engineer<br />
<br />
This position offers great opportunities to work in a high-quality academic environment at Emory University and Georgia Institute of Technology, Atlanta, Georgia, USA. The joint Department of Biomedical Engineering (BME) of Emory University and Georgia Institute of Technology provides one of the top BME programs to foster the next generation of leaders in biomedical engineering worldwide. The Department of Radiology and Imaging Sciences at Emory University School of Medicine provides one of the best education, training and research programs in the country. Successful applicant would work under the supervision of the principal investigator and will collaborate with other faculty members, clinicians, researchers, post-doctoral fellows, graduate and undergraduate students in a research team. This person would be involved in projects focused on multimodality medical imaging (ultrasound, PET/CT, and MRI) with emphasis on medical image analysis and image-guided interventions. As a regular staff of Emory University, this person and her/his family would be eligible for a full range of Emory benefits including health and dental insurance, tuition, and other benefits. <br />
<br />
JOB DESCRIPTION: Under minimal supervision, modifies and writes software programs for image processing and analysis. Develops requirements and specifications and implements computer algorithms in software programs. Performs image quantification using commercial software systems or home-made software programs. Uses independent judgment in applying or adapting scientific techniques. Assists in planning and scheduling research procedures. Performs a variety of laboratory tests and procedures. Analyzes and interprets results of studies. Reviews literature for related research developments and techniques and compiles findings. Monitors laboratory processes to maintain quality assurance standards. Records results of studies, compiles and analyzes data and prepares charts and graphs. Performs related responsibilities as required. <br />
<br />
MINIMUM QUALIFICATIONS: Bachelor's or Master’s degree in computer science, mathematics, electrical engineering, biomedical engineering, or other related fields, and two years of working experience, or equivalent combination of experience, education, and training. Two years of experience in software programming is required. Programming experience with IDL, C++, and MATLAB is preferred. Basic knowledge in medical image processing and analysis is required. Knowledge in medical imaging such as MRI, PET, CT, and ultrasound is a plus but not required. <br />
<br />
CONTACT:<br />
Baowei Fei, PhD, EngD,<br />
Georgia Cancer Coalition Distinguished Scholar<br />
Director of Quantitative BioImaging Laboratory (QBIL)<br />
Emory University and Georgia Institute of Technology<br />
1841 Clifton Road NE, Atlanta, GA 30329, USA<br />
Email: bfei@gatech.edu<br />
<br />
<br />
To apply for the position, send CV and Personal Statement to bfei@gatech.edu <br />
<br />
<br />
== Year 2011 ==<br />
<br />
=== ITK-SNAP Software Developer - University of Pennsylvania ===<br />
<br />
Posted Dec 5, 2011<br />
<br />
The Penn Image Computing and Science Laboratory (PICSL) seeks a qualified C++ programmer to support the development of ITK-SNAP, an interactive software application for biomedical image segmentation. The programmer will work with the principal investigator on an NIH-funded grant to develop the next-generation GUI for ITK-SNAP, accelerate the tool=92s performance, and incorporate multi-modality image segmentation algorithms. Applicants must have a Bachelors degree in computer science or related field. Minimal qualifications are<br />
<br />
* C++ programming (4 years experience)<br />
* Experience with user interface programming, preferably Qt<br />
* Strong interpersonal and communication skills, and ability to work<br />
independently<br />
<br />
Applicants with expertise in the following ares are particularly encouraged to apply:<br />
<br />
* Familiarity with ITK and VTK libraries, and CMake build system<br />
* Image processing, computer vision, and computer graphics<br />
* Strong mathematics background<br />
* GPU programming experience (CUDA, OpenCL)<br />
* Experience working in a research environment<br />
* Advanced degree in related field<br />
<br />
PICSL is a dynamic and growing research group involved in many exciting biomedical imaging projects, including development of novel analysis methodologies; application of the state-of-the-art techniques to clinical studies; and translational research. PICSL is located in Philadelphia, a vibrant city that offers many professional and cultural opportunities. PICSL fosters a friendly, noncompetitive, collaborative environment where each individual member of the laboratory is able to thrive, while also effectively contributing to the group=92s overall programmatic aims.<br />
<br />
The position is funded by a federal grant. Continued employment is subject to performance and availability of grant funding. PICSL has an excellent track record of obtaining research funding and personnel retention. The position features a competitive compensation package with generous fringe benefits.<br />
<br />
The University of Pennsylvania is an equal opportunity, affirmative action employer. Women and minority candidates are strongly encouraged to apply.<br />
<br />
Interested candidates should send an email to the address below. Please include the words =93snap developer=94 on the subject line. Include a brief statement of qualifications relevant to the project, a CV or resume, and a list of 3 references.<br />
<br />
Paul Yushkevich, Ph.D.<br />
Assistant Professor<br />
Penn Image Computing and Science Laboratory (PICSL)<br />
Department of Radiology<br />
University of Pennsylvania<br />
<br />
Email: pauly2 [at] mail [.] med [.] upenn [.] edu<br />
http://picsl.upenn.edu<br />
http://itksnap.org<br />
<br />
<br />
=== Software Engineer(s)-Electrical Geodesics, Inc. ===<br />
<br />
Electrical Geodesics, Inc. (www.egi.com), an international medical device company in the neurology/neuroscience field, is seeking to fill “three” software engineer position. The Software Engineer is responsible for software related product development, product engineering activities, and grant support.<br />
<br />
Opening 1Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• C++ (Objective-C a plus)<br />
Make, CMake, and other build environment expertise.<br />
<br />
• VTK, ITK, Tcl/Tk<br />
<br />
Desired Experiences:<br />
<br />
• MRI Processing<br />
• Cross platform development (Mac, Linux, Windows) experience a plus.<br />
<br />
Opening 2 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java, C, C++ (Objective-C a plus).<br />
<br />
Opening 3 Requirements:<br />
• Bachelor's degree in Computer Science, Mathematics, or strongly related field<br />
• 2 years experience in a multi-platform environment.<br />
• Java (principle), C, C++ (Objective-C a plus)<br />
• Strong knowledge of application server environments.<br />
• Strong profiency in database engineering, and demonstrable knowledge of SQL.<br />
• Experience with Netbeans or Eclipse (and comfortable to use either).<br />
<br />
Full Time, exempt, salary position with benefits.<br />
<br />
To apply for any of the above openings, resume and cover letter should be sent to dmarquez@egi.com<br />
<br />
<br />
=== Master training position, INRIA Sophia Antipolis, France: Prediction of Cardiac Electrophysiology Signal Characteristics from Image Features ===<br />
<br />
<br />
The aim of this project is to analyse both cardiac images and electrophysiology signals in order to explore correlations. Developped features will be mapped on a 3D mesh and overlaid on anatomical images of the heart in order to guide interventions. This project will require image analysis, registration for correlating anatomical and functional information, and machine learning. This project will be in collaboration with Bordeaux University Hospital.<br />
<br />
More information can be found in the detailed job description: <br />
<br />
http://www-sop.inria.fr/asclepios/recrutement/MasterTrainingINRIA2011.pdf<br />
<br />
<br />
== Year 2010 ==<br />
<br />
=== Postdoctoral Position: MIT/Harvard Medical School, Cambridge/Boston, MA ===<br />
<br />
* Posted on December 3rd 2010<br />
<br />
Location: Cambridge/Boston, MA<br />
Type: Postdoctoral position in Medical Robotics<br />
Expires:January 01, 2011<br />
<br />
Job description: We are currently seeking an engineer/computer scientist to join our dynamic team that is developing image-guided robots for accurate and efficient tumor ablation. The person will ideally have medical image processing experience and will be developing user interfaces for controlling robots using information in the medical imaging data.<br />
<br />
Our group involves a collaboration between the Massachusetts Institute of Technology, Massachusetts General Hospital and Brigham and Women's Hospital and has a large amount of technical and clinical expertise in this area.<br />
<br />
Information regarding the open positions and desired qualifications can be provided upon request. Graduate students, post-doc and recent graduates will all be considered. Interested candidates should send a CV and a brief paragraph along to Dr. Conor Walsh at walshcj@mit.edu.<br />
<br />
<br />
=== Two Postdoctoral Positions: Harvard Medical School, Boston, MA ===<br />
<br />
* Posted on November 30th 2010<br />
<br />
Website:http://http://vcp.med.harvard<br />
Location: Boston, MA<br />
Type: Postdoctoral<br />
Expires:January 22, 2011<br />
<br />
Job description: Applications are invited for two postdoctoral-level positions on a collaborative project funded by the European Human Frontiers Programme between the laboratories of Alfonso Martinez-Arias in the Department of Genetics at the University of Cambridge, UK, Kat Hadjantonakis in the Developmental Biology Program at Memorial Sloan Kettering Cancer Center in New York and Jeremy Gunawardena in the Department of Systems Biology at Harvard Medical School in Boston. The project centres on analysing signalling and gene regulation networks in the pre-implantation mouse embryo and in mouse embryonic stem cells, using quantitative measurements, 4D whole-embryo imaging, microfluidic devices and mathematical modelling. The first position is with Hadjantonakis in New York to develop a quantitative image analysis platform for 4D mouse embryo imaging. The successful applicant will need strong technical capabilities in live-cell image analysis, familiarity with software tool development with a focus on usability and the desire to work in close collaboration with experimentalists. The second position is with Gunawardena in Boston to analyse mouse ES cells using microfluidic devices and modelling. The successful applicant will have experience studying mammalian cells in culture using quantitative experimental methods, an interest in exploiting microfluidic technologies and an ability to work with mathematical models of molecular networks. Both positions will require occasional travel between the sites and an annual visit to Cambridge, UK. Interested candidates are asked to send a CV and the contact details of two referees to one of the two addresses below, along with a cover letter stating clearly why his or her background is appropriate for the corresponding position. The deadline for applications is 31 December 2010.<br />
<br />
Kat Hadjantonakis<br />
Developmental Biology Program<br />
Sloan-Kettering Institute<br />
New York, NY 10065,<br />
USA<br />
http://www.ski.edu/hadjantonakis<br />
<br />
Jeremy Gunawardena<br />
Department of Systems Biology<br />
Harvard Medical School<br />
200 Longwood Avenue<br />
Boston, MA 02115<br />
USA<br />
<br />
By e-mail to Nicole Wong, Nicole_Wong@hms.harvard.edu<br />
<br />
http://vcp.med.harvard.edu/<br />
<br />
=== Research Scientist (Junior) - Image and Signal Processing - Rennes,France ===<br />
<br />
* Posted on September 14th 2010<br />
<br />
Bruce Junior Chair position<br />
<br />
http://www.rbucewest.ueb.eu/<br />
<br />
R-Buce Junior Chair position in Biomedical Engineering.<br />
<br />
The UEB - UR1 seeks research scientist applicants working in the broad field of biomedical engineering, with particular focus on themes at the frontiers of ICT and health. Of special interest are the following topics: model-based bio-signal / bio-imaging processing and interpretation, integrative modeling, knowledge-based information representation and interpretation.<br />
<br />
The UEB - UR 1 laboratories involved in biomedical engineering have strong clinical partnerships with a number of medical institutions, including the Rennes University Hospital and the Centre of Cancer Eugène Marquis at Rennes.<br />
<br />
Qualified candidates working in the broad area of biomedical engineering, developing computational tools or multiscale systems-based techniques are encouraged to apply. Required qualifications include a doctorate in engineering or a related field with an outstanding record of publications in internationally recognized journals.<br />
<br />
Interested persons should submit detailed curriculum vitae including academic and professional experience, a list of peer-reviewed publications and any other technical documents relevant to the application.<br />
<br />
salary range : ~40kE/year + relocation<br />
<br />
Please send cover letter and resume to Oscar Acosta / Lotfi Senhadji <br />
(Oscar.Acosta@univ-rennes1.fr, Lotfi.Senhadji@univ-rennes1.fr) <br />
<br />
<br />
== Year 2009 ==<br />
<br />
=== Software Engineer (Junior) - Harvard Medical School ===<br />
<br />
* Posted on August 14th 2009<br />
<br />
The Megason Laboratory in the Department of Systems Biology at Harvard Medical School seeks to hire a Software Engineer for participating in the continued development of GoFigure. The lab’s goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology (www.digitalfish.org). The Software Engineer will be responsible for participating in the continued development of the principle software application for this endeavor called GoFigure. GoFigure recognizes and tracks cells in extremely large 4-dimensional (xyzt) image sets and digitizes that data into a database. GoFigure is written in C++, is cross-platform and uses Qt, MySQL, VTK (the Visualization Toolkit), ITK (Insight Segmentation and Registration Toolkit), CMake. The project is managed using Subversion, Doxygen for documentation generation, CTest and CDash for testing. The successful applicant should have a strong background in programming and work well in an academic environment. Interests in application development, image processing, microscopy, and systems biology are also a plus.<br />
<br />
'''Job Duties'''<br />
<br />
* Participate in software development project for GoFigure. GoFigure is developed by a team of ~4 which is lead by a Senior Research Engineer<br />
* Responsible for the development and testing of code as specified by management (senior software engineer and lab director). Incumbent will write code and will assist management in integration of code into GoFigure<br />
* Performs ongoing modifications and solution alternatives to accomplish research requirements of GoFigure software<br />
* Collaborates with researchers to define new strategies, approaches, methods and techniques to enhance research efforts<br />
* Participate in regular lab meetings, journal club presentations, and retreats<br />
* Other duties as assigned<br />
<br />
Please send cover letter and resume to Sean Megason<br />
(megason@hms.harvard.edu) <br />
<br />
=== Computer Programming - Image Guided Intervention ===<br />
<br />
* Posted Aug 2009,<br />
<br />
Department of Medicine at Harvard Medical School and Beth Israel Deaconess Medical Center is looking to hire a full time software engineer with strong background in computer vision and ITK/VTK. Intrested applicant should send a CV to :<br />
<br />
Reza Nezafat, Ph.D. rnezafat@bidmc.harvard.edu<br />
<br />
<br />
== Year 2008 ==<br />
<br />
=== Staff Scientist - Medical Image Processing ===<br />
<br />
* Posted: November, 2008<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 4 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service <br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Radiology and Imaging Sciences<br />
National Institutes of Health Clinical Center<br />
Building 10 Room 1C368X MSC 1182<br />
Bethesda, MD 20892-1182<br />
E-mail: rms@nih.gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== Research Developer - Medical Imaging ===<br />
<br />
'''About Calgary Scientific'''<br />
<br />
Calgary Scientific Inc. (CSI) is a software and intellectual property (IP) development company specializing in sophisticated digital signal, image processing and analysis technology. Our current product line includes customer focused applications for medical imaging and seismic data imaging. These applications offer innovative tools to help professionals to better interpret and analyze data through core innovations around which CSI applications are developed.<br />
<br />
Calgary Scientific is a privately held company with offices in Calgary, Alberta, Canada. The company was formed in 2003 to commercialize leading edge intellectual property into market leading software applications.<br />
<br />
Calgary Scientific works with research teams and individuals across multiple Universities to generate, refine, test, and commercialize breakthrough innovation into market driven commercial applications.<br />
<br />
'''Research Developer – Medical Imaging Role'''<br />
<br />
We are looking for several full-time Research Developers with Medical Image Processing skills who are willing to relocate to Calgary, Alberta, Canada. Duties will include:<br />
<br />
* Incorporating cutting edge research code from around the world into our production quality, C++ core technologies<br />
<br />
* Working with Research Scientists and Research Associates on various medical image processing algorithms<br />
<br />
* Working with QA to design and develop unit and validation tests that meet our ISO 13485 and ISO 14971 requirements<br />
<br />
* Working directly with Agile Product Teams to ensure the rapid integration of new technologies into various medical applications<br />
<br />
This is an excellent opportunity to contribute to the commercialization of market-driven medical imaging applications.<br />
<br />
'''Required Experience/Skills:'''<br />
<br />
* Degree in Engineering, Physics, Computer Science, or related fields<br />
<br />
* 5 or more years of experience in C++ development<br />
<br />
* 1 or more years of matlab and OpenGL experience<br />
<br />
* Applied or advanced math training, particularly in medical image processing or artificial intelligence<br />
<br />
* Demonstrated ability to learn new technologies<br />
<br />
* Desire to contribute to the successful commercialization of leading-edge technology<br />
<br />
'''Beneficial Experience/Skills:'''<br />
<br />
* Algorithm development using ITK<br />
<br />
* Working within an ISO certified environment<br />
<br />
Applications can be sent to careers@calgaryscientific.com<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
=== Post-doctoral Research Openings at Rensselaer Polytechnic Institute ===<br />
<br />
The FARSIGHT project has openings for several post-doctoral associates (or experienced individuals with a Masters degree), starting May 1, 2008. This project is developing an open-source 4-D/5-D image analysis toolkit for advanced biological microscopy of brain tissue, tumors, and immune system components. The required skills include <br />
<br />
* High-quality C++ programming, <br />
* 3-D image processing (segmentation, classification, registration), and <br />
* 3-D graphics programming. <br />
<br />
Prior exposure to ITK and/or VTK, and disciplined software development processes is highly desirable. <br />
<br />
These positions are renewable annually. <br />
<br />
Please contact <br />
Prof. Roysam <br />
by email: Roysam@ecse.rpi.edu.<br />
<br />
Badri Roysam<br />
Professor, Department of Electrical, Computer and Systems Engineering<br />
Associate Director, NSF Center for Subsurface Sensing & Imaging Systems (CenSSIS ERC)<br />
Rensselaer Polytechnic Institute<br />
110 8th Street, Troy, New York 12180-3590.<br />
Office(JEC 7010): 518-276-8067, Lab(JEC 6308): 518-276-8207, Fax: 518-276-8715<br />
Web: http://www.ecse.rpi.edu/~roysam<br />
<br />
=== Senior Developer - Medical Image Processing ===<br />
<br />
Status: Filled<br />
<br />
Please see http://www.calgaryscientific.com/company/careers.html for additional opportunities.<br />
<br />
<br />
=== Software Engineer, Intuitive Surgical Inc., Sunnyvale California ===<br />
<br />
The da Vinci(r) Surgical system includes six manipulator arms with a total of 41 degrees of freedom, along with a stereo endoscope and 3D video display, with over 600 installations worldwide. Surgeons use it to perform tens of thousands of minimally invasive surgeries per year. da Vinci represents an outstanding platform for the development and application of new technologies to surgery. This position offers an opportunity for a candidate with exceptional software development skills to work on projects ranging from blue-sky research to those ready for transition to product development groups. A successful candidate will be equally comfortable leading architecture development and producing high-quality implementations that lend themselves to re-use, testing, and productization. He or she must excel in a high energy team, must have excellent communication skills and must be able to balance independent production of results with the need to collaborate during planning, system integration, and testing of larger projects. This engineer will work closely with other members of the Applied Research Group and several product development groups on algorithm development, implementation, and systems integration.<br />
<br />
For more details, as well as to upload a resume, please visit our OpenHire listing:<br />
* Position: Software Engineer<br />
* Tracking Code: 220333-609<br />
* Posted: November, 2007<br />
* URL: http://hostedjobs.openhire.com/epostings/jobs/submit.cfm?fuseaction=dspjob&id=23&jobid=220333&company_id=15609&version=1&source=ONLINE&JobOwner=956377&level=levelid1&levelid1=10630&parent=Engineering&startflag=2&CFID=8647986&CFTOKEN=46344848<br />
<br />
<br />
=== Research Scientist Position in Medical Imaging in Brisbane, Australia ===<br />
<br />
CSIRO ICT centre is seeking to fill several positions at the scientist and post-doctoral level to work on neuro-degenerative diseases and brain tumour characterization.<br />
The Biomedical Imaging team part of the Australian e-Health Research centre is a leading Australian medical imaging research group, with a well developed expertise in image registration, extraction of quantitative information (shape, volume, texture), morphometry, soft-tissue modelling (3D meshing, visual and haptic interaction) and data classification. The successful applicants will be involved in activities focused on the development and application of novel techniques for segmentation, registration and analysis of PET and MR images. These positions offer the opportunity to work in a high quality research environment, with strong clinical collaboration. The research scientists and post-doctoral fellows will join a large team (>20 scientists, post-doctoral fellows, and students) in an exciting working environment ideally located in one of the fastest growing city in Australia close to many attractions and beautiful beaches.<br />
More details can be found on the CSIRO career website: <br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F487<br />
https://recruitment.csiro.au/asp/job_details.asp?RefNo=2008%2F9<br />
For further information please contact <br />
Olivier Salvado, PhD<br />
Team Leader Biomedical Imaging<br />
olivier.salvado@csiro.au<br />
<br />
CSIRO ICT Centre<br />
Australian e-Health Research Centre (AEHRC)<br />
Phone: +61 7 3024 1658<br />
Fax: +61 7 3024 1690<br />
Mobile: +61 4 0388 2249<br />
web: http://www.aehrc.net/<br />
<br />
== Year 2007 ==<br />
<br />
=== Summer 2007: National Institutes of Health Postdoc ===<br />
<br />
Post-doctoral fellowships are available in clinical image processing. Specific interest areas are image processing (virtual endoscopy, volumetric visualization, image segmentation, registration, fusion, and algorithm development) and computer-aided diagnosis (feature extraction, classification, and databases). Fellows have access to state-of-the-art whole body MRI, multi-row detector CT and advanced graphics workstations. Candidates must have or soon expect to receive doctorates in applied mathematics or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on image processing or computer visualization and having strong software development and C++ skills are encouraged to apply. Initial appointment is for two years and is renewable thereafter on a periodic basis. NIH is an equal opportunity employer.<br />
<br />
Address applications to: <br />
Jianhua Yao, Ph.D. <br />
Clinical Image Processing Service <br />
Department of Radiology <br />
National Institutes of Health <br />
10 Center Drive Bethesda, MD 20892-1182 <br />
E-mail: jyao@cc.nih.gov <br />
<br />
<br />
=== August 2007 to sept. 2008: Caltech & Harvard Medical School ===<br />
<br />
The Caltech Center of Excellence in Genomic Science (CEGS) is a newly funded initiative that’s driven to digitize life. Our goal is to understand embryonic development as the execution of a program in our genome. We seek to upload embryonic development into a virtual life form called the Digital Fish through the use of genetics, molecular imaging, and information technology. Our approach called “in toto imaging” is to use confocal/2-photon imaging to image all the cells in developing transgenic zebrafish embryos and special software we are developing called GoFigure to extract complete cell lineages and gene expression patterns.<br />
<br />
We are looking for people with strong experience in C++ programming and VTK/ITK to join our GoFigure development team. There are a number of significant image analysis problems we are addressing including: segmenting cells in space, across time, and across cell division; quantitating protein expression patterns and subcellular localization; developing a standard, cell-based, 4-d atlas of embryonic development; and registering molecular data from thousands of different embryos onto this atlas.<br />
<br />
There are opportunities at the graduate, post-doc, and staff levels. The successful applicant would join our team at Caltech in Pasadena/LA soon and then move with us to my new lab in the Department of Systems Biology at Harvard Medical School in Boston in summer 2008. To apply, please send a cover letter, CV, and letters of reference to me by email (megason@caltech.edu).<br />
<br />
For more information please see below:<br />
www.digitalfish.org <http://www.digitalfish.org/> <br />
or talk to Alexandre Gouaillard or myself at the upcoming NAMIC meeting in Boston ( june 2007 ).<br />
http://www.na-mic.org/Wiki/index.php/NA-MIC_NCBC_Collaboration:3D%2Bt_Cells_Lineage:GoFigure<br />
<br />
Sean Megason<br />
<br />
=== Spring 2007: University of Texas - M. D. Anderson Cancer Center ===<br />
<br />
The Image Processing & Visualization Laboratory (IPVL) has opened positions for a Programmer Analyst, Post Doctorate and Research Scientist to support its core mission in America’s largest cancer center.<br />
<br />
Images handled by the IPVL span the full spectrum of human and animal (small to large) imaging instrumentation for applications that range from research to clinic, all in direct and close interaction with departments and investigators throughout the institution. Computer equipment includes high-end clinical workstations and software, as well as high-end platforms under Windows, Linux or OSX for developments with OpenSource toolkits, IDL or MatLab. Other available equipment include database and compute servers (Windows, Unix/Solaris/Linux), as well as a state-of-the-art 512 CPUs cluster and 32 CPUs SMP, both shared with the institution and entirely dedicated to research.<br />
<br />
The successful candidates will need to demonstrate – in various capacities that depend on the targeted position - expertise and interest in the design, development, implementation or exploitation of advanced imaging applications, ideally in a biomedical setting and with multidimensional, multimodality and quantitative imaging for clinical and research applications. Topics of particular interests are 3D+ imaging (e.g., rendering, segmentation, navigation), non-rigid registration, parametric and quantitative imaging, kinetic modeling, etc. Expertise in modern and relevant languages and toolkits (e.g., C/C++, VTK, ITK, IGSTK) as well as in matching development tools and environments is considered an asset.<br />
<br />
If you believe your experience matches any of these profiles, please send your CV and other relevant information (e.g., three references, statement of interest/qualification for the specific position) to:<br />
<br />
Dr. Luc Bidaut, Ph.D.<br />
Director of the IPVL<br />
E-mail: lbidaut at mdanderson dot org<br />
<br />
== Year 2006 ==<br />
<br />
=== May 2006: National Institutes of Health Staff Scientist Position ===<br />
<br />
'''Staff Scientist'''<br />
Medical Image Processing<br />
Warren G. Magnuson Clinical Center Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research and clinical efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) and machine learning are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Computer Science, Electrical or Biomedical Engineering, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applicati!<br />
ons should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html <br />
<br />
=== Spring 2006: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing – Computer-Aided Detection<br />
Warren G. Magnuson Clinical Center <br />
Department of Radiology<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
A post-doctoral fellowship is available in three-dimensional radiology image processing. Specific interest areas are virtual endoscopy, volumetric visualization, image segmentation, registration and computer-aided detection (including feature extraction, classification, image databases and observer performance analysis [ROC]). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. Fellows have access to state-of-the-art whole body MRI, multi-detector helical CT, advanced graphics workstations (Windows PC) and Beowulf massively parallel processing cluster. Candidates must have or soon expect to receive doctorates in physics, biophysics, mathematics, statistics, biomedical engineering or computer science. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of computer visualization and image processing and having advanced mathematical and computer skills are encouraged to apply. Initial appointment is for one to two years and is renewable thereafter on a periodic basis. Applications should include a CV, brief statement of research interests and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
*Address applications to:<br />
<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: rms at nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
== Year 2005 ==<br />
<br />
=== Spring/Summer 2005: National Institutes of Health Postdoc ===<br />
<br />
'''Post-doctoral Fellowship'''<br />
Medical Image Processing<br />
Department of Radiology<br />
National Institutes of Health<br />
Department of Health and Human Services<br />
<br />
A Post-doctoral fellowship is available in three-dimensional medical<br />
imaging. Specific interest areas are image processing (virtual endoscopy,<br />
volumetric visualization, image segmentation, registration, fusion, and<br />
algorithm development) and computer-aided diagnosis (feature extraction,<br />
classification, and databases). Fellows have access to state-of-the-art<br />
whole body MRI, 16-row detector CT+PET and advanced graphics workstations (PC and Beowulf cluster). Candidates must have or soon expect to receive<br />
doctorates in applied mathematics or computer science. Applicants with a<br />
proven track record as evidenced by peer-reviewed publications on image <br />
processing and having strong software development and C++ skills are encouraged to apply. GPU shader programming experience is a plus. Applications should include a CV and a brief statement of research interests. NIH is an equal opportunity employer. If a US work permit is not available, then the only visa the NIH can provide for this position is a J visa.<br />
<br />
* Address applications to:<br />
<br />
Ingmar Bitter, Ph.D.<br />
Clinical Image Processing Services<br />
Diagnostic Radiology Department<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: ibitter at nih dot gov<br />
<br />
<br />
== Year 2004 ==<br />
<br />
=== November 2004: Kitware ===<br />
<br />
Kitware is seeking to fill positions immediately. We are looking for people who will relocate to the Albany, NY USA area, are willing to work in a small company, and show flexibility in work assignments. Important skills include proficiency in C++, scientific software development, medical image analysis, and/or ITK. Individuals demonstrating expertise in areas that significantly extend Kitware's software skill base are particularly favored. Please send your resume to kitware at kitware.com.<br />
<br />
Will<br />
<br />
William J. Schroeder, Ph.D.<br />
Kitware, Inc.<br />
28 Corporate Drive, Suite 204<br />
Clifton Park, NY 12065<br />
will.schroeder at kitware.com<br />
1-518-371-3971 x102 (phone)<br />
1-518-371-3971 (fax) <br />
<br />
([http://public.kitware.com/pipermail/insight-users/2004-July/009562.html Original post])<br />
<br />
<br />
=== Nov 2004: National Institutes of Health Staff Scientist ===<br />
<br />
Warren G. Magnuson Clinical Center<br />
National Institutes of Health<br />
U.S. Department of Health and Human Services<br />
<br />
'''Staff Scientist'''<br />
'''Medical Image Processing'''<br />
<br />
<br />
The Department of Radiology is seeking a Staff Scientist to support our research efforts in image processing (virtual endoscopy, volumetric visualization, segmentation, registration and algorithm development) and computer-aided diagnosis (feature extraction, classification, database development). In particular, advanced skills in image segmentation (level sets, active shape/appearance models, etc.) are sought. The incumbent will work closely with a team of computer scientists and engineers. Applicants with a proven track record as evidenced by peer-reviewed publications on medical applications of image processing and having advanced mathematical and computer skills are encouraged to apply. Demonstrated expertise in C++ and ITK (NLM’s Insight Toolkit) are required. The candidate should have a Ph.D. in Electrical or Biomedical Engineering, Computer Science, Mathematics, Biophysics or Physics. Salary commensurate with experience. Applications should include a CV, brief statement of research interests, and three letters of reference. Applications are due 6 weeks after posting of this announcement. DHHS and NIH are Equal Opportunity Employers.<br />
<br />
Address applications to:<br />
Ronald Summers, M.D., Ph.D.<br />
Chief, Clinical Image Processing Service<br />
and Virtual Endoscopy and Computer-Aided Diagnosis Laboratory<br />
Department of Radiology<br />
National Institutes of Health<br />
Building 10 Room 1C660<br />
Bethesda, MD 20892-1182<br />
E-mail: RobertsonS at cc dot nih dot gov<br />
Web site: http://www.cc.nih.gov/drd/summers.html<br />
<br />
<br />
=== June 2004: Computer Vision Research Position ===<br />
<br />
'''Computer Vision Research Positions at GE Global Research'''<br />
Visualization and Computer Vision Lab<br />
<br />
We are seeking highly qualified candidates to innovate and develop computer vision technology for commercial and government applications. We are particularly interested in recruiting candidates with expertise in one of the following areas:<br />
<br />
* Machine Learning - applying semantic knowledge to practical vision problems <br />
* Deformable Registration / Deformable Modeling<br />
* Segmentation<br />
* Object Detection and Tracking<br />
<br />
The Visualization & Computer Vision Lab at GE Global Research in Niskayuna, NY conducts basic and applied research in computer vision and closely related areas. With 30 Staff Researchers (most holding a PhD) the lab develops advanced technologies for GE businesses, including GE Security, GE Healthcare, GE Aircraft Engines, GE Power Systems and NBC Universal; Lockheed Martin; and US Government agencies including NIH, DARPA, FBI, AFRL and NIMA. Areas of active research include image segmentation, deformable registration, perceptual organization, texture classification, object detection, event recognition, tracking, camera calibration, optical metrology, video content extraction, change detection, and superresolution.<br />
<br />
We are active users and contributors to ITK and VXL; experience with either of these toolkits is desired. Strong C++ skills along with a superior ability to work in a team environment are essential qualities for successful candidates.<br />
<br />
Interested? Please contact Jim Miller at `millerjv at research.ge.com`<br />
<br />
Visualization & Computer Vision<br />
GE Research<br />
Bldg. KW, Room C218B<br />
P.O. Box 8, Schenectady NY 12301<br />
<br />
<br />
{{ITK/Template/Footer}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples&diff=48630ITK/Examples2012-08-24T18:16:06Z<p>Ccagataybilgin: /* Blob Detection, Labeling, and Properties */</p>
<hr />
<div>These are fully independent, compilable examples, developed with these [[ITK/Examples/Goals|goals]] in mind. There is significant overlap in the examples, but they are each intended to illustrate a different concept and be fully stand alone compilable.<br />
Please add examples in your areas of expertise!<br />
You can checkout the entire set of examples from this repository: <br />
http://gitorious.org/itkwikiexamples/itkwikiexamples<br />
<pre>git clone git://gitorious.org/itkwikiexamples/itkwikiexamples.git ITKWikiExamples</pre><br />
<br />
==About the Examples==<br />
* [http://www.itk.org/Wiki/images/e/e6/ITK_Examples_Iowa_Meeting_2010_11-8-2010.odp Official announcement]<br />
===ItkVtkGlue===<br />
ITK and VTK are very separate toolkits - ITK for image processing and VTK for data visualization. It is often convenient to use the two together - namely, to display an ITK image on the screen. The ITKVtkGlue module serves exactly this purpose. Also provided inside ItkVtkGlue is a QuickView class to allow a 2 line display of an ITK image.<br />
<br />
===[[ITK/Examples/Instructions/ForUsers|Information for Wiki Examples Users]]===<br />
If you just want to use the Wiki Examples, [[ITK/Examples/Instructions/ForUsers|go here]]. You will learn how to search for examples, build a few examples and build all of the examples.<br />
<br />
===[[ITK/Examples/Instructions/ForDevelopers|Information for Wiki Examples Developers]]===<br />
If you want to contribute examples [[ITK/Examples/Instructions/ForDevelopers|go here]]. You will learn how to add a new example and the guidelines for writing an example.<br />
<br />
===[[ITK/Examples/Instructions/ForAdministrators|Information for Wiki Examples Administrators]]===<br />
If you are a Wiki Example Administrator or want to learn more about the process [[ITK/Examples/Instructions/ForAdministrators|go here]]. You will learn how the Wiki Examples repository is organized, how the repository is synced to the wiki and how to add new topics, tests and regression baselines.<br />
<br />
==CMake Techniques==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/CMake/CheckForModule | Check if a specific module is present]] || || <br />
|-<br />
| [[ITK/Examples/CMake/CheckForITK4 | Check for ITK4]] || || <br />
|}<br />
<br />
==Visualization==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Visualization/QuickView | Display an image]] || || QuickView<br />
|}<br />
<br />
==Simple Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RequestedRegion | Apply a filter only to a specified region of an image ]] || || SetRequestedRegion<br />
|-<br />
| [[ITK/Examples/SimpleOperations/WidthHeight | Get the width and height of an image ]] || || row, column<br />
|-<br />
| [[ITK/Examples/SimpleOperations/VariableLengthVector | Variable length vector ]] || {{ITKDoxygenURL|VariableLengthVector}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TranslationTransform | Translate an image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|ResampleImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/NumericTraits | Get some basic information about a type]] || {{ITKDoxygenURL|NumericTraits}}|| Zero<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ScalarToRGBColormapImageFilter | Apply a color map to an image]] || {{ITKDoxygenURL|ScalarToRGBColormapImageFilter}}|| Pseudocolor, pseudo-color<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CustomColormap | Create and apply a custom colormap]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/ParaviewColormap | Create and apply a colormap closely resembling the default Paraview colormap "Cool to warm"]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TryCatch | Catch an ITK exception]] || || Try/Catch blocks<br />
|-<br />
| [[ITK/Examples/SimpleOperations/BresenhamLine | Get the points on a Bresenham line between two points]] || {{ITKDoxygenURL|BresenhamLine}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/Offset | Add an offset to a pixel index]] || {{ITKDoxygenURL|Offset}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenPoints | Distance between two points]] || {{ITKDoxygenURL|Point}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenIndices | Distance between two indices]] || {{ITKDoxygenURL|Point}}, {{ITKDoxygenURL|Index}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CreateVector | Create a vector]] || {{ITKDoxygenURL|Vector}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/GetNameOfClass | Get the name/type/class of an object ]] || || GetNameOfClass()<br />
|-<br />
| [[ITK/Examples/Images/Index | An object which holds the index of a pixel ]] || {{ITKDoxygenURL|Index}} || <br />
|-<br />
| [[ITK/Examples/Images/Size | An object which holds the size of an image ]] || {{ITKDoxygenURL|Size}} || <br />
|-<br />
| [[ITK/Examples/Images/ImageRegion | An object which holds the index (start) and size of a region of an image ]] || {{ITKDoxygenURL|ImageRegion}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/Transparency | Make part of an image transparent]] || {{ITKDoxygenURL|RGBAPixel}} || Transparency, RGBA, alpha<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionIntersection | Determine if one region is fully inside another region]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/PixelInsideRegion | Determine if a pixel is inside of a region]] || {{ITKDoxygenURL|ImageRegion}} || IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionOverlap | Determine the overlap of two regions]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, crop a region<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ImageDuplicator | Duplicate an image]] || {{ITKDoxygenURL|ImageDuplicator}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/RandomImageSource | Produce an image of noise]] || {{ITKDoxygenURL|RandomImageSource}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/SetPixels | Set specified pixels to specified values]] || {{ITKDoxygenURL|Image}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RGBPixel | Create an RGB image]] || {{ITKDoxygenURL|RGBPixel}} ||<br />
|}<br />
<br />
==Mathematical Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/CovariantVector | Create a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || This is the object which should be used to represent a mathematical vector.<br />
|-<br />
| [[ITK/Examples/Math/CovariantVectorNorm | Compute the norm of a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || In-place and non-inplace norms.<br />
|-<br />
| [[ITK/Examples/Math/Matrix | Matrix ]] || {{ITKDoxygenURL|Matrix}} || <br />
|-<br />
| [[ITK/Examples/Math/Pi | Mathematical constant pi = 3.14 ]] || {{ITKDoxygenURL|Math}} || <br />
|-<br />
| [[ITK/Examples/Math/DotProduct | Dot product (inner product) of two vectors ]] || {{ITKDoxygenURL|Vector}} || <br />
|}<br />
<br />
==Trigonometric Filters==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/Trig/SinImageFilter | Compute the sine of each pixel.]] || {{ITKDoxygenURL|SinImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Math/Trig/Atan2ImageFilter | Compute the arctangent of each pixel.]] || {{ITKDoxygenURL|Atan2ImageFilter}}<br />
|}<br />
<br />
==Image Functions==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Functions/NeighborhoodOperatorImageFunction | Multiply a kernel with an image at a particular location]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunction | GaussianBlurImageFunction ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunctionFilter | GaussianBlurImageFunctionFilter ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/MedianImageFunction| Compute the median of an image at a pixels (in a regular neighborhood)]] || {{ITKDoxygenURL|MedianImageFunction}} || <br />
|}<br />
<br />
==Point Set==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/PointSet/CreatePointSet | Create a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/ReadPointSet | Read a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/WritePointSet | Write a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/BoundingBox | Get the bounding box of a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|}<br />
<br />
==Input/Output (IO)==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/IO/ReadVectorImage| Read an image file with an unknown number of components]] || {{ITKDoxygenURL|ImageFileReader}},{{ITKDoxygenURL|VectorImage}} || <br />
|-<br />
| [[ITK/Examples/IO/ImportImageFilter| Convert a C-style array to an itkImage]] || {{ITKDoxygenURL|ImportImageFilter}} || <br />
|-<br />
| [[ITK/Examples/IO/ReadUnknownImageType | Read an image file without knowing its type before hand]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileWriter | Write an image]] || {{ITKDoxygenURL|ImageFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileReader | Read an image]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/TIFFImageIO | Write a TIFF image]] || {{ITKDoxygenURL|TIFFImageIO}} || This is a general demonstration of how to use a specific writer rather than relying on the ImageFileWriter to choose for you.<br />
|-<br />
| [[ITK/Examples/IO/ImageToVTKImageFilter | Display an ITK image]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileWriter | Write a transform to a file]] || {{ITKDoxygenURL|TransformFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileReader | Read a transform from a file]] || {{ITKDoxygenURL|TransformFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/VolumeFromSlices | Create a 3D volume from a series of 2D images]] || {{ITKDoxygenURL|ImageSeriesReader}} || Uses NumericSeriesFileNames to generate a list of file names<br />
|-<br />
| [[ITK/Examples/IO/itkVtkImageConvertDICOM | Uses a custom user matrix to align the image with DICOM physical space]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} || <br />
|}<br />
<br />
==DICOM==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/DICOM/ResampleDICOM | Resample a DICOM series]] || {{ITKDoxygenURL|GDCMImageIO}} || Resample a DICOM series with user-specified spacing.<br />
|}<br />
<br />
==Blob Detection, Labeling, and Properties==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ManuallyRemovingLabels | Remove labels from a LabelMap]] || {{ITKDoxygenURL|LabelMap}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ObjectByObjectLabelMapFilter | Apply an operation to every label object in a label map]] || {{ITKDoxygenURL|ObjectByObjectLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ShapeOpeningLabelMapFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|ShapeOpeningLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelShapeKeepNObjectsImageFilter | Keep only regions that rank above a certain level of a particular property]] || {{ITKDoxygenURL|LabelShapeKeepNObjectsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|BinaryStatisticsOpeningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapOverlayImageFilter | Color labeled regions in an image]] || {{ITKDoxygenURL|LabelMapOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelGeometryImageFilter | Get geometric properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelGeometryImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelStatisticsImageFilter | Get statistical properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelStatisticsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/LabelMapContourOverlayImageFilter | Color the boundaries of labeled regions in an image]] || {{ITKDoxygenURL|LabelMapContourOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToLabelMapFilter | Label binary regions in an image]] || {{ITKDoxygenURL|BinaryImageToLabelMapFilter}} || Also demonstrates how to obtain which pixels belong to each label.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToShapeLabelMapFilter | Label binary regions in an image and get their properties]] || {{ITKDoxygenURL|BinaryImageToShapeLabelMapFilter}} || Region bounding box, centroid, etc.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapToLabelImageFilter | Convert a LabelMap to a normal image with different values representing each region]] || {{ITKDoxygenURL|LabelMapToLabelImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MergeLabelMapFilter | Merges several labelmaps]] || {{ITKDoxygenURL|MergeLabelMapFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelOverlayImageFilter | Overlay a LabelMap on an image]] || {{ITKDoxygenURL|LabelOverlayImageFilter}} || <br />
|}<br />
<br />
==Correlation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Images/NormalizedCorrelationImageFilter | Normalized correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/NormalizedCorrelationImageFilterMasked | Normalized correlation of a masked image]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/FFTNormalizedCorrelationImageFilter | Normalized correlation using the FFT]] || {{ITKDoxygenURL|FFTNormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskedFFTNormalizedCorrelationImageFilter | Normalized correlation using the FFT with optional mask images for both input images]] || {{ITKDoxygenURL|MaskedFFTNormalizedCorrelationImageFilter}} ||<br />
|}<br />
<br />
==Image Processing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RGBToLuminanceImageFilter | Convert an RGB image to a luminance image]] || {{ITKDoxygenURL|RGBToLuminanceImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThinningImageFilter | Skeletonize/thin an image]] || {{ITKDoxygenURL|BinaryThinningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScaleTransform | Scale an image]] || {{ITKDoxygenURL|ScaleTransform}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ResampleImageFilter | Resample (stretch or compress) an image]] || {{ITKDoxygenURL|ResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RGBResampleImageFilter | Resample (stretch or compress) an RGB image]] || {{ITKDoxygenURL|VectorResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/MutualInformationImageToImageFilter | Compute the mutual information between two image]] || {{ITKDoxygenURL|MutualInformationImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianSharpeningImageFilter | Sharpen an image]] || {{ITKDoxygenURL|LaplacianSharpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/DivideImageFilter | Pixel-wise division of two images]] || {{ITKDoxygenURL|DivideImageFilter}} || Divide images<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ApproximateSignedDistanceMapImageFilter | Compute a distance map from objects in a binary image]] || {{ITKDoxygenURL|ApproximateSignedDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeToConstantImageFilter | Scale all pixels so that their sum is a specified constant]] || {{ITKDoxygenURL|NormalizeToConstantImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMinimaImageFilter | RegionalMinimaImageFilter]] || {{ITKDoxygenURL|RegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMaximaImageFilter | RegionalMaximaImageFilter]] || {{ITKDoxygenURL|RegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ZeroCrossingImageFilter| Find zero crossings in a signed image]] || {{ITKDoxygenURL|ZeroCrossingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RecursiveMultiResolutionPyramidImageFilter| Construct a multiresolution pyramid from an image]] || {{ITKDoxygenURL|RecursiveMultiResolutionPyramidImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddConstantToImageFilter| Add a constant to every pixel in an image]] || {{ITKDoxygenURL|AddImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractConstantFromImageFilter| Subtract a constant from every pixel in an image]] || {{ITKDoxygenURL|SubtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquareImageFilter| Square every pixel in an image]] || {{ITKDoxygenURL|SquareImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Upsampling| Upsampling an image]] || {{ITKDoxygenURL|BSplineInterpolateImageFunction}} {{ITKDoxygenURL|ResampleImageFilter}} || Interpolate missing pixels in order to upsample an image. Note this only works on scalar images.<br />
|-<br />
| [[ITK/Examples/Images/FlipImageFilter | Flip an image over specified axes]] || {{ITKDoxygenURL|FlipImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/VectorRescaleIntensityImageFilter | Apply a transformation to the magnitude of vector valued image pixels]] || {{ITKDoxygenURL|VectorRescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/NeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskNeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image that is non-zero in a mask]] || {{ITKDoxygenURL|MaskNeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianImageFilter | Compute the Laplacian of an image]] || {{ITKDoxygenURL|LaplacianImageFilter}} || Input image type must be double or float<br />
|-<br />
| [[ITK/Examples/Images/ConstantPadImageFilter | Pad an image with a constant value]] || {{ITKDoxygenURL|ConstantPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/MirrorPadImageFilter | Pad an image using mirroring over the boundaries]] || {{ITKDoxygenURL|MirrorPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/WrapPadImageFilter | Pad an image by wrapping]] || {{ITKDoxygenURL|WrapPadImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/IntensityWindowingImageFilter| IntensityWindowingImageFilter]] || {{ITKDoxygenURL|IntensityWindowingImageFilter}} || Apply a linear intensity transform from a specified input range to a specified output range.<br />
|-<br />
| [[ITK/Examples/Images/ShrinkImageFilter | Shrink an image]] || {{ITKDoxygenURL|ShrinkImageFilter}} || Downsample an image<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyByConstantImageFilter | Multiply every pixel in an image by a constant]] || {{ITKDoxygenURL|MultiplyImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquaredDifferenceImageFilter | Compute the squared difference of corresponding pixels in two images]] || {{ITKDoxygenURL|SquaredDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsoluteValueDifferenceImageFilter | Compute the absolute value of the difference of corresponding pixels in two images]] || {{ITKDoxygenURL|AbsoluteValueDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddPixelAccessor | Add a constant to every pixel without duplicating the image in memory (an accessor)]] || {{ITKDoxygenURL|AddPixelAccessor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMaximaImageFilter | ValuedRegionalMaximaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMinimaImageFilter | ValuedRegionalMinimaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaximumImageFilter | Pixel wise compare two input images and set the output pixel to their max]] || {{ITKDoxygenURL|MaximumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumImageFilter | Pixel wise compare two input images and set the output pixel to their min]] || {{ITKDoxygenURL|MinimumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AndImageFilter | Binary AND two images]] || {{ITKDoxygenURL|AndImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/OrImageFilter | Binary OR two images]] || {{ITKDoxygenURL|OrImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/XorImageFilter | Binary XOR (exclusive OR) two images]] || {{ITKDoxygenURL|XorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryNotImageFilter | Invert an image using the Binary Not operation]] || {{ITKDoxygenURL|BinaryNotImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Compose3DCovariantVectorImageFilter | Compose a vector image (with 3 components) from three scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/NthElementImageAdaptor | Extract a component/channel of an itkImage with pixels with multiple components]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || Use built in functionality to extract a component of an itkImage with CovariantVector components. Note this does not work for itkVectorImages - see VectorIndexSelectionCastImageFilter instead.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageAdaptorExtractVectorComponent | Present an image by first performing an operation]] || {{ITKDoxygenURL|ImageAdaptor}} || A demonstration of how to present an image pixel as a function of the pixel. In this example the functionality of NthElementImageAdaptor is demonstrated.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ProcessingNthImageElement | Process the nth component/element/channel of a vector image]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConvolutionImageFilter | Convolve an image with a kernel]] || {{ITKDoxygenURL|ConvolutionImageFilter}} || Convolution.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ExtractImageFilter | Crop an image by specifying the region to keep]] || {{ITKDoxygenURL|ExtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/CropImageFilter | Crop an image by specifying the region to throw away]] || {{ITKDoxygenURL|CropImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsImageFilter | Compute the absolute value of an image]] || {{ITKDoxygenURL|AbsImageFilter}} || magnitude<br />
|-<br />
| [[ITK/Examples/ImageProcessing/InvertIntensityImageFilter | Invert an image]] || {{ITKDoxygenURL|InvertIntensityImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskImageFilter | Apply a mask to an image]] || {{ITKDoxygenURL|MaskImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskNegatedImageFilter | Apply the inverse of a mask to an image]] || {{ITKDoxygenURL|MaskNegatedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SigmoidImageFilter | Pass image pixels through a sigmoid function]] || {{ITKDoxygenURL|SigmoidImageFilter}} || The qualitative description of how Alpha and Beta affect the function from the ITK Software Guide and the associated images would be nice to add to the doxygen.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|ThresholdImageFilter}} || The result is the original image but with the values below (or above) the threshold "clamped" to an output value.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|BinaryThresholdImageFilter}} || The result is a binary image (inside the threshold region or outside the threshold region).<br />
|-<br />
| [[ITK/Examples/ImageProcessing/UnaryFunctorImageFilter | Apply a custom operation to each pixel in an image]] || {{ITKDoxygenURL|UnaryFunctorImageFilter}} || Perform a custom operation on every pixel in an image. This example rotates the vector-valued pixels by 90 degrees.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilter | Apply a predefined operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilterCustom | Apply a custom operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || This example computes the squared difference between corresponding pixels.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumMaximumImageCalculator | Find the minimum and maximum value (and the position of the value) in an image]] || {{ITKDoxygenURL|MinimumMaximumImageCalculator}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddImageFilter | Add two images together]] || {{ITKDoxygenURL|AddImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractImageFilter | Subtract two images]] || {{ITKDoxygenURL|SubtractImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PasteImageFilter | Paste a part of one image into another image]] || {{ITKDoxygenURL|PasteImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_CreateVolume | Stack multiple 2D images into a 3D image]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_SideBySide | Tile multiple images side by side]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyImageFilter | Multiply two images together]] || {{ITKDoxygenURL|MultiplyImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionOfInterestImageFilter | Extract a portion of an image (region of interest)]] || {{ITKDoxygenURL|RegionOfInterestImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RescaleIntensityImageFilter | Rescale the intensity values of an image to a specified range]] || {{ITKDoxygenURL|RescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeImageFilter | Normalize an image]] || {{ITKDoxygenURL|NormalizeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/CastImageFilter | Cast an image from one type to another]] || {{ITKDoxygenURL|CastImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ClampImageFilter | Cast an image from one type to another but clamp to the output value range]] || {{ITKDoxygenURL|ClampImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PermuteAxesImageFilter | Switch the axes of an image]] || {{ITKDoxygenURL|PermuteAxesImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LinearInterpolateImageFunction | Linearly interpolate a position in an image]] || {{ITKDoxygenURL|LinearInterpolateImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/HammingWindowFunction | HammingWindowFunction]] || {{ITKDoxygenURL|HammingWindowFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageFilterOnARegion | Run an image filter on a region of an image]] || {{ITKDoxygenURL|PasteImageFIlter}} || This example uses the RequestedRegion of a filter to process a subset of an image.<br />
|}<br />
<br />
==Vector Images==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorMagnitudeImageFilter | Compute the magnitude of each pixel in a vector image to produce a magnitude image]] || {{ITKDoxygenURL|VectorMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImage | Create a vector image]] || {{ITKDoxygenURL|VectorImage}} || An image with an ND vector at each pixel<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Create a vector image from a collection of scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || Combine, layer<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImageToImageAdaptor | View a component of a vector image as if it were a scalar image]] || {{ITKDoxygenURL|VectorImageToImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/VectorImages/VectorIndexSelectionCastImageFilter | Extract a component/channel of a vector image]] || {{ITKDoxygenURL|VectorIndexSelectionCastImageFilter}} || This works with VectorImage as well as Image<Vector><br />
|-<br />
| [[ITK/Examples/VectorImages/VectorResampleImageFilter | Translate a vector image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|VectorResampleImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/JoinImageFilter | Join images, stacking their components]] || {{ITKDoxygenURL|JoinImageFilter}} || concatenate, channels<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Stack scalar images into a VectorImage]] || {{ITKDoxygenURL|ImageToVectorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/NeighborhoodIterator | NeighborhoodIterator on a VectorImage]] || {{ITKDoxygenURL|VectorImage}} {{ITKDoxygenURL|NeighborhoodIterator}}||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorCastImageFilter | Cast a VectorImage to another type of VectorImage]] || {{ITKDoxygenURL|VectorImage}} ||<br />
|}<br />
<br />
==Iterating Over (Traversing) An Image==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator_Manual | Iterate over a region of an image with a shaped neighborhood]] || Create the shape manually {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator | Iterate over a region of an image with a shaped neighborhood]] || Create the shape from a StructuringElement {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionExclusionConstIteratorWithIndex | Iterator over an image skipping a specified region]] || {{ITKDoxygenURL|ImageRegionExclusionConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomConstIteratorWithIndex | Randomly select pixels from a region of an image]] || {{ITKDoxygenURL|ImageRandomConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomNonRepeatingConstIteratorWithIndex | Randomly select pixels from a region of an image without replacement]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/LineIterator | Iterate over a line through an image]] || {{ITKDoxygenURL|LineIterator}} || Walks a Bresenham line through an image (with write access)<br />
|-<br />
| [[ITK/Examples/Iterators/LineConstIterator | Iterate over a line through an image without write access]] || {{ITKDoxygenURL|LineConstIterator}} || Walks a Bresenham line through an image (without write access)<br />
|-<br />
| [[ITK/Examples/Iterators/ImageBoundaryFacesCalculator | Iterate over the central region (non-boundary) separately from the face-regions (boundary)]] || {{ITKDoxygenURL|ImageBoundaryFacesCalculator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/NeighborhoodIterator | Iterate over a region of an image with a neighborhood (with write access)]] || {{ITKDoxygenURL|NeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstNeighborhoodIterator | Iterate over a region of an image with a neighborhood (without write access)]] || {{ITKDoxygenURL|ConstNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIterator | Iterate over a region of an image (with write access)]] || {{ITKDoxygenURL|ImageRegionIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIterator | Iterate over a region of an image (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstantBoundaryCondition | Make out of bounds pixels return a constant value]] || {{ITKDoxygenURL|ConstantBoundaryCondition}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (with write access)]] || {{ITKDoxygenURL|ImageRegionIteratorWithIndex}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIteratorWithIndex}} ||<br />
|}<br />
<br />
==Kernels==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Operators/GaussianOperator | Create a Gaussian kernel]] || {{ITKDoxygenURL|GaussianOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/GaussianDerivativeOperator | Create a Gaussian derivative kernel]] || {{ITKDoxygenURL|GaussianDerivativeOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/LaplacianOperator | Create a Laplacian kernel]] || {{ITKDoxygenURL|LaplacianOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/DerivativeOperator | Create a derivative kernel]] || {{ITKDoxygenURL|DerivativeOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/SobelOperator | Create the Sobel kernel]] || {{ITKDoxygenURL|SobelOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/ForwardDifferenceOperator | Create a forward difference kernel]] || {{ITKDoxygenURL|ForwardDifferenceOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/BackwardDifferenceOperator | Create a backward difference kernel]] || {{ITKDoxygenURL|BackwardDifferenceOperator}} || <br />
<br />
|}<br />
<br />
==Image Edges, Gradients, and Derivatives==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/SobelEdgeDetectionImageFilter | SobelEdgeDetectionImageFilter]] || {{ITKDoxygenURL|SobelEdgeDetectionImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/DerivativeImageFilter | Compute the derivative of an image in a particular direction]] || {{ITKDoxygenURL|DerivativeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientRecursiveGaussianImageFilter| Compute the gradient of an image by convolution with the first derivative of a Gaussian]] || {{ITKDoxygenURL|GradientRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeRecursiveGaussianImageFilter | Find the gradient magnitude of the image first smoothed with a Gaussian kernel]] || {{ITKDoxygenURL|GradientMagnitudeRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/RecursiveGaussianImageFilter | Find higher derivatives of an image]] || {{ITKDoxygenURL|RecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryContourImageFilter | Extract the boundaries of connected regions in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} || Blob boundary, border<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryBoundaries | Extract the inner and outer boundaries of blobs in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeImageFilter | Compute the gradient magnitude image]] || {{ITKDoxygenURL|GradientMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/LaplacianRecursiveGaussianImageFilter | Compute the Laplacian of Gaussian (LoG) of an image]] || {{ITKDoxygenURL|LaplacianRecursiveGaussianImageFilter}} ||<br />
|}<br />
<br />
==Smoothing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Smoothing/AntiAliasBinaryImageFilter | Anti alias a binary image]] || {{ITKDoxygenURL|AntiAliasBinaryImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinaryMinMaxCurvatureFlowImageFilter | BinaryMinMaxCurvatureFlow a binary image]] || {{ITKDoxygenURL|BinaryMinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MeanImageFilter | Mean filter an image]] || {{ITKDoxygenURL|MeanImageFilter}} || Replace each pixel by the mean of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/MedianImageFilter | Median filter an image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/RGBMedianImageFilter | Median filter an RGB image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/DiscreteGaussianImageFilter | Smooth an image with a discrete Gaussian filter]] || {{ITKDoxygenURL|DiscreteGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinomialBlurImageFilter | Blur an image]] || {{ITKDoxygenURL|BinomialBlurImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BilateralImageFilter | Bilateral filter an image]] || {{ITKDoxygenURL|BilateralImageFilter}} || Edge preserving smoothing.<br />
|-<br />
| [[ITK/Examples/Smoothing/CurvatureFlowImageFilter | Smooth an image using curvature flow]] || {{ITKDoxygenURL|CurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MinMaxCurvatureFlowImageFilter | Smooth an image using min/max curvature flow]] || {{ITKDoxygenURL|MinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/SmoothingRecursiveGaussianImageFilter | Gaussian smoothing that works with image adaptors]] || {{ITKDoxygenURL|SmoothingRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/VectorGradientAnisotropicDiffusionImageFilter | Smooth an image while preserving edges]] || {{ITKDoxygenURL|VectorGradientAnisotropicDiffusionImageFilter}} || Anisotropic diffusion.<br />
|}<br />
<br />
==Morphology==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Morphology/BinaryErodeImageFilter | Erode a binary image]] || {{ITKDoxygenURL|BinaryErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryDilateImageFilter | Dilate a binary image]] || {{ITKDoxygenURL|BinaryDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryPruningImageFilter | Prune a binary image]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalOpeningImageFilter | Opening a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalOpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalClosingImageFilter | Closing a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalClosingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleDilateImageFilter | Dilate a grayscale image]] || {{ITKDoxygenURL|GrayscaleDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleErodeImageFilter | Erode a grayscale image]] || {{ITKDoxygenURL|GrayscaleErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/FlatStructuringElement | Erode a binary image using a flat (box) structuring element]] || {{ITKDoxygenURL|FlatStructuringElement}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryBallStructuringElement | An elliptical structuring element]] || {{ITKDoxygenURL|BinaryBallStructuringElement}} || <br />
|}<br />
<br />
==Curves==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Curves/ContourMeanDistanceImageFilter | Compute the mean distance between all points of two curves]] || {{ITKDoxygenURL|ContourMeanDistanceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Curves/PolyLineParametricPath | A data structure for a piece-wise linear curve]] || {{ITKDoxygenURL|PolyLineParametricPath}} || <br />
|}<br />
<br />
==Spectral Analysis==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/ForwardFFTImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|ForwardFFTImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/InverseFFTImageFilter | Compute the inverse FFT of an image]] || {{ITKDoxygenURL|InverseFFTImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/VnlFFTRealToComplexConjugateImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/CrossCorrelationInFourierDomain | Compute the cross-correlation of two images in the Fourier domain]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}}{{ITKDoxygenURL|VnlFFTComplexConjugateToRealImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/RealAndImaginaryToComplexImageFilter | Convert a real image and an imaginary image to a complex image]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|}<br />
<br />
==Utilities==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Utilities/SortIndex | Sort itk::Index]] || {{ITKDoxygenURL|Image}} || Lexicographic, ordering<br />
|-<br />
| [[ITK/Examples/Utilities/ReturnObjectFromFunction | Return an object from a function]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateImageWithSameType | Create another instance of an image]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Create another instance of the same type of object]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/PassImageToFunction | Pass an image to a function]] || {{ITKDoxygenURL|Image}}<br />
|-<br />
| [[ITK/Examples/Utilities/NumericSeriesFileNames | Create a list of file names]] || {{ITKDoxygenURL|NumericSeriesFileNames}} || <br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Copy a filter]] || {{ITKDoxygenURL|Object}} || Copy/duplicate a filter<br />
|-<br />
| [[ITK/Examples/Utilities/AzimuthElevationToCartesianTransform | Cartesian to AzimuthElevation and vice-versa]] || {{ITKDoxygenURL|AzimuthElevationToCartesianTransform}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/FixedArray | C-style array]] || {{ITKDoxygenURL|FixedArray}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/DeepCopy | Deep copy an image]] || || <br />
|-<br />
| [[ITK/Examples/Utilities/RandomPermutation | Permute a sequence of indices]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Utilities/MersenneTwisterRandomVariateGenerator | Random number generator]] || {{ITKDoxygenURL|MersenneTwisterRandomVariateGenerator}} || <br />
|-<br />
| [[ITK/Examples/Utilities/JetColormapFunctor | Map scalars into a jet colormap]] || {{ITKDoxygenURL|JetColormapFunctor}} || <br />
|-<br />
| [[ITK/Examples/Utilities/SimpleFilterWatcher | Monitor a filter]] || {{ITKDoxygenURL|SimpleFilterWatcher}} || See debug style information.<br />
|-<br />
| [[ITK/Examples/Utilities/TimeProbe | Time probe]] || {{ITKDoxygenURL|TimeProbe}} || Compute the time between points in code. Timer. Timing.<br />
|-<br />
| [[ITK/Examples/Utilities/ObserveEvent | Observe an event]] || {{ITKDoxygenURL|Command}} || <br />
|-<br />
| [[ITK/Examples/Utilities/VectorContainer | Vector container]] || {{ITKDoxygenURL|VectorContainer}} || <br />
|}<br />
<br />
==Statistics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/MovingHistogramImageFilter | Compute histograms in a sliding window.]] || {{ITKDoxygenURL|MovingHistogramImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterRGB | Compute a histogram from an RGB image.]] || {{ITKDoxygenURL|HistogramToImageFilterRGB}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterVectorImage | Compute a histogram from a itk::VectorImage.]] || {{ITKDoxygenURL|HistogramToImageFilterVectorImage}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterGrayscale | Compute a histogram from a grayscale image.]] || {{ITKDoxygenURL|HistogramToImageFilterGrayscale}} || <br />
|-<br />
| [[ITK/Examples/Statistics/Histogram | Compute a histogram from measurements.]] || {{ITKDoxygenURL|Histogram}} || <br />
|-<br />
| [[ITK/Examples/Statistics/StatisticsImageFilter | Compute min, max, variance and mean of an Image.]] || {{ITKDoxygenURL|StatisticsImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/GaussianDistribution | Create a Gaussian distribution]] || {{ITKDoxygenURL|GaussianDistribution}} || <br />
|-<br />
| [[ITK/Examples/Statistics/SampleToHistogramFilter | Create a histogram from a list of sample measurements]] || {{ITKDoxygenURL|SampleToHistogramFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ListSample | Create a list of sample measurements]] || {{ITKDoxygenURL|ListSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageToListSampleAdaptor | Create a list of samples from an image without duplicating the data]] || {{ITKDoxygenURL|ImageToListSampleAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Statistics/MembershipSample | Create a list of samples with associated class IDs]] || {{ITKDoxygenURL|MembershipSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ExpectationMaximizationMixtureModelEstimator_2D | 2D Gaussian Mixture Model Expectation Maximization]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || EM<br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_1D | 1D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_3D | 3D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTree | Spatial search]] || {{ITKDoxygenURL|KdTreeGenerator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ScalarImageKmeansImageFilter | Cluster the pixels in a greyscale image]] || {{ITKDoxygenURL|ScalarImageKmeansImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/NoiseImageFilter | Compute the local noise in an image]] || {{ITKDoxygenURL|NoiseImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageKmeansModelEstimator | Compute kmeans clusters of pixels in an image]] || {{ITKDoxygenURL|ImageKmeansModelEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKmeansEstimator | Compute kmeans clusters]] || {{ITKDoxygenURL|KdTreeBasedKmeansEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/TextureFeatures | Extract texture features using GLCM]] || {{ITKDoxygenURL|ScalarImageToCooccurrenceMatrixFilter}} || <br />
|}<br />
<br />
==Spatial Objects==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpatialObjects/SpatialObjectToImageFilter | Convert a spatial object to an image ]] || {{ITKDoxygenURL|SpatialObjectToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/EllipseSpatialObject | Ellipse ]] || {{ITKDoxygenURL|EllipseSpatialObject}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/LineSpatialObject| Line spatial object]] || {{ITKDoxygenURL|LineSpatialObject}}, {{ITKDoxygenURL|LineSpatialObjectPoint}} || Specify a piecewise-linear object by specifying points along the line.<br />
|-<br />
| [[ITK/Examples/SpatialObjects/PlaneSpatialObject| Plane spatial object]] || {{ITKDoxygenURL|PlaneSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/SpatialObjects/BlobSpatialObject | Blob ]] || {{ITKDoxygenURL|BlobSpatialObject}} ||<br />
|}<br />
<br />
==Inspection==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Inspection/CheckerBoardImageFilter | Combine two images by alternating blocks of a checkerboard pattern]] || {{ITKDoxygenURL|CheckerBoardImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Inspection/PixelInspection | Printing a pixel value to the console]] || [http://www.itk.org/Doxygen/html/classitk_1_1Image.html#ad424c945604f339130b4ffe81b99738eGetPixel GetPixel] ||<br />
|}<br />
<br />
==Metrics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Metrics/MeanSquaresImageToImageMetric | Compute the mean squares metric between two images ]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} ||<br />
|}<br />
==Image Registration==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Registration/WarpImageFilter | Warp one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|WarpImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Registration/LandmarkBasedTransformInitializer | Rigidly register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|LandmarkBasedTransformInitializer}} ||<br />
|-<br />
| [[ITK/Examples/Registration/DeformationFieldTransform | Register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|DeformationFieldTransform}} ||<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethod | A basic global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|TranslationTransform}} || Translation only transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodAffine | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|AffineTransform}} || Full affine transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodBSpline | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|BSplineDeformableTransform}} || BSpline transform.<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformation | Mutual Information ]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|TranslationTransform}} || Global registration by maximizing the mutual information and using a translation only transform<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformationAffine | Mutual Information Affine]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|AffineTransform}} || Global registration by maximizing the mutual information and using an affine transform<br />
|}<br />
<br />
==Image Segmentation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Segmentation/ContourExtractor2DImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|ContourExtractor2DImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/WatershedImageFilter| Watershed segmentation]] ||{{ITKDoxygenURL|WatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/MorphologicalWatershedImageFilter| Morphological Watershed segmentation]] ||{{ITKDoxygenURL|MorphologicalWatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/EstimatePCAModel | Compute a PCA shape model from a training sample]] || {{ITKDoxygenURL|ImagePCAShapeModelEstimator}} ||<br />
Estimate the principal modes of variation of a shape from a training sample. Useful for shape guide segmentation.<br />
|-<br />
| [[ITK/Examples/Segmentation/MeanShiftClustering | Mean shift clustering]] || {{ITKDoxygenURL|SampleMeanShiftClusteringFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/kMeansClustering | KMeans Clustering]] || ||<br />
|-<br />
| [[ITK/Examples/Segmentation/MultiphaseChanAndVeseSparseFieldLevelSetSegmentation | Multiphase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseSparseFieldLevelSetSegmentation | Single-phase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseDenseFieldLevelSetSegmentation | Single-phase Chan And Vese Dense Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseDenseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/WishList/VoronoiDiagram2DGenerator | Voronoi diagram]] || {{ITKDoxygenURL|VoronoiDiagram2DGenerator}}, {{ITKDoxygenURL|VoronoiDiagram2D}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConnectedComponentImageFilter | Label connected components in a binary image]] || {{ITKDoxygenURL|ConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScalarConnectedComponentImageFilter | Label connected components in a grayscale image]] || {{ITKDoxygenURL|ScalarConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RelabelComponentImageFilter | Assign contiguous labels to connected regions of an image]] || {{ITKDoxygenURL|RelabelComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelContourImageFilter | Label the contours of connected components]] || {{ITKDoxygenURL|LabelContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ConfidenceConnectedImageFilter | Segment pixels with similar statistics using connectivity ]] || {{ITKDoxygenURL|ConfidenceConnectedImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToLabelMapFilter | Convert an itk::Image consisting of labeled regions to a LabelMap ]] || <br />
{{ITKDoxygenURL|LabelImageToLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToShapeLabelMapFilter | Convert an itk::Image consisting of labeled regions to a ShapeLabelMap ]] || {{ITKDoxygenURL|LabelImageToShapeLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ExtractLargestConnectedComponentFromBinaryImage | Extract the largest connected component from a Binary Image ]] || <br />
||<br />
|}<br />
<br />
==Meshes==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Meshes/Decimation | Decimation]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/AddPointsAndEdges | Add points and edges]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshNormalFilter | Compute normals of a mesh]] || {{ITKDoxygenURL|QuadEdgeMeshNormalFilter}} ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshParameterizationFilter | Planar parameterization of a mesh]] || {{ITKDoxygenURL|ParameterizationQuadEdgeMeshFilter}} || Compute linear parameterization of a mesh homeomorphic to a disk on the plane<br />
|-<br />
| [[ITK/Examples/Meshes/ConvertToVTK | Convert an itk::Mesh to a vtkUnstructuredGrid]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/WishList/WriteMeshToVTP | Write an itk::Mesh to a vtp (vtkPolyData) file]] || {{ITKDoxygenURL|VTKPolyDataWriter}} ||<br />
|}<br />
<br />
==Need Demo==<br />
This section consists of examples which compile and work, but a good demonstration image must be selected and added.<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/NeedDemo/ImageProcessing/AdaptiveHistogramEqualizationImageFilter | Adaptive histogram equalization]] || {{ITKDoxygenURL|AdaptiveHistogramEqualizationImageFilter}} ||<br />
|}<br />
<br />
<br />
==Wish List==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Pipeline/DisconnectPipeline | DisconnectPipeline]] || <br />
|-<br />
| [[ITK/Examples/WishList/Iterators/ConditionalConstIterator | ConditionalConstIterator]] || {{ITKDoxygenURL|ConditionalConstIterator}} || <br />
|-<br />
| [[ITK/Examples/WishList/Statistics/ScalarImageToTextureFeaturesFilter | Compute texture features]] || [http://www.itk.org/Doxygen/html/classitk_1_1Statistics_1_1ScalarImageToTextureFeaturesFilter.html ScalarImageToTextureFeaturesFilter] || How to interpret the output?<br />
|-<br />
| [[ITK/Examples/WishList/LevelSets/SignedDanielssonDistanceMapImageFilter | Compute the signed distance function over an image]] || {{ITKDoxygenURL|SignedDanielssonDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorImageResampleImageFilter | Resample an itk::VectorImage]] || ||<br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/OtsuMultipleThresholdsCalculator | Compute Otsu thresholds]] || {{ITKDoxygenURL|OtsuMultipleThresholdsCalculator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/MaskedImageToHistogramFilter | Compute the histogram of a masked region of an image]] || {{ITKDoxygenURL|MaskedImageToHistogramFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/PointSet/BSplineScatteredDataPointSetToImageFilter | Fit a spline to a point set]] || {{ITKDoxygenURL|BSplineScatteredDataPointSetToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Morphology/BinaryPruningImageFilter | BinaryPruningImageFilter]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/GaussianMixtureModelComponent | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|GaussianMixtureModelComponent}} ||<br />
|-<br />
| [[ITK/Examples/WishList/LevenbergMarquart| LevenbergMarquart]] || || <br />
|-<br />
| [[ITK/Examples/WishList/IterativeClosestPoints| IterativeClosestPoints]] || || <br />
|-<br />
| [[ITK/Examples/WishList/Operators/AllOperators| Demonstrate all operators]] || {{ITKDoxygenURL|NeighborhoodOperator}} || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/ColorNormalizedCorrelation| Color Normalized Correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/SpatialObjects/ContourSpatialObject| ContourSpatialObject]] || {{ITKDoxygenURL|ContourSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/Broken/SimpleOperations/MetaDataDictionary| Store non-pixel associated data in an image]] || {{ITKDoxygenURL|MetaDataDictionary}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/LevelSets| Level Sets]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation//RegionGrowing| Region Growing]] || || <br />
|-<br />
| [[ITK/Examples/Meshes/Subdivision| Mesh subdivision]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation/OtsuThresholdImageFilter| Separate foreground and background using Otsu's method]] || {{ITKDoxygenURL|OtsuThresholdImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/SimpleContourExtractorImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|SimpleContourExtractorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/RGBToVectorImageAdaptor| Present an image of RGBPixel pixels as an image of vectors]] || {{ITKDoxygenURL|RGBToVectorImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DCirclesImageFilter| HoughTransform2DCirclesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DCirclesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DLinesImageFilter| HoughTransform2DLinesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DLinesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Matlab/MatlabToITK| Write data from Matlab in a format readable by ITK]] || || <br />
|-<br />
| [[ITK/Examples/Matlab/ITKToMatlab| Write data from ITK in a format readable by Matlab]] || || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/EdgePotentialImageFilter| Compute edge potential]] ||{{ITKDoxygenURL|EdgePotentialImageFilter}} || <br />
|}<br />
<br />
==Included in the ITK Repository==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Included/Registration| Image registration]] || || <br />
|}<br />
<br />
==Matlab==<br />
{{ITKExamplesTable}}<br />
<br />
|}<br />
<br />
==Developer Examples==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Developer/Exceptions | Throw an exception]] || || <br />
|-<br />
| [[ITK/Examples/Developer/ImageSource | Produce an image programmatically.]] || {{ITKDoxygenURL|ImageSource}} || Nothing in, image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilter | Filter an image]] || {{ITKDoxygenURL|ImageToImageFilter}} || Image in, same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/InplaceImageFilter | Filter an image without copying its data]] || {{ITKDoxygenURL|InPlaceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Developer/MultiThreadedImageFilter | Filter an image using multiple threads]] || {{ITKDoxygenURL|ImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Developer/OilPaintingImageFilter | Multi-threaded oil painting image filter]] || {{ITKDoxygenURL|ImageToImageFilter}} and {{ITKDoxygenURL|MinimumMaximumImageCalculator}} || A simple multi-threaded scenario (oil painting artistic filter). You can also use this class as-is (copy .h and .txx files into your project and use them).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputs | Write a filter with multiple inputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (same type), same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputsDifferentType | Write a filter with multiple inputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (different type), image (same type as first input) out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputs | Write a filter with multiple outputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (same type as first input).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputsDifferentType | Write a filter with multiple outputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (different types).<br />
|-<br />
| [[ITK/Examples/Developer/SetGetMacro | Get or set a member variable of an ITK class.]] || || SetMacro, GetMacro<br />
|-<br />
| [[ITK/Examples/Developer/OutputMacros | Output an error, a warning, or debug information.]] || || DebugMacro, ErrorMacro, WarningMacro<br />
|-<br />
| [[ITK/Examples/Developer/Minipipeline | MiniPipeline]] || || <br />
|}<br />
<br />
==Problems==<br />
===Small Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFilledImageFunctionConditionalIterator | Iterate over an image starting at a seed and following a rule for connectivity decisions]] || {{ITKDoxygenURL|FloodFilledImageFunctionConditionalIterator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFillIterator | Traverse a region using a flood fill iterator]] || {{ITKDoxygenURL|FloodFilledSpatialFunctionConditionalIterator}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/GradientOfVectorImage | Compute the gradient of a vector image]] || {{ITKDoxygenURL|GradientImageFilter}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_Image | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_1D | Compute distributions of samples using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || Someone please confirm that this outputs the mean and the variance (i.e. I used a standard deviation of 30 to create the samples and the second estimated parameter is near 1000 (~30^2) . Is this correct?)<br />
|-<br />
| [[ITK/Examples/Broken/EdgesAndGradients/CannyEdgeDetectionImageFilter | Find edges in an image]] || {{ITKDoxygenURL|CannyEdgeDetectionImageFilter}} || How to set a reasonable Threshold for the output edges?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ImageToHistogramFilter | Compute the histogram of an image]] || {{ITKDoxygenURL|Statistics_1_1ImageToHistogramFilter}} || The last entry of the red histogram should contain several values, but it is 0?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/KmeansModelEstimator | Classifying pixels using KMeans]] || {{ITKDoxygenURL|KmeansModelEstimator}} || How to apply the labels of the filter to the input image?<br />
|-<br />
| [[ITK/Examples/Broken/Images/RegionGrowImageFilter | Basic region growing]] || {{ITKDoxygenURL|RegionGrowImageFilter}} || Just getting started with demo...<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConnectedThresholdImageFilter | Find connected components in an image]] || {{ITKDoxygenURL|ConnectedThresholdImageFilter}} || Just need to finish it.<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConvertPixelBuffer | Convert an image from one type to another]] || {{ITKDoxygenURL|ConvertPixelBuffer}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/InPlace | In-place filtering of an image]] || {{ITKDoxygenURL|InPlaceImageFilter}} || This only works for filters which derive from itkInPlaceImageFilter<br />
|-<br />
| [[ITK/Examples/Broken/Images/VTKImageToImageFilter | Convert a VTK image to an ITK image]] || {{ITKDoxygenURL|VTKImageToImageFilter}} || Seems to expect an input image with only 1 component? (i.e. greyscale)<br />
|}<br />
<br />
===Big Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Images/MeanSquaresImageToImageMetric | Find the best position of the moving image in the fixed image.]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} || Output (0,0) is incorrect.<br />
|-<br />
| [[ITK/Examples/Broken/Images/GradientImageFilter | Compute and display the gradient of an image]] || {{ITKDoxygenURL|GradientImageFilter}} || Blank output on the screen (the filter works fine). There should be a "DisplayVectorImage" added to itkQuickView that draws vector glyphs at specified pixels of an image.<br />
|}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/StatisticsOpeningLabelMapFilter&diff=48629ITK/Examples/ImageProcessing/StatisticsOpeningLabelMapFilter2012-08-24T18:14:27Z<p>Ccagataybilgin: moved ITK/Examples/ImageProcessing/StatisticsOpeningLabelMapFilter to ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter: The initial name was wrong. The example illustrates the use of BinaryStatisticsOpeningImageFilter.</p>
<hr />
<div>#REDIRECT [[ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter]]</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter&diff=48628ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter2012-08-24T18:14:27Z<p>Ccagataybilgin: moved ITK/Examples/ImageProcessing/StatisticsOpeningLabelMapFilter to ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter: The initial name was wrong. The example illustrates the use of BinaryStatisticsOpeningImageFilter.</p>
<hr />
<div>==BinaryStatisticsOpeningImageFilter.cxx==<br />
<source lang="cpp"><br />
<br />
#include "itkBinaryStatisticsOpeningImageFilter.h"<br />
#include "itkImageFileWriter.h"<br />
<br />
typedef itk::Image<unsigned char, 2> ImageType;<br />
void CreateImage(ImageType::Pointer image1, ImageType::Pointer image2);<br />
<br />
int main(int argc, char* argv[])<br />
{<br />
ImageType::Pointer binaryImage = ImageType::New();<br />
ImageType::Pointer featureImage = ImageType::New();<br />
<br />
CreateImage(binaryImage, featureImage);<br />
<br />
typedef itk::BinaryStatisticsOpeningImageFilter<ImageType, ImageType> <br />
BinaryOpeningType;<br />
BinaryOpeningType::Pointer opening = BinaryOpeningType::New();<br />
opening->SetInput(binaryImage);<br />
opening->SetFeatureImage(featureImage);<br />
opening->SetBackgroundValue(0);<br />
opening->SetForegroundValue(255);<br />
opening->SetLambda(150);<br />
opening->SetAttribute( BinaryOpeningType::LabelObjectType::MEAN);<br />
opening->Update();<br />
<br />
typedef itk::ImageFileWriter<ImageType> WriterType;<br />
WriterType::Pointer writer = WriterType::New();<br />
writer->SetFileName("input.mhd");<br />
writer->SetInput(featureImage);<br />
writer->Update();<br />
writer->SetFileName("output.mhd");<br />
writer->SetInput(opening->GetOutput());<br />
writer->Update();<br />
<br />
}<br />
<br />
void CreateImage(ImageType::Pointer image1, ImageType::Pointer image2)<br />
{<br />
// Create an image with 2 connected components<br />
ImageType::RegionType region;<br />
ImageType::IndexType start;<br />
start[0] = 0;<br />
start[1] = 0;<br />
<br />
ImageType::SizeType size;<br />
size[0] = 200;<br />
size[1] = 200;<br />
<br />
region.SetSize(size);<br />
region.SetIndex(start);<br />
<br />
image1->SetRegions(region);<br />
image1->Allocate();<br />
image1->FillBuffer(0);<br />
<br />
image2->SetRegions(region);<br />
image2->Allocate();<br />
image2->FillBuffer(0);<br />
<br />
// Make a square<br />
for(unsigned int r = 20; r < 80; r++)<br />
{<br />
for(unsigned int c = 30; c < 100; c++)<br />
{<br />
ImageType::IndexType pixelIndex;<br />
pixelIndex[0] = r;<br />
pixelIndex[1] = c;<br />
<br />
image1->SetPixel(pixelIndex, 255);<br />
image2->SetPixel(pixelIndex, 100);<br />
}<br />
}<br />
<br />
// Make another square<br />
for(unsigned int r = 100; r < 130; r++)<br />
{<br />
for(unsigned int c = 115; c < 160; c++)<br />
{<br />
ImageType::IndexType pixelIndex;<br />
pixelIndex[0] = r;<br />
pixelIndex[1] = c;<br />
<br />
image1->SetPixel(pixelIndex, 255);<br />
image2->SetPixel(pixelIndex, 200);<br />
}<br />
}<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|BinaryStatisticsOpeningImageFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter&diff=48627ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter2012-08-24T17:37:45Z<p>Ccagataybilgin: /* StatisticsOpeningImageFilter.cxx */</p>
<hr />
<div>==BinaryStatisticsOpeningImageFilter.cxx==<br />
<source lang="cpp"><br />
<br />
#include "itkBinaryStatisticsOpeningImageFilter.h"<br />
#include "itkImageFileWriter.h"<br />
<br />
typedef itk::Image<unsigned char, 2> ImageType;<br />
void CreateImage(ImageType::Pointer image1, ImageType::Pointer image2);<br />
<br />
int main(int argc, char* argv[])<br />
{<br />
ImageType::Pointer binaryImage = ImageType::New();<br />
ImageType::Pointer featureImage = ImageType::New();<br />
<br />
CreateImage(binaryImage, featureImage);<br />
<br />
typedef itk::BinaryStatisticsOpeningImageFilter<ImageType, ImageType> <br />
BinaryOpeningType;<br />
BinaryOpeningType::Pointer opening = BinaryOpeningType::New();<br />
opening->SetInput(binaryImage);<br />
opening->SetFeatureImage(featureImage);<br />
opening->SetBackgroundValue(0);<br />
opening->SetForegroundValue(255);<br />
opening->SetLambda(150);<br />
opening->SetAttribute( BinaryOpeningType::LabelObjectType::MEAN);<br />
opening->Update();<br />
<br />
typedef itk::ImageFileWriter<ImageType> WriterType;<br />
WriterType::Pointer writer = WriterType::New();<br />
writer->SetFileName("input.mhd");<br />
writer->SetInput(featureImage);<br />
writer->Update();<br />
writer->SetFileName("output.mhd");<br />
writer->SetInput(opening->GetOutput());<br />
writer->Update();<br />
<br />
}<br />
<br />
void CreateImage(ImageType::Pointer image1, ImageType::Pointer image2)<br />
{<br />
// Create an image with 2 connected components<br />
ImageType::RegionType region;<br />
ImageType::IndexType start;<br />
start[0] = 0;<br />
start[1] = 0;<br />
<br />
ImageType::SizeType size;<br />
size[0] = 200;<br />
size[1] = 200;<br />
<br />
region.SetSize(size);<br />
region.SetIndex(start);<br />
<br />
image1->SetRegions(region);<br />
image1->Allocate();<br />
image1->FillBuffer(0);<br />
<br />
image2->SetRegions(region);<br />
image2->Allocate();<br />
image2->FillBuffer(0);<br />
<br />
// Make a square<br />
for(unsigned int r = 20; r < 80; r++)<br />
{<br />
for(unsigned int c = 30; c < 100; c++)<br />
{<br />
ImageType::IndexType pixelIndex;<br />
pixelIndex[0] = r;<br />
pixelIndex[1] = c;<br />
<br />
image1->SetPixel(pixelIndex, 255);<br />
image2->SetPixel(pixelIndex, 100);<br />
}<br />
}<br />
<br />
// Make another square<br />
for(unsigned int r = 100; r < 130; r++)<br />
{<br />
for(unsigned int c = 115; c < 160; c++)<br />
{<br />
ImageType::IndexType pixelIndex;<br />
pixelIndex[0] = r;<br />
pixelIndex[1] = c;<br />
<br />
image1->SetPixel(pixelIndex, 255);<br />
image2->SetPixel(pixelIndex, 200);<br />
}<br />
}<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|BinaryStatisticsOpeningImageFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter&diff=48626ITK/Examples/ImageProcessing/BinaryStatisticsOpeningImageFilter2012-08-24T17:33:53Z<p>Ccagataybilgin: Created page with "==MergeLabelMapFilter.cxx== <source lang="cpp"> #include "itkBinaryImageToShapeLabelMapFilter.h" #include "itkMergeLabelMapFilter.h" #include "itkBinaryStatisticsOpeningImageFil..."</p>
<hr />
<div>==MergeLabelMapFilter.cxx==<br />
<source lang="cpp"><br />
<br />
#include "itkBinaryImageToShapeLabelMapFilter.h"<br />
#include "itkMergeLabelMapFilter.h"<br />
#include "itkBinaryStatisticsOpeningImageFilter.h"<br />
#include "itkImageFileWriter.h"<br />
<br />
typedef itk::Image<unsigned char, 2> ImageType;<br />
void CreateImage(ImageType::Pointer image1, ImageType::Pointer image2);<br />
<br />
int main(int argc, char* argv[])<br />
{<br />
ImageType::Pointer binaryImage = ImageType::New();<br />
ImageType::Pointer featureImage = ImageType::New();<br />
<br />
CreateImage(binaryImage, featureImage);<br />
<br />
typedef itk::BinaryStatisticsOpeningImageFilter<ImageType, ImageType> <br />
BinaryOpeningType;<br />
BinaryOpeningType::Pointer opening = BinaryOpeningType::New();<br />
opening->SetInput(binaryImage);<br />
opening->SetFeatureImage(featureImage);<br />
opening->SetBackgroundValue(0);<br />
opening->SetForegroundValue(255);<br />
opening->SetLambda(150);<br />
opening->SetAttribute( BinaryOpeningType::LabelObjectType::MEAN);<br />
opening->Update();<br />
<br />
typedef itk::ImageFileWriter<ImageType> WriterType;<br />
WriterType::Pointer writer = WriterType::New();<br />
writer->SetFileName("input.mhd");<br />
writer->SetInput(featureImage);<br />
writer->Update();<br />
writer->SetFileName("output.mhd");<br />
writer->SetInput(opening->GetOutput());<br />
writer->Update();<br />
<br />
}<br />
<br />
void CreateImage(ImageType::Pointer image1, ImageType::Pointer image2)<br />
{<br />
// Create an image with 2 connected components<br />
ImageType::RegionType region;<br />
ImageType::IndexType start;<br />
start[0] = 0;<br />
start[1] = 0;<br />
<br />
ImageType::SizeType size;<br />
size[0] = 200;<br />
size[1] = 200;<br />
<br />
region.SetSize(size);<br />
region.SetIndex(start);<br />
<br />
image1->SetRegions(region);<br />
image1->Allocate();<br />
image1->FillBuffer(0);<br />
<br />
image2->SetRegions(region);<br />
image2->Allocate();<br />
image2->FillBuffer(0);<br />
<br />
// Make a square<br />
for(unsigned int r = 20; r < 80; r++)<br />
{<br />
for(unsigned int c = 30; c < 100; c++)<br />
{<br />
ImageType::IndexType pixelIndex;<br />
pixelIndex[0] = r;<br />
pixelIndex[1] = c;<br />
<br />
image1->SetPixel(pixelIndex, 255);<br />
image2->SetPixel(pixelIndex, 100);<br />
}<br />
}<br />
<br />
// Make another square<br />
for(unsigned int r = 100; r < 130; r++)<br />
{<br />
for(unsigned int c = 115; c < 160; c++)<br />
{<br />
ImageType::IndexType pixelIndex;<br />
pixelIndex[0] = r;<br />
pixelIndex[1] = c;<br />
<br />
image1->SetPixel(pixelIndex, 255);<br />
image2->SetPixel(pixelIndex, 200);<br />
}<br />
}<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|BinaryStatisticsOpeningImageFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=File:BinaryStatisticsOpeningImageFilter.cpp&diff=48625File:BinaryStatisticsOpeningImageFilter.cpp2012-08-24T17:30:17Z<p>Ccagataybilgin: uploaded a new version of &quot;File:BinaryStatisticsOpeningImageFilter.cpp&quot;</p>
<hr />
<div>Creates an image with two squares in it having values 100 and 200 respectively. Statistics opening filter is applied to remove objects that have mean value less than 150.</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=File:CMakeLists.txt&diff=48624File:CMakeLists.txt2012-08-24T17:28:20Z<p>Ccagataybilgin: uploaded a new version of &quot;File:CMakeLists.txt&quot;</p>
<hr />
<div>CMakeLists for building and installing the 3DConnexion SDK for Linux.</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=File:BinaryStatisticsOpeningImageFilter.cpp&diff=48623File:BinaryStatisticsOpeningImageFilter.cpp2012-08-24T17:27:49Z<p>Ccagataybilgin: Creates an image with two squares in it having values 100 and 200 respectively. Statistics opening filter is applied to remove objects that have mean value less than 150.</p>
<hr />
<div>Creates an image with two squares in it having values 100 and 200 respectively. Statistics opening filter is applied to remove objects that have mean value less than 150.</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples&diff=48622ITK/Examples2012-08-24T17:25:44Z<p>Ccagataybilgin: /* Blob Detection, Labeling, and Properties */</p>
<hr />
<div>These are fully independent, compilable examples, developed with these [[ITK/Examples/Goals|goals]] in mind. There is significant overlap in the examples, but they are each intended to illustrate a different concept and be fully stand alone compilable.<br />
Please add examples in your areas of expertise!<br />
You can checkout the entire set of examples from this repository: <br />
http://gitorious.org/itkwikiexamples/itkwikiexamples<br />
<pre>git clone git://gitorious.org/itkwikiexamples/itkwikiexamples.git ITKWikiExamples</pre><br />
<br />
==About the Examples==<br />
* [http://www.itk.org/Wiki/images/e/e6/ITK_Examples_Iowa_Meeting_2010_11-8-2010.odp Official announcement]<br />
===ItkVtkGlue===<br />
ITK and VTK are very separate toolkits - ITK for image processing and VTK for data visualization. It is often convenient to use the two together - namely, to display an ITK image on the screen. The ITKVtkGlue module serves exactly this purpose. Also provided inside ItkVtkGlue is a QuickView class to allow a 2 line display of an ITK image.<br />
<br />
===[[ITK/Examples/Instructions/ForUsers|Information for Wiki Examples Users]]===<br />
If you just want to use the Wiki Examples, [[ITK/Examples/Instructions/ForUsers|go here]]. You will learn how to search for examples, build a few examples and build all of the examples.<br />
<br />
===[[ITK/Examples/Instructions/ForDevelopers|Information for Wiki Examples Developers]]===<br />
If you want to contribute examples [[ITK/Examples/Instructions/ForDevelopers|go here]]. You will learn how to add a new example and the guidelines for writing an example.<br />
<br />
===[[ITK/Examples/Instructions/ForAdministrators|Information for Wiki Examples Administrators]]===<br />
If you are a Wiki Example Administrator or want to learn more about the process [[ITK/Examples/Instructions/ForAdministrators|go here]]. You will learn how the Wiki Examples repository is organized, how the repository is synced to the wiki and how to add new topics, tests and regression baselines.<br />
<br />
==CMake Techniques==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/CMake/CheckForModule | Check if a specific module is present]] || || <br />
|-<br />
| [[ITK/Examples/CMake/CheckForITK4 | Check for ITK4]] || || <br />
|}<br />
<br />
==Visualization==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Visualization/QuickView | Display an image]] || || QuickView<br />
|}<br />
<br />
==Simple Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RequestedRegion | Apply a filter only to a specified region of an image ]] || || SetRequestedRegion<br />
|-<br />
| [[ITK/Examples/SimpleOperations/WidthHeight | Get the width and height of an image ]] || || row, column<br />
|-<br />
| [[ITK/Examples/SimpleOperations/VariableLengthVector | Variable length vector ]] || {{ITKDoxygenURL|VariableLengthVector}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TranslationTransform | Translate an image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|ResampleImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/NumericTraits | Get some basic information about a type]] || {{ITKDoxygenURL|NumericTraits}}|| Zero<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ScalarToRGBColormapImageFilter | Apply a color map to an image]] || {{ITKDoxygenURL|ScalarToRGBColormapImageFilter}}|| Pseudocolor, pseudo-color<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CustomColormap | Create and apply a custom colormap]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/ParaviewColormap | Create and apply a colormap closely resembling the default Paraview colormap "Cool to warm"]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TryCatch | Catch an ITK exception]] || || Try/Catch blocks<br />
|-<br />
| [[ITK/Examples/SimpleOperations/BresenhamLine | Get the points on a Bresenham line between two points]] || {{ITKDoxygenURL|BresenhamLine}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/Offset | Add an offset to a pixel index]] || {{ITKDoxygenURL|Offset}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenPoints | Distance between two points]] || {{ITKDoxygenURL|Point}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenIndices | Distance between two indices]] || {{ITKDoxygenURL|Point}}, {{ITKDoxygenURL|Index}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CreateVector | Create a vector]] || {{ITKDoxygenURL|Vector}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/GetNameOfClass | Get the name/type/class of an object ]] || || GetNameOfClass()<br />
|-<br />
| [[ITK/Examples/Images/Index | An object which holds the index of a pixel ]] || {{ITKDoxygenURL|Index}} || <br />
|-<br />
| [[ITK/Examples/Images/Size | An object which holds the size of an image ]] || {{ITKDoxygenURL|Size}} || <br />
|-<br />
| [[ITK/Examples/Images/ImageRegion | An object which holds the index (start) and size of a region of an image ]] || {{ITKDoxygenURL|ImageRegion}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/Transparency | Make part of an image transparent]] || {{ITKDoxygenURL|RGBAPixel}} || Transparency, RGBA, alpha<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionIntersection | Determine if one region is fully inside another region]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/PixelInsideRegion | Determine if a pixel is inside of a region]] || {{ITKDoxygenURL|ImageRegion}} || IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionOverlap | Determine the overlap of two regions]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, crop a region<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ImageDuplicator | Duplicate an image]] || {{ITKDoxygenURL|ImageDuplicator}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/RandomImageSource | Produce an image of noise]] || {{ITKDoxygenURL|RandomImageSource}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/SetPixels | Set specified pixels to specified values]] || {{ITKDoxygenURL|Image}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RGBPixel | Create an RGB image]] || {{ITKDoxygenURL|RGBPixel}} ||<br />
|}<br />
<br />
==Mathematical Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/CovariantVector | Create a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || This is the object which should be used to represent a mathematical vector.<br />
|-<br />
| [[ITK/Examples/Math/CovariantVectorNorm | Compute the norm of a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || In-place and non-inplace norms.<br />
|-<br />
| [[ITK/Examples/Math/Matrix | Matrix ]] || {{ITKDoxygenURL|Matrix}} || <br />
|-<br />
| [[ITK/Examples/Math/Pi | Mathematical constant pi = 3.14 ]] || {{ITKDoxygenURL|Math}} || <br />
|-<br />
| [[ITK/Examples/Math/DotProduct | Dot product (inner product) of two vectors ]] || {{ITKDoxygenURL|Vector}} || <br />
|}<br />
<br />
==Trigonometric Filters==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/Trig/SinImageFilter | Compute the sine of each pixel.]] || {{ITKDoxygenURL|SinImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Math/Trig/Atan2ImageFilter | Compute the arctangent of each pixel.]] || {{ITKDoxygenURL|Atan2ImageFilter}}<br />
|}<br />
<br />
==Image Functions==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Functions/NeighborhoodOperatorImageFunction | Multiply a kernel with an image at a particular location]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunction | GaussianBlurImageFunction ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunctionFilter | GaussianBlurImageFunctionFilter ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/MedianImageFunction| Compute the median of an image at a pixels (in a regular neighborhood)]] || {{ITKDoxygenURL|MedianImageFunction}} || <br />
|}<br />
<br />
==Point Set==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/PointSet/CreatePointSet | Create a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/ReadPointSet | Read a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/WritePointSet | Write a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/BoundingBox | Get the bounding box of a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|}<br />
<br />
==Input/Output (IO)==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/IO/ReadVectorImage| Read an image file with an unknown number of components]] || {{ITKDoxygenURL|ImageFileReader}},{{ITKDoxygenURL|VectorImage}} || <br />
|-<br />
| [[ITK/Examples/IO/ImportImageFilter| Convert a C-style array to an itkImage]] || {{ITKDoxygenURL|ImportImageFilter}} || <br />
|-<br />
| [[ITK/Examples/IO/ReadUnknownImageType | Read an image file without knowing its type before hand]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileWriter | Write an image]] || {{ITKDoxygenURL|ImageFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileReader | Read an image]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/TIFFImageIO | Write a TIFF image]] || {{ITKDoxygenURL|TIFFImageIO}} || This is a general demonstration of how to use a specific writer rather than relying on the ImageFileWriter to choose for you.<br />
|-<br />
| [[ITK/Examples/IO/ImageToVTKImageFilter | Display an ITK image]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileWriter | Write a transform to a file]] || {{ITKDoxygenURL|TransformFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileReader | Read a transform from a file]] || {{ITKDoxygenURL|TransformFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/VolumeFromSlices | Create a 3D volume from a series of 2D images]] || {{ITKDoxygenURL|ImageSeriesReader}} || Uses NumericSeriesFileNames to generate a list of file names<br />
|-<br />
| [[ITK/Examples/IO/itkVtkImageConvertDICOM | Uses a custom user matrix to align the image with DICOM physical space]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} || <br />
|}<br />
<br />
==DICOM==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/DICOM/ResampleDICOM | Resample a DICOM series]] || {{ITKDoxygenURL|GDCMImageIO}} || Resample a DICOM series with user-specified spacing.<br />
|}<br />
<br />
==Blob Detection, Labeling, and Properties==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ManuallyRemovingLabels | Remove labels from a LabelMap]] || {{ITKDoxygenURL|LabelMap}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ObjectByObjectLabelMapFilter | Apply an operation to every label object in a label map]] || {{ITKDoxygenURL|ObjectByObjectLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ShapeOpeningLabelMapFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|ShapeOpeningLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelShapeKeepNObjectsImageFilter | Keep only regions that rank above a certain level of a particular property]] || {{ITKDoxygenURL|LabelShapeKeepNObjectsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/StatisticsOpeningLabelMapFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|BinaryStatisticsOpeningLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapOverlayImageFilter | Color labeled regions in an image]] || {{ITKDoxygenURL|LabelMapOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelGeometryImageFilter | Get geometric properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelGeometryImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelStatisticsImageFilter | Get statistical properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelStatisticsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/LabelMapContourOverlayImageFilter | Color the boundaries of labeled regions in an image]] || {{ITKDoxygenURL|LabelMapContourOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToLabelMapFilter | Label binary regions in an image]] || {{ITKDoxygenURL|BinaryImageToLabelMapFilter}} || Also demonstrates how to obtain which pixels belong to each label.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToShapeLabelMapFilter | Label binary regions in an image and get their properties]] || {{ITKDoxygenURL|BinaryImageToShapeLabelMapFilter}} || Region bounding box, centroid, etc.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapToLabelImageFilter | Convert a LabelMap to a normal image with different values representing each region]] || {{ITKDoxygenURL|LabelMapToLabelImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MergeLabelMapFilter | Merges several labelmaps]] || {{ITKDoxygenURL|MergeLabelMapFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelOverlayImageFilter | Overlay a LabelMap on an image]] || {{ITKDoxygenURL|LabelOverlayImageFilter}} || <br />
|}<br />
<br />
==Correlation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Images/NormalizedCorrelationImageFilter | Normalized correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/NormalizedCorrelationImageFilterMasked | Normalized correlation of a masked image]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/FFTNormalizedCorrelationImageFilter | Normalized correlation using the FFT]] || {{ITKDoxygenURL|FFTNormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskedFFTNormalizedCorrelationImageFilter | Normalized correlation using the FFT with optional mask images for both input images]] || {{ITKDoxygenURL|MaskedFFTNormalizedCorrelationImageFilter}} ||<br />
|}<br />
<br />
==Image Processing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RGBToLuminanceImageFilter | Convert an RGB image to a luminance image]] || {{ITKDoxygenURL|RGBToLuminanceImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThinningImageFilter | Skeletonize/thin an image]] || {{ITKDoxygenURL|BinaryThinningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScaleTransform | Scale an image]] || {{ITKDoxygenURL|ScaleTransform}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ResampleImageFilter | Resample (stretch or compress) an image]] || {{ITKDoxygenURL|ResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RGBResampleImageFilter | Resample (stretch or compress) an RGB image]] || {{ITKDoxygenURL|VectorResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/MutualInformationImageToImageFilter | Compute the mutual information between two image]] || {{ITKDoxygenURL|MutualInformationImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianSharpeningImageFilter | Sharpen an image]] || {{ITKDoxygenURL|LaplacianSharpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/DivideImageFilter | Pixel-wise division of two images]] || {{ITKDoxygenURL|DivideImageFilter}} || Divide images<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ApproximateSignedDistanceMapImageFilter | Compute a distance map from objects in a binary image]] || {{ITKDoxygenURL|ApproximateSignedDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeToConstantImageFilter | Scale all pixels so that their sum is a specified constant]] || {{ITKDoxygenURL|NormalizeToConstantImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMinimaImageFilter | RegionalMinimaImageFilter]] || {{ITKDoxygenURL|RegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMaximaImageFilter | RegionalMaximaImageFilter]] || {{ITKDoxygenURL|RegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ZeroCrossingImageFilter| Find zero crossings in a signed image]] || {{ITKDoxygenURL|ZeroCrossingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RecursiveMultiResolutionPyramidImageFilter| Construct a multiresolution pyramid from an image]] || {{ITKDoxygenURL|RecursiveMultiResolutionPyramidImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddConstantToImageFilter| Add a constant to every pixel in an image]] || {{ITKDoxygenURL|AddImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractConstantFromImageFilter| Subtract a constant from every pixel in an image]] || {{ITKDoxygenURL|SubtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquareImageFilter| Square every pixel in an image]] || {{ITKDoxygenURL|SquareImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Upsampling| Upsampling an image]] || {{ITKDoxygenURL|BSplineInterpolateImageFunction}} {{ITKDoxygenURL|ResampleImageFilter}} || Interpolate missing pixels in order to upsample an image. Note this only works on scalar images.<br />
|-<br />
| [[ITK/Examples/Images/FlipImageFilter | Flip an image over specified axes]] || {{ITKDoxygenURL|FlipImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/VectorRescaleIntensityImageFilter | Apply a transformation to the magnitude of vector valued image pixels]] || {{ITKDoxygenURL|VectorRescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/NeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskNeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image that is non-zero in a mask]] || {{ITKDoxygenURL|MaskNeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianImageFilter | Compute the Laplacian of an image]] || {{ITKDoxygenURL|LaplacianImageFilter}} || Input image type must be double or float<br />
|-<br />
| [[ITK/Examples/Images/ConstantPadImageFilter | Pad an image with a constant value]] || {{ITKDoxygenURL|ConstantPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/MirrorPadImageFilter | Pad an image using mirroring over the boundaries]] || {{ITKDoxygenURL|MirrorPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/WrapPadImageFilter | Pad an image by wrapping]] || {{ITKDoxygenURL|WrapPadImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/IntensityWindowingImageFilter| IntensityWindowingImageFilter]] || {{ITKDoxygenURL|IntensityWindowingImageFilter}} || Apply a linear intensity transform from a specified input range to a specified output range.<br />
|-<br />
| [[ITK/Examples/Images/ShrinkImageFilter | Shrink an image]] || {{ITKDoxygenURL|ShrinkImageFilter}} || Downsample an image<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyByConstantImageFilter | Multiply every pixel in an image by a constant]] || {{ITKDoxygenURL|MultiplyImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquaredDifferenceImageFilter | Compute the squared difference of corresponding pixels in two images]] || {{ITKDoxygenURL|SquaredDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsoluteValueDifferenceImageFilter | Compute the absolute value of the difference of corresponding pixels in two images]] || {{ITKDoxygenURL|AbsoluteValueDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddPixelAccessor | Add a constant to every pixel without duplicating the image in memory (an accessor)]] || {{ITKDoxygenURL|AddPixelAccessor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMaximaImageFilter | ValuedRegionalMaximaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMinimaImageFilter | ValuedRegionalMinimaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaximumImageFilter | Pixel wise compare two input images and set the output pixel to their max]] || {{ITKDoxygenURL|MaximumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumImageFilter | Pixel wise compare two input images and set the output pixel to their min]] || {{ITKDoxygenURL|MinimumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AndImageFilter | Binary AND two images]] || {{ITKDoxygenURL|AndImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/OrImageFilter | Binary OR two images]] || {{ITKDoxygenURL|OrImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/XorImageFilter | Binary XOR (exclusive OR) two images]] || {{ITKDoxygenURL|XorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryNotImageFilter | Invert an image using the Binary Not operation]] || {{ITKDoxygenURL|BinaryNotImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Compose3DCovariantVectorImageFilter | Compose a vector image (with 3 components) from three scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/NthElementImageAdaptor | Extract a component/channel of an itkImage with pixels with multiple components]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || Use built in functionality to extract a component of an itkImage with CovariantVector components. Note this does not work for itkVectorImages - see VectorIndexSelectionCastImageFilter instead.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageAdaptorExtractVectorComponent | Present an image by first performing an operation]] || {{ITKDoxygenURL|ImageAdaptor}} || A demonstration of how to present an image pixel as a function of the pixel. In this example the functionality of NthElementImageAdaptor is demonstrated.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ProcessingNthImageElement | Process the nth component/element/channel of a vector image]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConvolutionImageFilter | Convolve an image with a kernel]] || {{ITKDoxygenURL|ConvolutionImageFilter}} || Convolution.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ExtractImageFilter | Crop an image by specifying the region to keep]] || {{ITKDoxygenURL|ExtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/CropImageFilter | Crop an image by specifying the region to throw away]] || {{ITKDoxygenURL|CropImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsImageFilter | Compute the absolute value of an image]] || {{ITKDoxygenURL|AbsImageFilter}} || magnitude<br />
|-<br />
| [[ITK/Examples/ImageProcessing/InvertIntensityImageFilter | Invert an image]] || {{ITKDoxygenURL|InvertIntensityImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskImageFilter | Apply a mask to an image]] || {{ITKDoxygenURL|MaskImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskNegatedImageFilter | Apply the inverse of a mask to an image]] || {{ITKDoxygenURL|MaskNegatedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SigmoidImageFilter | Pass image pixels through a sigmoid function]] || {{ITKDoxygenURL|SigmoidImageFilter}} || The qualitative description of how Alpha and Beta affect the function from the ITK Software Guide and the associated images would be nice to add to the doxygen.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|ThresholdImageFilter}} || The result is the original image but with the values below (or above) the threshold "clamped" to an output value.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|BinaryThresholdImageFilter}} || The result is a binary image (inside the threshold region or outside the threshold region).<br />
|-<br />
| [[ITK/Examples/ImageProcessing/UnaryFunctorImageFilter | Apply a custom operation to each pixel in an image]] || {{ITKDoxygenURL|UnaryFunctorImageFilter}} || Perform a custom operation on every pixel in an image. This example rotates the vector-valued pixels by 90 degrees.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilter | Apply a predefined operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilterCustom | Apply a custom operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || This example computes the squared difference between corresponding pixels.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumMaximumImageCalculator | Find the minimum and maximum value (and the position of the value) in an image]] || {{ITKDoxygenURL|MinimumMaximumImageCalculator}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddImageFilter | Add two images together]] || {{ITKDoxygenURL|AddImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractImageFilter | Subtract two images]] || {{ITKDoxygenURL|SubtractImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PasteImageFilter | Paste a part of one image into another image]] || {{ITKDoxygenURL|PasteImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_CreateVolume | Stack multiple 2D images into a 3D image]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_SideBySide | Tile multiple images side by side]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyImageFilter | Multiply two images together]] || {{ITKDoxygenURL|MultiplyImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionOfInterestImageFilter | Extract a portion of an image (region of interest)]] || {{ITKDoxygenURL|RegionOfInterestImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RescaleIntensityImageFilter | Rescale the intensity values of an image to a specified range]] || {{ITKDoxygenURL|RescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeImageFilter | Normalize an image]] || {{ITKDoxygenURL|NormalizeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/CastImageFilter | Cast an image from one type to another]] || {{ITKDoxygenURL|CastImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ClampImageFilter | Cast an image from one type to another but clamp to the output value range]] || {{ITKDoxygenURL|ClampImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PermuteAxesImageFilter | Switch the axes of an image]] || {{ITKDoxygenURL|PermuteAxesImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LinearInterpolateImageFunction | Linearly interpolate a position in an image]] || {{ITKDoxygenURL|LinearInterpolateImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/HammingWindowFunction | HammingWindowFunction]] || {{ITKDoxygenURL|HammingWindowFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageFilterOnARegion | Run an image filter on a region of an image]] || {{ITKDoxygenURL|PasteImageFIlter}} || This example uses the RequestedRegion of a filter to process a subset of an image.<br />
|}<br />
<br />
==Vector Images==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorMagnitudeImageFilter | Compute the magnitude of each pixel in a vector image to produce a magnitude image]] || {{ITKDoxygenURL|VectorMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImage | Create a vector image]] || {{ITKDoxygenURL|VectorImage}} || An image with an ND vector at each pixel<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Create a vector image from a collection of scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || Combine, layer<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImageToImageAdaptor | View a component of a vector image as if it were a scalar image]] || {{ITKDoxygenURL|VectorImageToImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/VectorImages/VectorIndexSelectionCastImageFilter | Extract a component/channel of a vector image]] || {{ITKDoxygenURL|VectorIndexSelectionCastImageFilter}} || This works with VectorImage as well as Image<Vector><br />
|-<br />
| [[ITK/Examples/VectorImages/VectorResampleImageFilter | Translate a vector image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|VectorResampleImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/JoinImageFilter | Join images, stacking their components]] || {{ITKDoxygenURL|JoinImageFilter}} || concatenate, channels<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Stack scalar images into a VectorImage]] || {{ITKDoxygenURL|ImageToVectorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/NeighborhoodIterator | NeighborhoodIterator on a VectorImage]] || {{ITKDoxygenURL|VectorImage}} {{ITKDoxygenURL|NeighborhoodIterator}}||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorCastImageFilter | Cast a VectorImage to another type of VectorImage]] || {{ITKDoxygenURL|VectorImage}} ||<br />
|}<br />
<br />
==Iterating Over (Traversing) An Image==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator_Manual | Iterate over a region of an image with a shaped neighborhood]] || Create the shape manually {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator | Iterate over a region of an image with a shaped neighborhood]] || Create the shape from a StructuringElement {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionExclusionConstIteratorWithIndex | Iterator over an image skipping a specified region]] || {{ITKDoxygenURL|ImageRegionExclusionConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomConstIteratorWithIndex | Randomly select pixels from a region of an image]] || {{ITKDoxygenURL|ImageRandomConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomNonRepeatingConstIteratorWithIndex | Randomly select pixels from a region of an image without replacement]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/LineIterator | Iterate over a line through an image]] || {{ITKDoxygenURL|LineIterator}} || Walks a Bresenham line through an image (with write access)<br />
|-<br />
| [[ITK/Examples/Iterators/LineConstIterator | Iterate over a line through an image without write access]] || {{ITKDoxygenURL|LineConstIterator}} || Walks a Bresenham line through an image (without write access)<br />
|-<br />
| [[ITK/Examples/Iterators/ImageBoundaryFacesCalculator | Iterate over the central region (non-boundary) separately from the face-regions (boundary)]] || {{ITKDoxygenURL|ImageBoundaryFacesCalculator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/NeighborhoodIterator | Iterate over a region of an image with a neighborhood (with write access)]] || {{ITKDoxygenURL|NeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstNeighborhoodIterator | Iterate over a region of an image with a neighborhood (without write access)]] || {{ITKDoxygenURL|ConstNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIterator | Iterate over a region of an image (with write access)]] || {{ITKDoxygenURL|ImageRegionIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIterator | Iterate over a region of an image (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstantBoundaryCondition | Make out of bounds pixels return a constant value]] || {{ITKDoxygenURL|ConstantBoundaryCondition}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (with write access)]] || {{ITKDoxygenURL|ImageRegionIteratorWithIndex}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIteratorWithIndex}} ||<br />
|}<br />
<br />
==Kernels==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Operators/GaussianOperator | Create a Gaussian kernel]] || {{ITKDoxygenURL|GaussianOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/GaussianDerivativeOperator | Create a Gaussian derivative kernel]] || {{ITKDoxygenURL|GaussianDerivativeOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/LaplacianOperator | Create a Laplacian kernel]] || {{ITKDoxygenURL|LaplacianOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/DerivativeOperator | Create a derivative kernel]] || {{ITKDoxygenURL|DerivativeOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/SobelOperator | Create the Sobel kernel]] || {{ITKDoxygenURL|SobelOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/ForwardDifferenceOperator | Create a forward difference kernel]] || {{ITKDoxygenURL|ForwardDifferenceOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/BackwardDifferenceOperator | Create a backward difference kernel]] || {{ITKDoxygenURL|BackwardDifferenceOperator}} || <br />
<br />
|}<br />
<br />
==Image Edges, Gradients, and Derivatives==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/SobelEdgeDetectionImageFilter | SobelEdgeDetectionImageFilter]] || {{ITKDoxygenURL|SobelEdgeDetectionImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/DerivativeImageFilter | Compute the derivative of an image in a particular direction]] || {{ITKDoxygenURL|DerivativeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientRecursiveGaussianImageFilter| Compute the gradient of an image by convolution with the first derivative of a Gaussian]] || {{ITKDoxygenURL|GradientRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeRecursiveGaussianImageFilter | Find the gradient magnitude of the image first smoothed with a Gaussian kernel]] || {{ITKDoxygenURL|GradientMagnitudeRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/RecursiveGaussianImageFilter | Find higher derivatives of an image]] || {{ITKDoxygenURL|RecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryContourImageFilter | Extract the boundaries of connected regions in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} || Blob boundary, border<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryBoundaries | Extract the inner and outer boundaries of blobs in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeImageFilter | Compute the gradient magnitude image]] || {{ITKDoxygenURL|GradientMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/LaplacianRecursiveGaussianImageFilter | Compute the Laplacian of Gaussian (LoG) of an image]] || {{ITKDoxygenURL|LaplacianRecursiveGaussianImageFilter}} ||<br />
|}<br />
<br />
==Smoothing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Smoothing/AntiAliasBinaryImageFilter | Anti alias a binary image]] || {{ITKDoxygenURL|AntiAliasBinaryImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinaryMinMaxCurvatureFlowImageFilter | BinaryMinMaxCurvatureFlow a binary image]] || {{ITKDoxygenURL|BinaryMinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MeanImageFilter | Mean filter an image]] || {{ITKDoxygenURL|MeanImageFilter}} || Replace each pixel by the mean of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/MedianImageFilter | Median filter an image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/RGBMedianImageFilter | Median filter an RGB image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/DiscreteGaussianImageFilter | Smooth an image with a discrete Gaussian filter]] || {{ITKDoxygenURL|DiscreteGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinomialBlurImageFilter | Blur an image]] || {{ITKDoxygenURL|BinomialBlurImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BilateralImageFilter | Bilateral filter an image]] || {{ITKDoxygenURL|BilateralImageFilter}} || Edge preserving smoothing.<br />
|-<br />
| [[ITK/Examples/Smoothing/CurvatureFlowImageFilter | Smooth an image using curvature flow]] || {{ITKDoxygenURL|CurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MinMaxCurvatureFlowImageFilter | Smooth an image using min/max curvature flow]] || {{ITKDoxygenURL|MinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/SmoothingRecursiveGaussianImageFilter | Gaussian smoothing that works with image adaptors]] || {{ITKDoxygenURL|SmoothingRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/VectorGradientAnisotropicDiffusionImageFilter | Smooth an image while preserving edges]] || {{ITKDoxygenURL|VectorGradientAnisotropicDiffusionImageFilter}} || Anisotropic diffusion.<br />
|}<br />
<br />
==Morphology==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Morphology/BinaryErodeImageFilter | Erode a binary image]] || {{ITKDoxygenURL|BinaryErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryDilateImageFilter | Dilate a binary image]] || {{ITKDoxygenURL|BinaryDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryPruningImageFilter | Prune a binary image]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalOpeningImageFilter | Opening a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalOpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalClosingImageFilter | Closing a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalClosingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleDilateImageFilter | Dilate a grayscale image]] || {{ITKDoxygenURL|GrayscaleDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleErodeImageFilter | Erode a grayscale image]] || {{ITKDoxygenURL|GrayscaleErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/FlatStructuringElement | Erode a binary image using a flat (box) structuring element]] || {{ITKDoxygenURL|FlatStructuringElement}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryBallStructuringElement | An elliptical structuring element]] || {{ITKDoxygenURL|BinaryBallStructuringElement}} || <br />
|}<br />
<br />
==Curves==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Curves/ContourMeanDistanceImageFilter | Compute the mean distance between all points of two curves]] || {{ITKDoxygenURL|ContourMeanDistanceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Curves/PolyLineParametricPath | A data structure for a piece-wise linear curve]] || {{ITKDoxygenURL|PolyLineParametricPath}} || <br />
|}<br />
<br />
==Spectral Analysis==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/ForwardFFTImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|ForwardFFTImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/InverseFFTImageFilter | Compute the inverse FFT of an image]] || {{ITKDoxygenURL|InverseFFTImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/VnlFFTRealToComplexConjugateImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/CrossCorrelationInFourierDomain | Compute the cross-correlation of two images in the Fourier domain]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}}{{ITKDoxygenURL|VnlFFTComplexConjugateToRealImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/RealAndImaginaryToComplexImageFilter | Convert a real image and an imaginary image to a complex image]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|}<br />
<br />
==Utilities==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Utilities/SortIndex | Sort itk::Index]] || {{ITKDoxygenURL|Image}} || Lexicographic, ordering<br />
|-<br />
| [[ITK/Examples/Utilities/ReturnObjectFromFunction | Return an object from a function]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateImageWithSameType | Create another instance of an image]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Create another instance of the same type of object]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/PassImageToFunction | Pass an image to a function]] || {{ITKDoxygenURL|Image}}<br />
|-<br />
| [[ITK/Examples/Utilities/NumericSeriesFileNames | Create a list of file names]] || {{ITKDoxygenURL|NumericSeriesFileNames}} || <br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Copy a filter]] || {{ITKDoxygenURL|Object}} || Copy/duplicate a filter<br />
|-<br />
| [[ITK/Examples/Utilities/AzimuthElevationToCartesianTransform | Cartesian to AzimuthElevation and vice-versa]] || {{ITKDoxygenURL|AzimuthElevationToCartesianTransform}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/FixedArray | C-style array]] || {{ITKDoxygenURL|FixedArray}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/DeepCopy | Deep copy an image]] || || <br />
|-<br />
| [[ITK/Examples/Utilities/RandomPermutation | Permute a sequence of indices]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Utilities/MersenneTwisterRandomVariateGenerator | Random number generator]] || {{ITKDoxygenURL|MersenneTwisterRandomVariateGenerator}} || <br />
|-<br />
| [[ITK/Examples/Utilities/JetColormapFunctor | Map scalars into a jet colormap]] || {{ITKDoxygenURL|JetColormapFunctor}} || <br />
|-<br />
| [[ITK/Examples/Utilities/SimpleFilterWatcher | Monitor a filter]] || {{ITKDoxygenURL|SimpleFilterWatcher}} || See debug style information.<br />
|-<br />
| [[ITK/Examples/Utilities/TimeProbe | Time probe]] || {{ITKDoxygenURL|TimeProbe}} || Compute the time between points in code. Timer. Timing.<br />
|-<br />
| [[ITK/Examples/Utilities/ObserveEvent | Observe an event]] || {{ITKDoxygenURL|Command}} || <br />
|-<br />
| [[ITK/Examples/Utilities/VectorContainer | Vector container]] || {{ITKDoxygenURL|VectorContainer}} || <br />
|}<br />
<br />
==Statistics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/MovingHistogramImageFilter | Compute histograms in a sliding window.]] || {{ITKDoxygenURL|MovingHistogramImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterRGB | Compute a histogram from an RGB image.]] || {{ITKDoxygenURL|HistogramToImageFilterRGB}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterVectorImage | Compute a histogram from a itk::VectorImage.]] || {{ITKDoxygenURL|HistogramToImageFilterVectorImage}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterGrayscale | Compute a histogram from a grayscale image.]] || {{ITKDoxygenURL|HistogramToImageFilterGrayscale}} || <br />
|-<br />
| [[ITK/Examples/Statistics/Histogram | Compute a histogram from measurements.]] || {{ITKDoxygenURL|Histogram}} || <br />
|-<br />
| [[ITK/Examples/Statistics/StatisticsImageFilter | Compute min, max, variance and mean of an Image.]] || {{ITKDoxygenURL|StatisticsImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/GaussianDistribution | Create a Gaussian distribution]] || {{ITKDoxygenURL|GaussianDistribution}} || <br />
|-<br />
| [[ITK/Examples/Statistics/SampleToHistogramFilter | Create a histogram from a list of sample measurements]] || {{ITKDoxygenURL|SampleToHistogramFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ListSample | Create a list of sample measurements]] || {{ITKDoxygenURL|ListSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageToListSampleAdaptor | Create a list of samples from an image without duplicating the data]] || {{ITKDoxygenURL|ImageToListSampleAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Statistics/MembershipSample | Create a list of samples with associated class IDs]] || {{ITKDoxygenURL|MembershipSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ExpectationMaximizationMixtureModelEstimator_2D | 2D Gaussian Mixture Model Expectation Maximization]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || EM<br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_1D | 1D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_3D | 3D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTree | Spatial search]] || {{ITKDoxygenURL|KdTreeGenerator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ScalarImageKmeansImageFilter | Cluster the pixels in a greyscale image]] || {{ITKDoxygenURL|ScalarImageKmeansImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/NoiseImageFilter | Compute the local noise in an image]] || {{ITKDoxygenURL|NoiseImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageKmeansModelEstimator | Compute kmeans clusters of pixels in an image]] || {{ITKDoxygenURL|ImageKmeansModelEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKmeansEstimator | Compute kmeans clusters]] || {{ITKDoxygenURL|KdTreeBasedKmeansEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/TextureFeatures | Extract texture features using GLCM]] || {{ITKDoxygenURL|ScalarImageToCooccurrenceMatrixFilter}} || <br />
|}<br />
<br />
==Spatial Objects==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpatialObjects/SpatialObjectToImageFilter | Convert a spatial object to an image ]] || {{ITKDoxygenURL|SpatialObjectToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/EllipseSpatialObject | Ellipse ]] || {{ITKDoxygenURL|EllipseSpatialObject}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/LineSpatialObject| Line spatial object]] || {{ITKDoxygenURL|LineSpatialObject}}, {{ITKDoxygenURL|LineSpatialObjectPoint}} || Specify a piecewise-linear object by specifying points along the line.<br />
|-<br />
| [[ITK/Examples/SpatialObjects/PlaneSpatialObject| Plane spatial object]] || {{ITKDoxygenURL|PlaneSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/SpatialObjects/BlobSpatialObject | Blob ]] || {{ITKDoxygenURL|BlobSpatialObject}} ||<br />
|}<br />
<br />
==Inspection==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Inspection/CheckerBoardImageFilter | Combine two images by alternating blocks of a checkerboard pattern]] || {{ITKDoxygenURL|CheckerBoardImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Inspection/PixelInspection | Printing a pixel value to the console]] || [http://www.itk.org/Doxygen/html/classitk_1_1Image.html#ad424c945604f339130b4ffe81b99738eGetPixel GetPixel] ||<br />
|}<br />
<br />
==Metrics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Metrics/MeanSquaresImageToImageMetric | Compute the mean squares metric between two images ]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} ||<br />
|}<br />
==Image Registration==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Registration/WarpImageFilter | Warp one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|WarpImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Registration/LandmarkBasedTransformInitializer | Rigidly register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|LandmarkBasedTransformInitializer}} ||<br />
|-<br />
| [[ITK/Examples/Registration/DeformationFieldTransform | Register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|DeformationFieldTransform}} ||<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethod | A basic global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|TranslationTransform}} || Translation only transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodAffine | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|AffineTransform}} || Full affine transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodBSpline | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|BSplineDeformableTransform}} || BSpline transform.<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformation | Mutual Information ]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|TranslationTransform}} || Global registration by maximizing the mutual information and using a translation only transform<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformationAffine | Mutual Information Affine]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|AffineTransform}} || Global registration by maximizing the mutual information and using an affine transform<br />
|}<br />
<br />
==Image Segmentation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Segmentation/ContourExtractor2DImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|ContourExtractor2DImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/WatershedImageFilter| Watershed segmentation]] ||{{ITKDoxygenURL|WatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/MorphologicalWatershedImageFilter| Morphological Watershed segmentation]] ||{{ITKDoxygenURL|MorphologicalWatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/EstimatePCAModel | Compute a PCA shape model from a training sample]] || {{ITKDoxygenURL|ImagePCAShapeModelEstimator}} ||<br />
Estimate the principal modes of variation of a shape from a training sample. Useful for shape guide segmentation.<br />
|-<br />
| [[ITK/Examples/Segmentation/MeanShiftClustering | Mean shift clustering]] || {{ITKDoxygenURL|SampleMeanShiftClusteringFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/kMeansClustering | KMeans Clustering]] || ||<br />
|-<br />
| [[ITK/Examples/Segmentation/MultiphaseChanAndVeseSparseFieldLevelSetSegmentation | Multiphase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseSparseFieldLevelSetSegmentation | Single-phase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseDenseFieldLevelSetSegmentation | Single-phase Chan And Vese Dense Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseDenseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/WishList/VoronoiDiagram2DGenerator | Voronoi diagram]] || {{ITKDoxygenURL|VoronoiDiagram2DGenerator}}, {{ITKDoxygenURL|VoronoiDiagram2D}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConnectedComponentImageFilter | Label connected components in a binary image]] || {{ITKDoxygenURL|ConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScalarConnectedComponentImageFilter | Label connected components in a grayscale image]] || {{ITKDoxygenURL|ScalarConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RelabelComponentImageFilter | Assign contiguous labels to connected regions of an image]] || {{ITKDoxygenURL|RelabelComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelContourImageFilter | Label the contours of connected components]] || {{ITKDoxygenURL|LabelContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ConfidenceConnectedImageFilter | Segment pixels with similar statistics using connectivity ]] || {{ITKDoxygenURL|ConfidenceConnectedImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToLabelMapFilter | Convert an itk::Image consisting of labeled regions to a LabelMap ]] || <br />
{{ITKDoxygenURL|LabelImageToLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToShapeLabelMapFilter | Convert an itk::Image consisting of labeled regions to a ShapeLabelMap ]] || {{ITKDoxygenURL|LabelImageToShapeLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ExtractLargestConnectedComponentFromBinaryImage | Extract the largest connected component from a Binary Image ]] || <br />
||<br />
|}<br />
<br />
==Meshes==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Meshes/Decimation | Decimation]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/AddPointsAndEdges | Add points and edges]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshNormalFilter | Compute normals of a mesh]] || {{ITKDoxygenURL|QuadEdgeMeshNormalFilter}} ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshParameterizationFilter | Planar parameterization of a mesh]] || {{ITKDoxygenURL|ParameterizationQuadEdgeMeshFilter}} || Compute linear parameterization of a mesh homeomorphic to a disk on the plane<br />
|-<br />
| [[ITK/Examples/Meshes/ConvertToVTK | Convert an itk::Mesh to a vtkUnstructuredGrid]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/WishList/WriteMeshToVTP | Write an itk::Mesh to a vtp (vtkPolyData) file]] || {{ITKDoxygenURL|VTKPolyDataWriter}} ||<br />
|}<br />
<br />
==Need Demo==<br />
This section consists of examples which compile and work, but a good demonstration image must be selected and added.<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/NeedDemo/ImageProcessing/AdaptiveHistogramEqualizationImageFilter | Adaptive histogram equalization]] || {{ITKDoxygenURL|AdaptiveHistogramEqualizationImageFilter}} ||<br />
|}<br />
<br />
<br />
==Wish List==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Pipeline/DisconnectPipeline | DisconnectPipeline]] || <br />
|-<br />
| [[ITK/Examples/WishList/Iterators/ConditionalConstIterator | ConditionalConstIterator]] || {{ITKDoxygenURL|ConditionalConstIterator}} || <br />
|-<br />
| [[ITK/Examples/WishList/Statistics/ScalarImageToTextureFeaturesFilter | Compute texture features]] || [http://www.itk.org/Doxygen/html/classitk_1_1Statistics_1_1ScalarImageToTextureFeaturesFilter.html ScalarImageToTextureFeaturesFilter] || How to interpret the output?<br />
|-<br />
| [[ITK/Examples/WishList/LevelSets/SignedDanielssonDistanceMapImageFilter | Compute the signed distance function over an image]] || {{ITKDoxygenURL|SignedDanielssonDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorImageResampleImageFilter | Resample an itk::VectorImage]] || ||<br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/OtsuMultipleThresholdsCalculator | Compute Otsu thresholds]] || {{ITKDoxygenURL|OtsuMultipleThresholdsCalculator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/MaskedImageToHistogramFilter | Compute the histogram of a masked region of an image]] || {{ITKDoxygenURL|MaskedImageToHistogramFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/PointSet/BSplineScatteredDataPointSetToImageFilter | Fit a spline to a point set]] || {{ITKDoxygenURL|BSplineScatteredDataPointSetToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Morphology/BinaryPruningImageFilter | BinaryPruningImageFilter]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/GaussianMixtureModelComponent | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|GaussianMixtureModelComponent}} ||<br />
|-<br />
| [[ITK/Examples/WishList/LevenbergMarquart| LevenbergMarquart]] || || <br />
|-<br />
| [[ITK/Examples/WishList/IterativeClosestPoints| IterativeClosestPoints]] || || <br />
|-<br />
| [[ITK/Examples/WishList/Operators/AllOperators| Demonstrate all operators]] || {{ITKDoxygenURL|NeighborhoodOperator}} || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/ColorNormalizedCorrelation| Color Normalized Correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/SpatialObjects/ContourSpatialObject| ContourSpatialObject]] || {{ITKDoxygenURL|ContourSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/Broken/SimpleOperations/MetaDataDictionary| Store non-pixel associated data in an image]] || {{ITKDoxygenURL|MetaDataDictionary}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/LevelSets| Level Sets]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation//RegionGrowing| Region Growing]] || || <br />
|-<br />
| [[ITK/Examples/Meshes/Subdivision| Mesh subdivision]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation/OtsuThresholdImageFilter| Separate foreground and background using Otsu's method]] || {{ITKDoxygenURL|OtsuThresholdImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/SimpleContourExtractorImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|SimpleContourExtractorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/RGBToVectorImageAdaptor| Present an image of RGBPixel pixels as an image of vectors]] || {{ITKDoxygenURL|RGBToVectorImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DCirclesImageFilter| HoughTransform2DCirclesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DCirclesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DLinesImageFilter| HoughTransform2DLinesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DLinesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Matlab/MatlabToITK| Write data from Matlab in a format readable by ITK]] || || <br />
|-<br />
| [[ITK/Examples/Matlab/ITKToMatlab| Write data from ITK in a format readable by Matlab]] || || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/EdgePotentialImageFilter| Compute edge potential]] ||{{ITKDoxygenURL|EdgePotentialImageFilter}} || <br />
|}<br />
<br />
==Included in the ITK Repository==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Included/Registration| Image registration]] || || <br />
|}<br />
<br />
==Matlab==<br />
{{ITKExamplesTable}}<br />
<br />
|}<br />
<br />
==Developer Examples==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Developer/Exceptions | Throw an exception]] || || <br />
|-<br />
| [[ITK/Examples/Developer/ImageSource | Produce an image programmatically.]] || {{ITKDoxygenURL|ImageSource}} || Nothing in, image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilter | Filter an image]] || {{ITKDoxygenURL|ImageToImageFilter}} || Image in, same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/InplaceImageFilter | Filter an image without copying its data]] || {{ITKDoxygenURL|InPlaceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Developer/MultiThreadedImageFilter | Filter an image using multiple threads]] || {{ITKDoxygenURL|ImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Developer/OilPaintingImageFilter | Multi-threaded oil painting image filter]] || {{ITKDoxygenURL|ImageToImageFilter}} and {{ITKDoxygenURL|MinimumMaximumImageCalculator}} || A simple multi-threaded scenario (oil painting artistic filter). You can also use this class as-is (copy .h and .txx files into your project and use them).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputs | Write a filter with multiple inputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (same type), same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputsDifferentType | Write a filter with multiple inputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (different type), image (same type as first input) out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputs | Write a filter with multiple outputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (same type as first input).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputsDifferentType | Write a filter with multiple outputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (different types).<br />
|-<br />
| [[ITK/Examples/Developer/SetGetMacro | Get or set a member variable of an ITK class.]] || || SetMacro, GetMacro<br />
|-<br />
| [[ITK/Examples/Developer/OutputMacros | Output an error, a warning, or debug information.]] || || DebugMacro, ErrorMacro, WarningMacro<br />
|-<br />
| [[ITK/Examples/Developer/Minipipeline | MiniPipeline]] || || <br />
|}<br />
<br />
==Problems==<br />
===Small Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFilledImageFunctionConditionalIterator | Iterate over an image starting at a seed and following a rule for connectivity decisions]] || {{ITKDoxygenURL|FloodFilledImageFunctionConditionalIterator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFillIterator | Traverse a region using a flood fill iterator]] || {{ITKDoxygenURL|FloodFilledSpatialFunctionConditionalIterator}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/GradientOfVectorImage | Compute the gradient of a vector image]] || {{ITKDoxygenURL|GradientImageFilter}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_Image | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_1D | Compute distributions of samples using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || Someone please confirm that this outputs the mean and the variance (i.e. I used a standard deviation of 30 to create the samples and the second estimated parameter is near 1000 (~30^2) . Is this correct?)<br />
|-<br />
| [[ITK/Examples/Broken/EdgesAndGradients/CannyEdgeDetectionImageFilter | Find edges in an image]] || {{ITKDoxygenURL|CannyEdgeDetectionImageFilter}} || How to set a reasonable Threshold for the output edges?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ImageToHistogramFilter | Compute the histogram of an image]] || {{ITKDoxygenURL|Statistics_1_1ImageToHistogramFilter}} || The last entry of the red histogram should contain several values, but it is 0?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/KmeansModelEstimator | Classifying pixels using KMeans]] || {{ITKDoxygenURL|KmeansModelEstimator}} || How to apply the labels of the filter to the input image?<br />
|-<br />
| [[ITK/Examples/Broken/Images/RegionGrowImageFilter | Basic region growing]] || {{ITKDoxygenURL|RegionGrowImageFilter}} || Just getting started with demo...<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConnectedThresholdImageFilter | Find connected components in an image]] || {{ITKDoxygenURL|ConnectedThresholdImageFilter}} || Just need to finish it.<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConvertPixelBuffer | Convert an image from one type to another]] || {{ITKDoxygenURL|ConvertPixelBuffer}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/InPlace | In-place filtering of an image]] || {{ITKDoxygenURL|InPlaceImageFilter}} || This only works for filters which derive from itkInPlaceImageFilter<br />
|-<br />
| [[ITK/Examples/Broken/Images/VTKImageToImageFilter | Convert a VTK image to an ITK image]] || {{ITKDoxygenURL|VTKImageToImageFilter}} || Seems to expect an input image with only 1 component? (i.e. greyscale)<br />
|}<br />
<br />
===Big Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Images/MeanSquaresImageToImageMetric | Find the best position of the moving image in the fixed image.]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} || Output (0,0) is incorrect.<br />
|-<br />
| [[ITK/Examples/Broken/Images/GradientImageFilter | Compute and display the gradient of an image]] || {{ITKDoxygenURL|GradientImageFilter}} || Blank output on the screen (the filter works fine). There should be a "DisplayVectorImage" added to itkQuickView that draws vector glyphs at specified pixels of an image.<br />
|}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/MergeLabelMapFilter&diff=45214ITK/Examples/ImageProcessing/MergeLabelMapFilter2012-01-21T00:41:36Z<p>Ccagataybilgin: /* MergeLabelMapFilter.cxx */</p>
<hr />
<div>==MergeLabelMapFilter.cxx==<br />
<source lang="cpp"><br />
#include "itkBinaryImageToShapeLabelMapFilter.h"<br />
#include "itkMergeLabelMapFilter.h"<br />
<br />
int main(int argc, char* argv[])<br />
{<br />
typedef itk::Image<int, 3> ImageType;<br />
<br />
//Binary Image to Shape Label Map. <br />
typedef itk::BinaryImageToShapeLabelMapFilter<ImageType> BI2SLMType;<br />
typedef BI2SLMType::OutputImageType LabelMapType;<br />
typedef BI2SLMType::LabelObjectType LabelObjectType;<br />
<br />
typedef itk::MergeLabelMapFilter<LabelMapType> MergerType;<br />
MergerType::Pointer merger = MergerType::New();<br />
merger->SetMethod(MergerType::PACK);<br />
<br />
int noObjects = 4;<br />
<br />
for (int i = 1; i <= noObjects; i++)<br />
{<br />
LabelMapType::Pointer labelMap = LabelMapType::New();<br />
LabelObjectType::Pointer labelObject = LabelObjectType::New();<br />
<br />
labelObject->SetLabel(1);<br />
labelMap->AddLabelObject(labelObject);<br />
labelMap->Update();<br />
<br />
merger->SetInput(i - 1, labelMap);<br />
}<br />
<br />
merger->Update();<br />
std::cout << "number of objects: "<br />
<< merger->GetOutput()->GetNumberOfLabelObjects() << "\n";<br />
std::cout << "number of expected objects: " << noObjects << "\n";<br />
<br />
return EXIT_SUCCESS;<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|MergeLabelMapFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples&diff=44786ITK/Examples2012-01-12T18:29:39Z<p>Ccagataybilgin: /* Smoothing */</p>
<hr />
<div>These are fully independent, compilable examples, developed with these [[ITK/Examples/Goals|goals]] in mind. There is significant overlap in the examples, but they are each intended to illustrate a different concept and be fully stand alone compilable.<br />
Please add examples in your areas of expertise!<br />
You can checkout the entire set of examples from this repository: <br />
http://gitorious.org/itkwikiexamples/itkwikiexamples<br />
<pre>git clone git://gitorious.org/itkwikiexamples/itkwikiexamples.git ITKWikiExamples</pre><br />
<br />
==About the Examples==<br />
* [http://www.itk.org/Wiki/images/e/e6/ITK_Examples_Iowa_Meeting_2010_11-8-2010.odp Official announcement]<br />
===ItkVtkGlue===<br />
ITK and VTK are very separate toolkits - ITK for image processing and VTK for data visualization. It is often convenient to use the two together - namely, to display an ITK image on the screen. The ItkVtkGlue kit serves exactly this purpose. Also provided inside ItkVtkGlue is a QuickView class to allow a 2 line display of an ITK image.<br />
<br />
If you download the entire ITK Wiki Examples Collection, the ItkVtkGlue directory will be included and configured. If you wish to just build a few examples, then you will need to [http://gitorious.org/itkwikiexamples/itkwikiexamples/blobs/raw/143b4a80c6f5bbe44edbcbeccaa9c05b83042d65/ItkVtkGlue.tar.gz download ItkVtkGlue] and build it.<br />
<br />
===[[ITK/Examples/Instructions/ForUsers|Information for Wiki Examples Users]]===<br />
If you just want to use the Wiki Examples, [[ITK/Examples/Instructions/ForUsers|go here]]. You will learn how to search for examples, build a few examples and build all of the examples.<br />
<br />
===[[ITK/Examples/Instructions/ForDevelopers|Information for Wiki Examples Developers]]===<br />
If you want to contribute examples [[ITK/Examples/Instructions/ForDevelopers|go here]]. You will learn how to add a new example and the guidelines for writing an example.<br />
<br />
===[[ITK/Examples/Instructions/ForAdministrators|Information for Wiki Examples Administrators]]===<br />
If you are a Wiki Example Administrator or want to learn more about the process [[ITK/Examples/Instructions/ForAdministrators|go here]]. You will learn how the Wiki Examples repository is organized, how the repository is synced to the wiki and how to add new topics, tests and regression baselines.<br />
<br />
==Simple Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RequestedRegion | Apply a filter only to a specified region of an image ]] || || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/WidthHeight | Get the width and height of an image ]] || || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/VariableLengthVector | Variable length vector ]] || {{ITKDoxygenURL|VariableLengthVector}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TranslationTransform | Translate an image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|ResampleImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/NumericTraits | Get some basic information about a type]] || {{ITKDoxygenURL|NumericTraits}}|| Zero<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ScalarToRGBColormapImageFilter | Apply a color map to an image]] || {{ITKDoxygenURL|ScalarToRGBColormapImageFilter}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/CustomColormap | Create and apply a custom colormap]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TryCatch | Catch an ITK exception]] || || Try/Catch blocks<br />
|-<br />
| [[ITK/Examples/SimpleOperations/BresenhamLine | Get the points on a Bresenham line between two points]] || {{ITKDoxygenURL|BresenhamLine}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/Offset | Add an offset to a pixel index]] || {{ITKDoxygenURL|Offset}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenPoints | Distance between two points]] || {{ITKDoxygenURL|Point}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenIndices | Distance between two indices]] || {{ITKDoxygenURL|Point}}, {{ITKDoxygenURL|Index}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CreateVector | Create a vector]] || {{ITKDoxygenURL|Vector}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/GetNameOfClass | Get the name/type/class of an object ]] || || GetNameOfClass()<br />
|-<br />
| [[ITK/Examples/Images/Index | An object which holds the index of a pixel ]] || {{ITKDoxygenURL|Index}} || <br />
|-<br />
| [[ITK/Examples/Images/Size | An object which holds the size of an image ]] || {{ITKDoxygenURL|Size}} || <br />
|-<br />
| [[ITK/Examples/Images/ImageRegion | An object which holds the index (start) and size of a region of an image ]] || {{ITKDoxygenURL|ImageRegion}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/Transparency | Make part of an image transparent]] || {{ITKDoxygenURL|RGBAPixel}} || Transparency, RGBA, alpha<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionIntersection | Determine if one region is fully inside another region]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/PixelInsideRegion | Determine if a pixel is inside of a region]] || {{ITKDoxygenURL|ImageRegion}} || IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionOverlap | Determine the overlap of two regions]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, crop a region<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ImageDuplicator | Duplicate an image]] || {{ITKDoxygenURL|ImageDuplicator}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/RandomImageSource | Produce an image of noise]] || {{ITKDoxygenURL|RandomImageSource}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/SetPixels | Set specified pixels to specified values]] || {{ITKDoxygenURL|Image}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RGBPixel | Create an RGB image]] || {{ITKDoxygenURL|RGBPixel}} ||<br />
|}<br />
<br />
==Mathematical Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/CovariantVector | Create a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || This is the object which should be used to represent a mathematical vector.<br />
|-<br />
| [[ITK/Examples/Math/CovariantVectorNorm | Compute the norm of a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || In-place and non-inplace norms.<br />
|-<br />
| [[ITK/Examples/Math/Matrix | Matrix ]] || {{ITKDoxygenURL|Matrix}} || <br />
|-<br />
| [[ITK/Examples/Math/Pi | Mathematical constant pi = 3.14 ]] || {{ITKDoxygenURL|Math}} || <br />
|-<br />
| [[ITK/Examples/Math/DotProduct | Dot product (inner product) of two vectors ]] || {{ITKDoxygenURL|Vector}} || <br />
|}<br />
<br />
==Trigonometric Filters==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/Trig/SinImageFilter | Compute the sine of each pixel.]] || {{ITKDoxygenURL|SinImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Math/Trig/Atan2ImageFilter | Compute the arctangent of each pixel.]] || {{ITKDoxygenURL|Atan2ImageFilter}}<br />
|}<br />
<br />
==Image Functions==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Functions/NeighborhoodOperatorImageFunction | Multiply a kernel with an image at a particular location]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunction | GaussianBlurImageFunction ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunctionFilter | GaussianBlurImageFunctionFilter ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/MedianImageFunction| Compute the median of an image at a pixels (in a regular neighborhood)]] || {{ITKDoxygenURL|MedianImageFunction}} || <br />
|}<br />
<br />
==Point Set==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/PointSet/CreatePointSet | Create a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/ReadPointSet | Read a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/WritePointSet | Write a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/BoundingBox | Get the bounding box of a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|}<br />
<br />
==Input/Output (IO)==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/IO/ReadVectorImage| Read an image file with an unknown number of components]] || {{ITKDoxygenURL|ImageFileReader}},{{ITKDoxygenURL|VectorImage}} || <br />
|-<br />
| [[ITK/Examples/IO/ImportImageFilter| Convert a C-style array to an itkImage]] || {{ITKDoxygenURL|ImportImageFilter}} || <br />
|-<br />
| [[ITK/Examples/IO/ReadUnknownImageType | Read an image file without knowing its type before hand]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileWriter | Write an image]] || {{ITKDoxygenURL|ImageFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileReader | Read an image]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/TIFFImageIO | Write a TIFF image]] || {{ITKDoxygenURL|TIFFImageIO}} || This is a general demonstration of how to use a specific writer rather than relying on the ImageFileWriter to choose for you.<br />
|-<br />
| [[ITK/Examples/IO/ImageToVTKImageFilter | Display an ITK image]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileWriter | Write a transform to a file]] || {{ITKDoxygenURL|TransformFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileReader | Read a transform from a file]] || {{ITKDoxygenURL|TransformFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/VolumeFromSlices | Create a 3D volume from a series of 2D images]] || {{ITKDoxygenURL|ImageSeriesReader}} || Uses NumericSeriesFileNames to generate a list of file names<br />
|-<br />
| [[ITK/Examples/IO/itkVtkImageConvertDICOM | Uses a custom user matrix to align the image with DICOM physical space]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} || <br />
|}<br />
<br />
==DICOM==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/DICOM/ResampleDICOM | Resample a DICOM series]] || {{ITKDoxygenURL|GDCMImageIO}} || Resample a DICOM series with user-specified spacing.<br />
|}<br />
<br />
==Blob Detection, Labeling, and Properties==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ManuallyRemovingLabels | Remove labels from a LabelMap]] || {{ITKDoxygenURL|LabelMap}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ObjectByObjectLabelMapFilter | Apply an operation to every label object in a label map]] || {{ITKDoxygenURL|ObjectByObjectLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ShapeOpeningLabelMapFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|ShapeOpeningLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelShapeKeepNObjectsImageFilter | Keep only regions that rank above a certain level of a particular property]] || {{ITKDoxygenURL|LabelShapeKeepNObjectsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapOverlayImageFilter | Color labeled regions in an image]] || {{ITKDoxygenURL|LabelMapOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelGeometryImageFilter | Get geometric properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelGeometryImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelStatisticsImageFilter | Get statistical properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelStatisticsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/LabelMapContourOverlayImageFilter | Color the boundaries of labeled regions in an image]] || {{ITKDoxygenURL|LabelMapContourOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToLabelMapFilter | Label binary regions in an image]] || {{ITKDoxygenURL|BinaryImageToLabelMapFilter}} || Also demonstrates how to obtain which pixels belong to each label.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToShapeLabelMapFilter | Label binary regions in an image and get their properties]] || {{ITKDoxygenURL|BinaryImageToShapeLabelMapFilter}} || Region bounding box, centroid, etc.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapToLabelImageFilter | Convert a LabelMap to a normal image with different values representing each region]] || {{ITKDoxygenURL|LabelMapToLabelImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MergeLabelMapFilter | Merges several labelmaps]] || {{ITKDoxygenURL|MergeLabelMapFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelOverlayImageFilter | Overlay a LabelMap on an image]] || {{ITKDoxygenURL|LabelOverlayImageFilter}} || <br />
|}<br />
<br />
==Image Processing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThinningImageFilter | Skeletonize/thin an image]] || {{ITKDoxygenURL|BinaryThinningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScaleTransform | Scale an image]] || {{ITKDoxygenURL|ScaleTransform}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ResampleImageFilter | Resample (stretch or compress) an image]] || {{ITKDoxygenURL|ResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/MutualInformationImageToImageFilter | Compute the mutual information between two image]] || {{ITKDoxygenURL|MutualInformationImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianSharpeningImageFilter | Sharpen an image]] || {{ITKDoxygenURL|LaplacianSharpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/DivideImageFilter | Pixel-wise division of two images]] || {{ITKDoxygenURL|DivideImageFilter}} || Divide images<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ApproximateSignedDistanceMapImageFilter | Compute a distance map from objects in a binary image]] || {{ITKDoxygenURL|ApproximateSignedDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeToConstantImageFilter | Scale all pixels so that their sum is a specified constant]] || {{ITKDoxygenURL|NormalizeToConstantImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMinimaImageFilter | RegionalMinimaImageFilter]] || {{ITKDoxygenURL|RegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMaximaImageFilter | RegionalMaximaImageFilter]] || {{ITKDoxygenURL|RegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ZeroCrossingImageFilter| Find zero crossings in a signed image]] || {{ITKDoxygenURL|ZeroCrossingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RecursiveMultiResolutionPyramidImageFilter| Construct a multiresolution pyramid from an image]] || {{ITKDoxygenURL|RecursiveMultiResolutionPyramidImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddConstantToImageFilter| Add a constant to every pixel in an image]] || {{ITKDoxygenURL|AddImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractConstantFromImageFilter| Subtract a constant from every pixel in an image]] || {{ITKDoxygenURL|SubtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquareImageFilter| Square every pixel in an image]] || {{ITKDoxygenURL|SquareImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Upsampling| Upsampling an image]] || {{ITKDoxygenURL|BSplineInterpolateImageFunction}} {{ITKDoxygenURL|ResampleImageFilter}} || Interpolate missing pixels in order to upsample an image. Note this only works on scalar images.<br />
|-<br />
| [[ITK/Examples/Images/FlipImageFilter | Flip an image over specified axes]] || {{ITKDoxygenURL|FlipImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/VectorRescaleIntensityImageFilter | Apply a transformation to the magnitude of vector valued image pixels]] || {{ITKDoxygenURL|VectorRescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/NeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskNeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image that is non-zero in a mask]] || {{ITKDoxygenURL|MaskNeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianImageFilter | Compute the Laplacian of an image]] || {{ITKDoxygenURL|LaplacianImageFilter}} || Input image type must be double or float<br />
|-<br />
| [[ITK/Examples/Images/ConstantPadImageFilter | Pad an image with a constant value]] || {{ITKDoxygenURL|ConstantPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/MirrorPadImageFilter | Pad an image using mirroring over the boundaries]] || {{ITKDoxygenURL|MirrorPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/WrapPadImageFilter | Pad an image by wrapping]] || {{ITKDoxygenURL|WrapPadImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/IntensityWindowingImageFilter| IntensityWindowingImageFilter]] || {{ITKDoxygenURL|IntensityWindowingImageFilter}} || Apply a linear intensity transform from a specified input range to a specified output range.<br />
|-<br />
| [[ITK/Examples/Images/ShrinkImageFilter | Shrink an image]] || {{ITKDoxygenURL|ShrinkImageFilter}} || Downsample an image<br />
|-<br />
| [[ITK/Examples/Images/NormalizedCorrelationImageFilter | Normalized correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/NormalizedCorrelationImageFilterMasked | Normalized correlation of a masked image]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyByConstantImageFilter | Multiply every pixel in an image by a constant]] || {{ITKDoxygenURL|MultiplyImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquaredDifferenceImageFilter | Compute the squared difference of corresponding pixels in two images]] || {{ITKDoxygenURL|SquaredDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsoluteValueDifferenceImageFilter | Compute the absolute value of the difference of corresponding pixels in two images]] || {{ITKDoxygenURL|AbsoluteValueDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddPixelAccessor | Add a constant to every pixel without duplicating the image in memory (an accessor)]] || {{ITKDoxygenURL|AddPixelAccessor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMaximaImageFilter | ValuedRegionalMaximaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMinimaImageFilter | ValuedRegionalMinimaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaximumImageFilter | Pixel wise compare two input images and set the output pixel to their max]] || {{ITKDoxygenURL|MaximumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumImageFilter | Pixel wise compare two input images and set the output pixel to their min]] || {{ITKDoxygenURL|MinimumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AndImageFilter | Binary AND two images]] || {{ITKDoxygenURL|AndImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/OrImageFilter | Binary OR two images]] || {{ITKDoxygenURL|OrImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/XorImageFilter | Binary XOR (exclusive OR) two images]] || {{ITKDoxygenURL|XorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryNotImageFilter | Invert an image using the Binary Not operation]] || {{ITKDoxygenURL|BinaryNotImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Compose3DCovariantVectorImageFilter | Compose a vector image (with 3 components) from three scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/NthElementImageAdaptor | Extract a component/channel of an itkImage with pixels with multiple components]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || Use built in functionality to extract a component of an itkImage with CovariantVector components. Note this does not work for itkVectorImages - see VectorIndexSelectionCastImageFilter instead.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageAdaptorExtractVectorComponent | Present an image by first performing an operation]] || {{ITKDoxygenURL|ImageAdaptor}} || A demonstration of how to present an image pixel as a function of the pixel. In this example the functionality of NthElementImageAdaptor is demonstrated.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ProcessingNthImageElement | Process the nth component/element/channel of a vector image]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConvolutionImageFilter | Convolve an image with a kernel]] || {{ITKDoxygenURL|ConvolutionImageFilter}} || Convolution.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ExtractImageFilter | Crop an image by specifying the region to keep]] || {{ITKDoxygenURL|ExtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/CropImageFilter | Crop an image by specifying the region to throw away]] || {{ITKDoxygenURL|CropImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsImageFilter | Compute the absolute value of an image]] || {{ITKDoxygenURL|AbsImageFilter}} || magnitude<br />
|-<br />
| [[ITK/Examples/ImageProcessing/InvertIntensityImageFilter | Invert an image]] || {{ITKDoxygenURL|InvertIntensityImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskImageFilter | Apply a mask to an image]] || {{ITKDoxygenURL|MaskImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskNegatedImageFilter | Apply the inverse of a mask to an image]] || {{ITKDoxygenURL|MaskNegatedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SigmoidImageFilter | Pass image pixels through a sigmoid function]] || {{ITKDoxygenURL|SigmoidImageFilter}} || The qualitative description of how Alpha and Beta affect the function from the ITK Software Guide and the associated images would be nice to add to the doxygen.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|ThresholdImageFilter}} || The result is the original image but with the values below (or above) the threshold "clamped" to an output value.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|BinaryThresholdImageFilter}} || The result is a binary image (inside the threshold region or outside the threshold region).<br />
|-<br />
| [[ITK/Examples/ImageProcessing/UnaryFunctorImageFilter | Apply a custom operation to each pixel in an image]] || {{ITKDoxygenURL|UnaryFunctorImageFilter}} || Perform a custom operation on every pixel in an image. This example rotates the vector-valued pixels by 90 degrees.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilter | Apply a predefined operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilterCustom | Apply a custom operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || This example computes the squared difference between corresponding pixels.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumMaximumImageCalculator | Find the minimum and maximum value (and the position of the value) in an image]] || {{ITKDoxygenURL|MinimumMaximumImageCalculator}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddImageFilter | Add two images together]] || {{ITKDoxygenURL|AddImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractImageFilter | Subtract two images]] || {{ITKDoxygenURL|SubtractImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PasteImageFilter | Paste a part of one image into another image]] || {{ITKDoxygenURL|PasteImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_CreateVolume | Stack multiple 2D images into a 3D image]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_SideBySide | Tile multiple images side by side]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyImageFilter | Multiply two images together]] || {{ITKDoxygenURL|MultiplyImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionOfInterestImageFilter | Extract a portion of an image (region of interest)]] || {{ITKDoxygenURL|RegionOfInterestImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RescaleIntensityImageFilter | Rescale the intensity values of an image to a specified range]] || {{ITKDoxygenURL|RescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeImageFilter | Normalize an image]] || {{ITKDoxygenURL|NormalizeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/CastImageFilter | Cast an image from one type to another]] || {{ITKDoxygenURL|CastImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ClampImageFilter | Cast an image from one type to another but clamp to the output value range]] || {{ITKDoxygenURL|ClampImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PermuteAxesImageFilter | Switch the axes of an image]] || {{ITKDoxygenURL|PermuteAxesImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LinearInterpolateImageFunction | Linearly interpolate a position in an image]] || {{ITKDoxygenURL|LinearInterpolateImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/HammingWindowFunction | HammingWindowFunction]] || {{ITKDoxygenURL|HammingWindowFunction}} ||<br />
|}<br />
<br />
==Vector Images==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorMagnitudeImageFilter | Compute the magnitude of each pixel in a vector image to produce a magnitude image]] || {{ITKDoxygenURL|VectorMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImage | Create a vector image]] || {{ITKDoxygenURL|VectorImage}} || An image with an ND vector at each pixel<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Create a vector image from a collection of scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || Combine, layer<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImageToImageAdaptor | View a component of a vector image as if it were a scalar image]] || {{ITKDoxygenURL|VectorImageToImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/VectorImages/VectorIndexSelectionCastImageFilter | Extract a component/channel of a vector image]] || {{ITKDoxygenURL|VectorIndexSelectionCastImageFilter}} || This works with VectorImage as well as Image<Vector><br />
|-<br />
| [[ITK/Examples/VectorImages/VectorResampleImageFilter | Translate a vector image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|VectorResampleImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/JoinImageFilter | Join images, stacking their components]] || {{ITKDoxygenURL|JoinImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Stack scalar images into a VectorImage]] || {{ITKDoxygenURL|ImageToVectorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/NeighborhoodIterator | NeighborhoodIterator on a VectorImage]] || {{ITKDoxygenURL|VectorImage}} {{ITKDoxygenURL|NeighborhoodIterator}}||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorCastImageFilter | Cast a VectorImage to another type of VectorImage]] || {{ITKDoxygenURL|VectorImage}} ||<br />
|}<br />
<br />
==Iterating Over (Traversing) An Image==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator_Manual | Iterate over a region of an image with a shaped neighborhood]] || Create the shape manually {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator | Iterate over a region of an image with a shaped neighborhood]] || Create the shape from a StructuringElement {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionExclusionConstIteratorWithIndex | Iterator over an image skipping a specified region]] || {{ITKDoxygenURL|ImageRegionExclusionConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomConstIteratorWithIndex | Randomly select pixels from a region of an image]] || {{ITKDoxygenURL|ImageRandomConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomNonRepeatingConstIteratorWithIndex | Randomly select pixels from a region of an image without replacement]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/LineIterator | Iterate over a line through an image]] || {{ITKDoxygenURL|LineIterator}} || Walks a Bresenham line through an image (with write access)<br />
|-<br />
| [[ITK/Examples/Iterators/LineConstIterator | Iterate over a line through an image without write access]] || {{ITKDoxygenURL|LineConstIterator}} || Walks a Bresenham line through an image (without write access)<br />
|-<br />
| [[ITK/Examples/Iterators/ImageBoundaryFacesCalculator | Iterate over the central region (non-boundary) separately from the face-regions (boundary)]] || {{ITKDoxygenURL|ImageBoundaryFacesCalculator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/NeighborhoodIterator | Iterate over a region of an image with a neighborhood (with write access)]] || {{ITKDoxygenURL|NeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstNeighborhoodIterator | Iterate over a region of an image with a neighborhood (without write access)]] || {{ITKDoxygenURL|ConstNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIterator | Iterate over a region of an image (with write access)]] || {{ITKDoxygenURL|ImageRegionIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIterator | Iterate over a region of an image (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstantBoundaryCondition | Make out of bounds pixels return a constant value]] || {{ITKDoxygenURL|ConstantBoundaryCondition}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (with write access)]] || {{ITKDoxygenURL|ImageRegionIteratorWithIndex}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIteratorWithIndex}} ||<br />
|}<br />
<br />
==Kernels==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Operators/GaussianOperator | Create a Gaussian kernel]] || {{ITKDoxygenURL|GaussianOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/GaussianDerivativeOperator | Create a Gaussian derivative kernel]] || {{ITKDoxygenURL|GaussianDerivativeOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/LaplacianOperator | Create a Laplacian kernel]] || {{ITKDoxygenURL|LaplacianOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/DerivativeOperator | Create a derivative kernel]] || {{ITKDoxygenURL|DerivativeOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/SobelOperator | Create the Sobel kernel]] || {{ITKDoxygenURL|SobelOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/ForwardDifferenceOperator | Create a forward difference kernel]] || {{ITKDoxygenURL|ForwardDifferenceOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/BackwardDifferenceOperator | Create a backward difference kernel]] || {{ITKDoxygenURL|BackwardDifferenceOperator}} || <br />
<br />
|}<br />
<br />
==Image Edges, Gradients, and Derivatives==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/SobelEdgeDetectionImageFilter | SobelEdgeDetectionImageFilter]] || {{ITKDoxygenURL|SobelEdgeDetectionImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/DerivativeImageFilter | Compute the derivative of an image in a particular direction]] || {{ITKDoxygenURL|DerivativeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientRecursiveGaussianImageFilter| Compute the gradient of an image by convolution with the first derivative of a Gaussian]] || {{ITKDoxygenURL|GradientRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeRecursiveGaussianImageFilter | Find the gradient magnitude of the image first smoothed with a Gaussian kernel]] || {{ITKDoxygenURL|GradientMagnitudeRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/RecursiveGaussianImageFilter | Find higher derivatives of an image]] || {{ITKDoxygenURL|RecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryContourImageFilter | Extract the boundaries of connected regions in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} || Blob boundary, border<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryBoundaries | Extract the inner and outer boundaries of blobs in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeImageFilter | Compute the gradient magnitude image]] || {{ITKDoxygenURL|GradientMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/LaplacianRecursiveGaussianImageFilter | Compute the Laplacian of Gaussian (LoG) of an image]] || {{ITKDoxygenURL|LaplacianRecursiveGaussianImageFilter}} ||<br />
|}<br />
<br />
==Smoothing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Smoothing/AntiAliasBinaryImageFilter | Anti alias a binary image]] || {{ITKDoxygenURL|AntiAliasBinaryImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinaryMinMaxCurvatureFlowImageFilter | BinaryMinMaxCurvatureFlow a binary image]] || {{ITKDoxygenURL|BinaryMinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MeanImageFilter | Mean filter an image]] || {{ITKDoxygenURL|MeanImageFilter}} || Replace each pixel by the mean of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/MedianImageFilter | Median filter an image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/RGBMedianImageFilter | Median filter an RGB image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/DiscreteGaussianImageFilter | Smooth an image with a discrete Gaussian filter]] || {{ITKDoxygenURL|DiscreteGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinomialBlurImageFilter | Blur an image]] || {{ITKDoxygenURL|BinomialBlurImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BilateralImageFilter | Bilateral filter an image]] || {{ITKDoxygenURL|BilateralImageFilter}} || Edge preserving smoothing.<br />
|-<br />
| [[ITK/Examples/Smoothing/CurvatureFlowImageFilter | Smooth an image using curvature flow]] || {{ITKDoxygenURL|CurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MinMaxCurvatureFlowImageFilter | Smooth an image using min/max curvature flow]] || {{ITKDoxygenURL|MinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/SmoothingRecursiveGaussianImageFilter | Gaussian smoothing that works with image adaptors]] || {{ITKDoxygenURL|SmoothingRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/VectorGradientAnisotropicDiffusionImageFilter | Smooth an image while preserving edges]] || {{ITKDoxygenURL|VectorGradientAnisotropicDiffusionImageFilter}} || Anisotropic diffusion.<br />
|}<br />
<br />
==Morphology==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Morphology/BinaryErodeImageFilter | Erode a binary image]] || {{ITKDoxygenURL|BinaryErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryDilateImageFilter | Dilate a binary image]] || {{ITKDoxygenURL|BinaryDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryPruningImageFilter | Prune a binary image]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalOpeningImageFilter | Opening a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalOpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalClosingImageFilter | Closing a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalClosingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleDilateImageFilter | Dilate a grayscale image]] || {{ITKDoxygenURL|GrayscaleDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleErodeImageFilter | Erode a grayscale image]] || {{ITKDoxygenURL|GrayscaleErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/FlatStructuringElement | Erode a binary image using a flat (box) structuring element]] || {{ITKDoxygenURL|FlatStructuringElement}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryBallStructuringElement | An elliptical structuring element]] || {{ITKDoxygenURL|BinaryBallStructuringElement}} || <br />
|}<br />
<br />
==Curves==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Curves/ContourMeanDistanceImageFilter | Compute the mean distance between all points of two curves]] || {{ITKDoxygenURL|ContourMeanDistanceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Curves/PolyLineParametricPath | A data structure for a piece-wise linear curve]] || {{ITKDoxygenURL|PolyLineParametricPath}} || <br />
|}<br />
<br />
==Spectral Analysis==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/VnlFFTRealToComplexConjugateImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/CrossCorrelationInFourierDomain | Compute the cross-correlation of two images in the Fourier domain]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}}{{ITKDoxygenURL|VnlFFTComplexConjugateToRealImageFilter}} || || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/RealAndImaginaryToComplexImageFilter | Convert a real image and an imaginary image to a complex image]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|}<br />
<br />
==Utilities==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Utilities/CreateImageWithSameType | Create another instance of an image]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Create another instance of the same type of object]] || ||<br />
|-<br />
| [[ITK/Examples/Broken/Utilities/NonSmartPointers | Using non-smart pointers]] || {{ITKDoxygenURL|Image}}<br />
|-<br />
| [[ITK/Examples/Utilities/NumericSeriesFileNames | Create a list of file names]] || {{ITKDoxygenURL|NumericSeriesFileNames}} || <br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Copy a filter]] || {{ITKDoxygenURL|Object}} || Copy/duplicate a filter<br />
|-<br />
| [[ITK/Examples/Utilities/AzimuthElevationToCartesianTransform | Cartesian to AzimuthElevation and vice-versa]] || {{ITKDoxygenURL|AzimuthElevationToCartesianTransform}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/FixedArray | C-style array]] || {{ITKDoxygenURL|FixedArray}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/DeepCopy | Deep copy an image]] || || <br />
|-<br />
| [[ITK/Examples/Utilities/RandomPermutation | Permute a sequence of indices]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Utilities/MersenneTwisterRandomVariateGenerator | Random number generator]] || {{ITKDoxygenURL|MersenneTwisterRandomVariateGenerator}} || <br />
|-<br />
| [[ITK/Examples/Utilities/JetColormapFunctor | Map scalars into a jet colormap]] || {{ITKDoxygenURL|JetColormapFunctor}} || <br />
|-<br />
| [[ITK/Examples/Utilities/SimpleFilterWatcher | Monitor a filter]] || {{ITKDoxygenURL|SimpleFilterWatcher}} || See debug style information.<br />
|-<br />
| [[ITK/Examples/Utilities/TimeProbe | Time probe]] || {{ITKDoxygenURL|TimeProbe}} || Compute the time between points in code. Timer. Timing.<br />
|-<br />
| [[ITK/Examples/Utilities/ObserveEvent | Observe an event]] || {{ITKDoxygenURL|Command}} || <br />
|-<br />
| [[ITK/Examples/Utilities/VectorContainer | Vector container]] || {{ITKDoxygenURL|VectorContainer}} || <br />
|}<br />
<br />
==Statistics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/MovingHistogramImageFilter | Compute histograms in a sliding window.]] || {{ITKDoxygenURL|MovingHistogramImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterRGB | Compute a histogram from an RGB image.]] || {{ITKDoxygenURL|HistogramToImageFilterRGB}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterVectorImage | Compute a histogram from a itk::VectorImage.]] || {{ITKDoxygenURL|HistogramToImageFilterVectorImage}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterGrayscale | Compute a histogram from a grayscale image.]] || {{ITKDoxygenURL|HistogramToImageFilterGrayscale}} || <br />
|-<br />
| [[ITK/Examples/Statistics/Histogram | Compute a histogram from measurements.]] || {{ITKDoxygenURL|Histogram}} || <br />
|-<br />
| [[ITK/Examples/Statistics/StatisticsImageFilter | Compute min, max, variance and mean of an Image.]] || {{ITKDoxygenURL|StatisticsImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/GaussianDistribution | Create a Gaussian distribution]] || {{ITKDoxygenURL|GaussianDistribution}} || <br />
|-<br />
| [[ITK/Examples/Statistics/SampleToHistogramFilter | Create a histogram from a list of sample measurements]] || {{ITKDoxygenURL|SampleToHistogramFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ListSample | Create a list of sample measurements]] || {{ITKDoxygenURL|ListSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageToListSampleAdaptor | Create a list of samples from an image without duplicating the data]] || {{ITKDoxygenURL|ImageToListSampleAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Statistics/MembershipSample | Create a list of samples with associated class IDs]] || {{ITKDoxygenURL|MembershipSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ExpectationMaximizationMixtureModelEstimator_2D | 2D Gaussian Mixture Model Expectation Maximization]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || EM<br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_1D | 1D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_3D | 3D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTree | Spatial search]] || {{ITKDoxygenURL|KdTreeGenerator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ScalarImageKmeansImageFilter | Cluster the pixels in a greyscale image]] || {{ITKDoxygenURL|ScalarImageKmeansImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/NoiseImageFilter | Compute the local noise in an image]] || {{ITKDoxygenURL|NoiseImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageKmeansModelEstimator | Compute kmeans clusters of pixels in an image]] || {{ITKDoxygenURL|ImageKmeansModelEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKmeansEstimator | Compute kmeans clusters]] || {{ITKDoxygenURL|KdTreeBasedKmeansEstimator}} || <br />
|}<br />
<br />
==Spatial Objects==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpatialObjects/SpatialObjectToImageFilter | Convert a spatial object to an image ]] || {{ITKDoxygenURL|SpatialObjectToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/EllipseSpatialObject | Ellipse ]] || {{ITKDoxygenURL|EllipseSpatialObject}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/LineSpatialObject| Line spatial object]] || {{ITKDoxygenURL|LineSpatialObject}}, {{ITKDoxygenURL|LineSpatialObjectPoint}} || Specify a piecewise-linear object by specifying points along the line.<br />
|-<br />
| [[ITK/Examples/SpatialObjects/PlaneSpatialObject| Plane spatial object]] || {{ITKDoxygenURL|PlaneSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/SpatialObjects/BlobSpatialObject | Blob ]] || {{ITKDoxygenURL|BlobSpatialObject}} ||<br />
|}<br />
<br />
==Inspection==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Inspection/CheckerBoardImageFilter | Combine two images by alternating blocks of a checkerboard pattern]] || {{ITKDoxygenURL|CheckerBoardImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Inspection/PixelInspection | Printing a pixel value to the console]] || [http://www.itk.org/Doxygen/html/classitk_1_1Image.html#ad424c945604f339130b4ffe81b99738eGetPixel GetPixel] ||<br />
|}<br />
<br />
==Metrics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Metrics/MeanSquaresImageToImageMetric | Compute the mean squares metric between two images ]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} ||<br />
|}<br />
==Image Registration==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Registration/WarpImageFilter | Warp one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|WarpImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Registration/LandmarkBasedTransformInitializer | Rigidly register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|LandmarkBasedTransformInitializer}} ||<br />
|-<br />
| [[ITK/Examples/Registration/DeformationFieldTransform | Register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|DeformationFieldTransform}} ||<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethod | A basic global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|TranslationTransform}} || Translation only transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodAffine | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|AffineTransform}} || Full affine transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodBSpline | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|BSplineDeformableTransform}} || BSpline transform.<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformation | Mutual Information ]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|TranslationTransform}} || Global registration by maximizing the mutual information and using a translation only transform<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformationAffine | Mutual Information Affine]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|AffineTransform}} || Global registration by maximizing the mutual information and using an affine transform<br />
|}<br />
<br />
==Image Segmentation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Segmentation/ContourExtractor2DImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|ContourExtractor2DImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/WatershedImageFilter| Watershed segmentation]] ||{{ITKDoxygenURL|WatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/MorphologicalWatershedImageFilter| Morphological Watershed segmentation]] ||{{ITKDoxygenURL|MorphologicalWatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/EstimatePCAModel | Compute a PCA shape model from a training sample]] || {{ITKDoxygenURL|ImagePCAShapeModelEstimator}} ||<br />
Estimate the principal modes of variation of a shape from a training sample. Useful for shape guide segmentation.<br />
|-<br />
| [[ITK/Examples/Segmentation/MeanShiftClustering | Mean shift clustering]] || {{ITKDoxygenURL|SampleMeanShiftClusteringFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/kMeansClustering | KMeans Clustering]] || ||<br />
|-<br />
| [[ITK/Examples/Segmentation/MultiphaseChanAndVeseSparseFieldLevelSetSegmentation | Multiphase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseSparseFieldLevelSetSegmentation | Single-phase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseDenseFieldLevelSetSegmentation | Single-phase Chan And Vese Dense Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseDenseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/WishList/VoronoiDiagram2DGenerator | Voronoi diagram]] || {{ITKDoxygenURL|VoronoiDiagram2DGenerator}}, {{ITKDoxygenURL|VoronoiDiagram2D}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConnectedComponentImageFilter | Label connected components in a binary image]] || {{ITKDoxygenURL|ConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScalarConnectedComponentImageFilter | Label connected components in a grayscale image]] || {{ITKDoxygenURL|ScalarConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RelabelComponentImageFilter | Assign contiguous labels to connected regions of an image]] || {{ITKDoxygenURL|RelabelComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelContourImageFilter | Label the contours of connected components]] || {{ITKDoxygenURL|LabelContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ConfidenceConnectedImageFilter | Segment pixels with similar statistics using connectivity ]] || {{ITKDoxygenURL|ConfidenceConnectedImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToLabelMapFilter | Convert an itk::Image consisting of labeled regions to a LabelMap ]] || <br />
{{ITKDoxygenURL|LabelImageToLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToShapeLabelMapFilter | Convert an itk::Image consisting of labeled regions to a ShapeLabelMap ]] || {{ITKDoxygenURL|LabelImageToShapeLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ExtractLargestConnectedComponentFromBinaryImage | Extract the largest connected component from a Binary Image ]] || <br />
||<br />
|}<br />
<br />
==Meshes==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Meshes/Decimation | Decimation]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/AddPointsAndEdges | Add points and edges]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshNormalFilter | Compute normals of a mesh]] || {{ITKDoxygenURL|QuadEdgeMeshNormalFilter}} ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshParameterizationFilter | Planar parameterization of a mesh]] || {{ITKDoxygenURL|ParameterizationQuadEdgeMeshFilter}} || Compute linear parameterization of a mesh homeomorphic to a disk on the plane<br />
|-<br />
| [[ITK/Examples/Meshes/ConvertToVTK | Convert an itk::Mesh to a vtkUnstructuredGrid]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/WishList/WriteMeshToVTP | Write an itk::Mesh to a vtp (vtkPolyData) file]] || {{ITKDoxygenURL|VTKPolyDataWriter}} ||<br />
|}<br />
<br />
==Need Demo==<br />
This section consists of examples which compile and work, but a good demonstration image must be selected and added.<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/NeedDemo/ImageProcessing/AdaptiveHistogramEqualizationImageFilter | Adaptive histogram equalization]] || {{ITKDoxygenURL|AdaptiveHistogramEqualizationImageFilter}} ||<br />
|}<br />
<br />
<br />
==Wish List==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/ScalarImageToTextureFeaturesFilter | Compute texture features]] || {{ITKDoxygenURL|ScalarImageToTextureFeaturesFilter}} || How to interpret the output?<br />
|-<br />
| [[ITK/Examples/WishList/LevelSets/SignedDanielssonDistanceMapImageFilter | Compute the signed distance function over an image]] || {{ITKDoxygenURL|SignedDanielssonDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorImageResampleImageFilter | Resample an itk::VectorImage]] || ||<br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/OtsuMultipleThresholdsCalculator | Compute Otsu thresholds]] || {{ITKDoxygenURL|OtsuMultipleThresholdsCalculator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/MaskedImageToHistogramFilter | Compute the histogram of a masked region of an image]] || {{ITKDoxygenURL|MaskedImageToHistogramFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/PointSet/BSplineScatteredDataPointSetToImageFilter | Fit a spline to a point set]] || {{ITKDoxygenURL|BSplineScatteredDataPointSetToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Morphology/BinaryPruningImageFilter | BinaryPruningImageFilter]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/GaussianMixtureModelComponent | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|GaussianMixtureModelComponent}} ||<br />
|-<br />
| [[ITK/Examples/WishList/LevenbergMarquart| LevenbergMarquart]] || || <br />
|-<br />
| [[ITK/Examples/WishList/IterativeClosestPoints| IterativeClosestPoints]] || || <br />
|-<br />
| [[ITK/Examples/WishList/Operators/AllOperators| Demonstrate all operators]] || {{ITKDoxygenURL|NeighborhoodOperator}} || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/ColorNormalizedCorrelation| Color Normalized Correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/SpatialObjects/ContourSpatialObject| ContourSpatialObject]] || {{ITKDoxygenURL|ContourSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/Broken/SimpleOperations/MetaDataDictionary| Store non-pixel associated data in an image]] || {{ITKDoxygenURL|MetaDataDictionary}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/LevelSets| Level Sets]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation//RegionGrowing| Region Growing]] || || <br />
|-<br />
| [[ITK/Examples/Meshes/Subdivision| Mesh subdivision]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation/OtsuThresholdImageFilter| Separate foreground and background using Otsu's method]] || {{ITKDoxygenURL|OtsuThresholdImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/SimpleContourExtractorImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|SimpleContourExtractorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/RGBToVectorImageAdaptor| Present an image of RGBPixel pixels as an image of vectors]] || {{ITKDoxygenURL|RGBToVectorImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DCirclesImageFilter| HoughTransform2DCirclesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DCirclesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DLinesImageFilter| HoughTransform2DLinesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DLinesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Matlab/MatlabToITK| Write data from Matlab in a format readable by ITK]] || || <br />
|-<br />
| [[ITK/Examples/Matlab/ITKToMatlab| Write data from ITK in a format readable by Matlab]] || || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/EdgePotentialImageFilter| Compute edge potential]] ||{{ITKDoxygenURL|EdgePotentialImageFilter}} || <br />
|}<br />
<br />
==Included in the ITK Repository==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Included/Registration| Image registration]] || || <br />
|}<br />
<br />
==Matlab==<br />
{{ITKExamplesTable}}<br />
<br />
|}<br />
<br />
==Developer Examples==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Developer/Exceptions | Throw an exception]] || || <br />
|-<br />
| [[ITK/Examples/Developer/ImageSource | Produce an image programmatically.]] || {{ITKDoxygenURL|ImageSource}} || Nothing in, image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilter | Filter an image]] || {{ITKDoxygenURL|ImageToImageFilter}} || Image in, same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/OilPaintingImageFilter | Multi-threaded oil painting image filter]] || {{ITKDoxygenURL|ImageToImageFilter}} and {{ITKDoxygenURL|MinimumMaximumImageCalculator}} || A simple multi-threaded scenario (oil painting artistic filter). You can also use this class as-is (copy .h and .txx files into your project and use them).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputs | Write a filter with multiple inputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (same type), same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputsDifferentType | Write a filter with multiple inputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (different type), image (same type as first input) out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputs | Write a filter with multiple outputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (same type as first input).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputsDifferentType | Write a filter with multiple outputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (different types).<br />
|-<br />
| [[ITK/Examples/Developer/SetGetMacro | Get or set a member variable of an ITK class.]] || || SetMacro, GetMacro<br />
|-<br />
| [[ITK/Examples/Developer/OutputMacros | Output an error, a warning, or debug information.]] || || DebugMacro, ErrorMacro, WarningMacro<br />
|}<br />
<br />
==Problems==<br />
===Small Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFilledImageFunctionConditionalIterator | Iterate over an image starting at a seed and following a rule for connectivity decisions]] || {{ITKDoxygenURL|FloodFilledImageFunctionConditionalIterator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFillIterator | Traverse a region using a flood fill iterator]] || {{ITKDoxygenURL|FloodFilledSpatialFunctionConditionalIterator}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/GradientOfVectorImage | Compute the gradient of a vector image]] || {{ITKDoxygenURL|GradientImageFilter}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_Image | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_1D | Compute distributions of samples using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || Someone please confirm that this outputs the mean and the variance (i.e. I used a standard deviation of 30 to create the samples and the second estimated parameter is near 1000 (~30^2) . Is this correct?)<br />
|-<br />
| [[ITK/Examples/Broken/EdgesAndGradients/CannyEdgeDetectionImageFilter | Find edges in an image]] || {{ITKDoxygenURL|CannyEdgeDetectionImageFilter}} || How to set a reasonable Threshold for the output edges?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ImageToHistogramFilter | Compute the histogram of an image]] || {{ITKDoxygenURL|Statistics_1_1ImageToHistogramFilter}} || The last entry of the red histogram should contain several values, but it is 0?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/KmeansModelEstimator | Classifying pixels using KMeans]] || {{ITKDoxygenURL|KmeansModelEstimator}} || How to apply the labels of the filter to the input image?<br />
|-<br />
| [[ITK/Examples/Broken/Images/RegionGrowImageFilter | Basic region growing]] || {{ITKDoxygenURL|RegionGrowImageFilter}} || Just getting started with demo...<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConnectedThresholdImageFilter | Find connected components in an image]] || {{ITKDoxygenURL|ConnectedThresholdImageFilter}} || Just need to finish it.<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConvertPixelBuffer | Convert an image from one type to another]] || {{ITKDoxygenURL|ConvertPixelBuffer}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/InPlace | In-place filtering of an image]] || {{ITKDoxygenURL|InPlaceImageFilter}} || This only works for filters which derive from itkInPlaceImageFilter<br />
|-<br />
| [[ITK/Examples/Broken/Images/VTKImageToImageFilter | Convert a VTK image to an ITK image]] || {{ITKDoxygenURL|VTKImageToImageFilter}} || Seems to expect an input image with only 1 component? (i.e. greyscale)<br />
|}<br />
<br />
===Big Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Images/MeanSquaresImageToImageMetric | Find the best position of the moving image in the fixed image.]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} || Output (0,0) is incorrect.<br />
|-<br />
| [[ITK/Examples/Broken/Images/GradientImageFilter | Compute and display the gradient of an image]] || {{ITKDoxygenURL|GradientImageFilter}} || Blank output on the screen (the filter works fine). There should be a "DisplayVectorImage" added to itkQuickView that draws vector glyphs at specified pixels of an image.<br />
|}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=File:GaussianDerivativeOperatorCoefficients.cpp&diff=44785File:GaussianDerivativeOperatorCoefficients.cpp2012-01-12T18:20:35Z<p>Ccagataybilgin: uploaded a new version of &quot;File:GaussianDerivativeOperatorCoefficients.cpp&quot;</p>
<hr />
<div></div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=File:GaussianDerivativeOperatorCoefficients.cpp&diff=44784File:GaussianDerivativeOperatorCoefficients.cpp2012-01-12T18:15:17Z<p>Ccagataybilgin: uploaded a new version of &quot;File:GaussianDerivativeOperatorCoefficients.cpp&quot;</p>
<hr />
<div></div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=File:GaussianDerivativeOperatorCoefficients.cpp&diff=44783File:GaussianDerivativeOperatorCoefficients.cpp2012-01-12T18:14:00Z<p>Ccagataybilgin: </p>
<hr />
<div></div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples&diff=44782ITK/Examples2012-01-12T18:12:50Z<p>Ccagataybilgin: /* Smoothing */</p>
<hr />
<div>These are fully independent, compilable examples, developed with these [[ITK/Examples/Goals|goals]] in mind. There is significant overlap in the examples, but they are each intended to illustrate a different concept and be fully stand alone compilable.<br />
Please add examples in your areas of expertise!<br />
You can checkout the entire set of examples from this repository: <br />
http://gitorious.org/itkwikiexamples/itkwikiexamples<br />
<pre>git clone git://gitorious.org/itkwikiexamples/itkwikiexamples.git ITKWikiExamples</pre><br />
<br />
==About the Examples==<br />
* [http://www.itk.org/Wiki/images/e/e6/ITK_Examples_Iowa_Meeting_2010_11-8-2010.odp Official announcement]<br />
===ItkVtkGlue===<br />
ITK and VTK are very separate toolkits - ITK for image processing and VTK for data visualization. It is often convenient to use the two together - namely, to display an ITK image on the screen. The ItkVtkGlue kit serves exactly this purpose. Also provided inside ItkVtkGlue is a QuickView class to allow a 2 line display of an ITK image.<br />
<br />
If you download the entire ITK Wiki Examples Collection, the ItkVtkGlue directory will be included and configured. If you wish to just build a few examples, then you will need to [http://gitorious.org/itkwikiexamples/itkwikiexamples/blobs/raw/143b4a80c6f5bbe44edbcbeccaa9c05b83042d65/ItkVtkGlue.tar.gz download ItkVtkGlue] and build it.<br />
<br />
===[[ITK/Examples/Instructions/ForUsers|Information for Wiki Examples Users]]===<br />
If you just want to use the Wiki Examples, [[ITK/Examples/Instructions/ForUsers|go here]]. You will learn how to search for examples, build a few examples and build all of the examples.<br />
<br />
===[[ITK/Examples/Instructions/ForDevelopers|Information for Wiki Examples Developers]]===<br />
If you want to contribute examples [[ITK/Examples/Instructions/ForDevelopers|go here]]. You will learn how to add a new example and the guidelines for writing an example.<br />
<br />
===[[ITK/Examples/Instructions/ForAdministrators|Information for Wiki Examples Administrators]]===<br />
If you are a Wiki Example Administrator or want to learn more about the process [[ITK/Examples/Instructions/ForAdministrators|go here]]. You will learn how the Wiki Examples repository is organized, how the repository is synced to the wiki and how to add new topics, tests and regression baselines.<br />
<br />
==Simple Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RequestedRegion | Apply a filter only to a specified region of an image ]] || || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/WidthHeight | Get the width and height of an image ]] || || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/VariableLengthVector | Variable length vector ]] || {{ITKDoxygenURL|VariableLengthVector}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TranslationTransform | Translate an image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|ResampleImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/NumericTraits | Get some basic information about a type]] || {{ITKDoxygenURL|NumericTraits}}|| Zero<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ScalarToRGBColormapImageFilter | Apply a color map to an image]] || {{ITKDoxygenURL|ScalarToRGBColormapImageFilter}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/CustomColormap | Create and apply a custom colormap]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TryCatch | Catch an ITK exception]] || || Try/Catch blocks<br />
|-<br />
| [[ITK/Examples/SimpleOperations/BresenhamLine | Get the points on a Bresenham line between two points]] || {{ITKDoxygenURL|BresenhamLine}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/Offset | Add an offset to a pixel index]] || {{ITKDoxygenURL|Offset}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenPoints | Distance between two points]] || {{ITKDoxygenURL|Point}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenIndices | Distance between two indices]] || {{ITKDoxygenURL|Point}}, {{ITKDoxygenURL|Index}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CreateVector | Create a vector]] || {{ITKDoxygenURL|Vector}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/GetNameOfClass | Get the name/type/class of an object ]] || || GetNameOfClass()<br />
|-<br />
| [[ITK/Examples/Images/Index | An object which holds the index of a pixel ]] || {{ITKDoxygenURL|Index}} || <br />
|-<br />
| [[ITK/Examples/Images/Size | An object which holds the size of an image ]] || {{ITKDoxygenURL|Size}} || <br />
|-<br />
| [[ITK/Examples/Images/ImageRegion | An object which holds the index (start) and size of a region of an image ]] || {{ITKDoxygenURL|ImageRegion}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/Transparency | Make part of an image transparent]] || {{ITKDoxygenURL|RGBAPixel}} || Transparency, RGBA, alpha<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionIntersection | Determine if one region is fully inside another region]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/PixelInsideRegion | Determine if a pixel is inside of a region]] || {{ITKDoxygenURL|ImageRegion}} || IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionOverlap | Determine the overlap of two regions]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, crop a region<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ImageDuplicator | Duplicate an image]] || {{ITKDoxygenURL|ImageDuplicator}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/RandomImageSource | Produce an image of noise]] || {{ITKDoxygenURL|RandomImageSource}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/SetPixels | Set specified pixels to specified values]] || {{ITKDoxygenURL|Image}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RGBPixel | Create an RGB image]] || {{ITKDoxygenURL|RGBPixel}} ||<br />
|}<br />
<br />
==Mathematical Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/CovariantVector | Create a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || This is the object which should be used to represent a mathematical vector.<br />
|-<br />
| [[ITK/Examples/Math/CovariantVectorNorm | Compute the norm of a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || In-place and non-inplace norms.<br />
|-<br />
| [[ITK/Examples/Math/Matrix | Matrix ]] || {{ITKDoxygenURL|Matrix}} || <br />
|-<br />
| [[ITK/Examples/Math/Pi | Mathematical constant pi = 3.14 ]] || {{ITKDoxygenURL|Math}} || <br />
|-<br />
| [[ITK/Examples/Math/DotProduct | Dot product (inner product) of two vectors ]] || {{ITKDoxygenURL|Vector}} || <br />
|}<br />
<br />
==Trigonometric Filters==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/Trig/SinImageFilter | Compute the sine of each pixel.]] || {{ITKDoxygenURL|SinImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Math/Trig/Atan2ImageFilter | Compute the arctangent of each pixel.]] || {{ITKDoxygenURL|Atan2ImageFilter}}<br />
|}<br />
<br />
==Image Functions==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Functions/NeighborhoodOperatorImageFunction | Multiply a kernel with an image at a particular location]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunction | GaussianBlurImageFunction ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunctionFilter | GaussianBlurImageFunctionFilter ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/MedianImageFunction| Compute the median of an image at a pixels (in a regular neighborhood)]] || {{ITKDoxygenURL|MedianImageFunction}} || <br />
|}<br />
<br />
==Point Set==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/PointSet/CreatePointSet | Create a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/ReadPointSet | Read a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/WritePointSet | Write a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/BoundingBox | Get the bounding box of a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|}<br />
<br />
==Input/Output (IO)==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/IO/ReadVectorImage| Read an image file with an unknown number of components]] || {{ITKDoxygenURL|ImageFileReader}},{{ITKDoxygenURL|VectorImage}} || <br />
|-<br />
| [[ITK/Examples/IO/ImportImageFilter| Convert a C-style array to an itkImage]] || {{ITKDoxygenURL|ImportImageFilter}} || <br />
|-<br />
| [[ITK/Examples/IO/ReadUnknownImageType | Read an image file without knowing its type before hand]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileWriter | Write an image]] || {{ITKDoxygenURL|ImageFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileReader | Read an image]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/TIFFImageIO | Write a TIFF image]] || {{ITKDoxygenURL|TIFFImageIO}} || This is a general demonstration of how to use a specific writer rather than relying on the ImageFileWriter to choose for you.<br />
|-<br />
| [[ITK/Examples/IO/ImageToVTKImageFilter | Display an ITK image]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileWriter | Write a transform to a file]] || {{ITKDoxygenURL|TransformFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileReader | Read a transform from a file]] || {{ITKDoxygenURL|TransformFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/VolumeFromSlices | Create a 3D volume from a series of 2D images]] || {{ITKDoxygenURL|ImageSeriesReader}} || Uses NumericSeriesFileNames to generate a list of file names<br />
|-<br />
| [[ITK/Examples/IO/itkVtkImageConvertDICOM | Uses a custom user matrix to align the image with DICOM physical space]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} || <br />
|}<br />
<br />
==DICOM==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/DICOM/ResampleDICOM | Resample a DICOM series]] || {{ITKDoxygenURL|GDCMImageIO}} || Resample a DICOM series with user-specified spacing.<br />
|}<br />
<br />
==Blob Detection, Labeling, and Properties==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ManuallyRemovingLabels | Remove labels from a LabelMap]] || {{ITKDoxygenURL|LabelMap}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ObjectByObjectLabelMapFilter | Apply an operation to every label object in a label map]] || {{ITKDoxygenURL|ObjectByObjectLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ShapeOpeningLabelMapFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|ShapeOpeningLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelShapeKeepNObjectsImageFilter | Keep only regions that rank above a certain level of a particular property]] || {{ITKDoxygenURL|LabelShapeKeepNObjectsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapOverlayImageFilter | Color labeled regions in an image]] || {{ITKDoxygenURL|LabelMapOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelGeometryImageFilter | Get geometric properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelGeometryImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelStatisticsImageFilter | Get statistical properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelStatisticsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/LabelMapContourOverlayImageFilter | Color the boundaries of labeled regions in an image]] || {{ITKDoxygenURL|LabelMapContourOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToLabelMapFilter | Label binary regions in an image]] || {{ITKDoxygenURL|BinaryImageToLabelMapFilter}} || Also demonstrates how to obtain which pixels belong to each label.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToShapeLabelMapFilter | Label binary regions in an image and get their properties]] || {{ITKDoxygenURL|BinaryImageToShapeLabelMapFilter}} || Region bounding box, centroid, etc.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapToLabelImageFilter | Convert a LabelMap to a normal image with different values representing each region]] || {{ITKDoxygenURL|LabelMapToLabelImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MergeLabelMapFilter | Merges several labelmaps]] || {{ITKDoxygenURL|MergeLabelMapFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelOverlayImageFilter | Overlay a LabelMap on an image]] || {{ITKDoxygenURL|LabelOverlayImageFilter}} || <br />
|}<br />
<br />
==Image Processing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThinningImageFilter | Skeletonize/thin an image]] || {{ITKDoxygenURL|BinaryThinningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScaleTransform | Scale an image]] || {{ITKDoxygenURL|ScaleTransform}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ResampleImageFilter | Resample (stretch or compress) an image]] || {{ITKDoxygenURL|ResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/MutualInformationImageToImageFilter | Compute the mutual information between two image]] || {{ITKDoxygenURL|MutualInformationImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianSharpeningImageFilter | Sharpen an image]] || {{ITKDoxygenURL|LaplacianSharpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/DivideImageFilter | Pixel-wise division of two images]] || {{ITKDoxygenURL|DivideImageFilter}} || Divide images<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ApproximateSignedDistanceMapImageFilter | Compute a distance map from objects in a binary image]] || {{ITKDoxygenURL|ApproximateSignedDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeToConstantImageFilter | Scale all pixels so that their sum is a specified constant]] || {{ITKDoxygenURL|NormalizeToConstantImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMinimaImageFilter | RegionalMinimaImageFilter]] || {{ITKDoxygenURL|RegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMaximaImageFilter | RegionalMaximaImageFilter]] || {{ITKDoxygenURL|RegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ZeroCrossingImageFilter| Find zero crossings in a signed image]] || {{ITKDoxygenURL|ZeroCrossingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RecursiveMultiResolutionPyramidImageFilter| Construct a multiresolution pyramid from an image]] || {{ITKDoxygenURL|RecursiveMultiResolutionPyramidImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddConstantToImageFilter| Add a constant to every pixel in an image]] || {{ITKDoxygenURL|AddImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractConstantFromImageFilter| Subtract a constant from every pixel in an image]] || {{ITKDoxygenURL|SubtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquareImageFilter| Square every pixel in an image]] || {{ITKDoxygenURL|SquareImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Upsampling| Upsampling an image]] || {{ITKDoxygenURL|BSplineInterpolateImageFunction}} {{ITKDoxygenURL|ResampleImageFilter}} || Interpolate missing pixels in order to upsample an image. Note this only works on scalar images.<br />
|-<br />
| [[ITK/Examples/Images/FlipImageFilter | Flip an image over specified axes]] || {{ITKDoxygenURL|FlipImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/VectorRescaleIntensityImageFilter | Apply a transformation to the magnitude of vector valued image pixels]] || {{ITKDoxygenURL|VectorRescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/NeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskNeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image that is non-zero in a mask]] || {{ITKDoxygenURL|MaskNeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianImageFilter | Compute the Laplacian of an image]] || {{ITKDoxygenURL|LaplacianImageFilter}} || Input image type must be double or float<br />
|-<br />
| [[ITK/Examples/Images/ConstantPadImageFilter | Pad an image with a constant value]] || {{ITKDoxygenURL|ConstantPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/MirrorPadImageFilter | Pad an image using mirroring over the boundaries]] || {{ITKDoxygenURL|MirrorPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/WrapPadImageFilter | Pad an image by wrapping]] || {{ITKDoxygenURL|WrapPadImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/IntensityWindowingImageFilter| IntensityWindowingImageFilter]] || {{ITKDoxygenURL|IntensityWindowingImageFilter}} || Apply a linear intensity transform from a specified input range to a specified output range.<br />
|-<br />
| [[ITK/Examples/Images/ShrinkImageFilter | Shrink an image]] || {{ITKDoxygenURL|ShrinkImageFilter}} || Downsample an image<br />
|-<br />
| [[ITK/Examples/Images/NormalizedCorrelationImageFilter | Normalized correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/NormalizedCorrelationImageFilterMasked | Normalized correlation of a masked image]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyByConstantImageFilter | Multiply every pixel in an image by a constant]] || {{ITKDoxygenURL|MultiplyImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquaredDifferenceImageFilter | Compute the squared difference of corresponding pixels in two images]] || {{ITKDoxygenURL|SquaredDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsoluteValueDifferenceImageFilter | Compute the absolute value of the difference of corresponding pixels in two images]] || {{ITKDoxygenURL|AbsoluteValueDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddPixelAccessor | Add a constant to every pixel without duplicating the image in memory (an accessor)]] || {{ITKDoxygenURL|AddPixelAccessor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMaximaImageFilter | ValuedRegionalMaximaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMinimaImageFilter | ValuedRegionalMinimaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaximumImageFilter | Pixel wise compare two input images and set the output pixel to their max]] || {{ITKDoxygenURL|MaximumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumImageFilter | Pixel wise compare two input images and set the output pixel to their min]] || {{ITKDoxygenURL|MinimumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AndImageFilter | Binary AND two images]] || {{ITKDoxygenURL|AndImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/OrImageFilter | Binary OR two images]] || {{ITKDoxygenURL|OrImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/XorImageFilter | Binary XOR (exclusive OR) two images]] || {{ITKDoxygenURL|XorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryNotImageFilter | Invert an image using the Binary Not operation]] || {{ITKDoxygenURL|BinaryNotImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Compose3DCovariantVectorImageFilter | Compose a vector image (with 3 components) from three scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/NthElementImageAdaptor | Extract a component/channel of an itkImage with pixels with multiple components]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || Use built in functionality to extract a component of an itkImage with CovariantVector components. Note this does not work for itkVectorImages - see VectorIndexSelectionCastImageFilter instead.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageAdaptorExtractVectorComponent | Present an image by first performing an operation]] || {{ITKDoxygenURL|ImageAdaptor}} || A demonstration of how to present an image pixel as a function of the pixel. In this example the functionality of NthElementImageAdaptor is demonstrated.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ProcessingNthImageElement | Process the nth component/element/channel of a vector image]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConvolutionImageFilter | Convolve an image with a kernel]] || {{ITKDoxygenURL|ConvolutionImageFilter}} || Convolution.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ExtractImageFilter | Crop an image by specifying the region to keep]] || {{ITKDoxygenURL|ExtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/CropImageFilter | Crop an image by specifying the region to throw away]] || {{ITKDoxygenURL|CropImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsImageFilter | Compute the absolute value of an image]] || {{ITKDoxygenURL|AbsImageFilter}} || magnitude<br />
|-<br />
| [[ITK/Examples/ImageProcessing/InvertIntensityImageFilter | Invert an image]] || {{ITKDoxygenURL|InvertIntensityImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskImageFilter | Apply a mask to an image]] || {{ITKDoxygenURL|MaskImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskNegatedImageFilter | Apply the inverse of a mask to an image]] || {{ITKDoxygenURL|MaskNegatedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SigmoidImageFilter | Pass image pixels through a sigmoid function]] || {{ITKDoxygenURL|SigmoidImageFilter}} || The qualitative description of how Alpha and Beta affect the function from the ITK Software Guide and the associated images would be nice to add to the doxygen.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|ThresholdImageFilter}} || The result is the original image but with the values below (or above) the threshold "clamped" to an output value.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|BinaryThresholdImageFilter}} || The result is a binary image (inside the threshold region or outside the threshold region).<br />
|-<br />
| [[ITK/Examples/ImageProcessing/UnaryFunctorImageFilter | Apply a custom operation to each pixel in an image]] || {{ITKDoxygenURL|UnaryFunctorImageFilter}} || Perform a custom operation on every pixel in an image. This example rotates the vector-valued pixels by 90 degrees.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilter | Apply a predefined operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilterCustom | Apply a custom operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || This example computes the squared difference between corresponding pixels.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumMaximumImageCalculator | Find the minimum and maximum value (and the position of the value) in an image]] || {{ITKDoxygenURL|MinimumMaximumImageCalculator}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddImageFilter | Add two images together]] || {{ITKDoxygenURL|AddImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractImageFilter | Subtract two images]] || {{ITKDoxygenURL|SubtractImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PasteImageFilter | Paste a part of one image into another image]] || {{ITKDoxygenURL|PasteImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_CreateVolume | Stack multiple 2D images into a 3D image]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_SideBySide | Tile multiple images side by side]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyImageFilter | Multiply two images together]] || {{ITKDoxygenURL|MultiplyImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionOfInterestImageFilter | Extract a portion of an image (region of interest)]] || {{ITKDoxygenURL|RegionOfInterestImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RescaleIntensityImageFilter | Rescale the intensity values of an image to a specified range]] || {{ITKDoxygenURL|RescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeImageFilter | Normalize an image]] || {{ITKDoxygenURL|NormalizeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/CastImageFilter | Cast an image from one type to another]] || {{ITKDoxygenURL|CastImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ClampImageFilter | Cast an image from one type to another but clamp to the output value range]] || {{ITKDoxygenURL|ClampImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PermuteAxesImageFilter | Switch the axes of an image]] || {{ITKDoxygenURL|PermuteAxesImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LinearInterpolateImageFunction | Linearly interpolate a position in an image]] || {{ITKDoxygenURL|LinearInterpolateImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/HammingWindowFunction | HammingWindowFunction]] || {{ITKDoxygenURL|HammingWindowFunction}} ||<br />
|}<br />
<br />
==Vector Images==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorMagnitudeImageFilter | Compute the magnitude of each pixel in a vector image to produce a magnitude image]] || {{ITKDoxygenURL|VectorMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImage | Create a vector image]] || {{ITKDoxygenURL|VectorImage}} || An image with an ND vector at each pixel<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Create a vector image from a collection of scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || Combine, layer<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImageToImageAdaptor | View a component of a vector image as if it were a scalar image]] || {{ITKDoxygenURL|VectorImageToImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/VectorImages/VectorIndexSelectionCastImageFilter | Extract a component/channel of a vector image]] || {{ITKDoxygenURL|VectorIndexSelectionCastImageFilter}} || This works with VectorImage as well as Image<Vector><br />
|-<br />
| [[ITK/Examples/VectorImages/VectorResampleImageFilter | Translate a vector image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|VectorResampleImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/JoinImageFilter | Join images, stacking their components]] || {{ITKDoxygenURL|JoinImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Stack scalar images into a VectorImage]] || {{ITKDoxygenURL|ImageToVectorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/NeighborhoodIterator | NeighborhoodIterator on a VectorImage]] || {{ITKDoxygenURL|VectorImage}} {{ITKDoxygenURL|NeighborhoodIterator}}||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorCastImageFilter | Cast a VectorImage to another type of VectorImage]] || {{ITKDoxygenURL|VectorImage}} ||<br />
|}<br />
<br />
==Iterating Over (Traversing) An Image==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator_Manual | Iterate over a region of an image with a shaped neighborhood]] || Create the shape manually {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator | Iterate over a region of an image with a shaped neighborhood]] || Create the shape from a StructuringElement {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionExclusionConstIteratorWithIndex | Iterator over an image skipping a specified region]] || {{ITKDoxygenURL|ImageRegionExclusionConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomConstIteratorWithIndex | Randomly select pixels from a region of an image]] || {{ITKDoxygenURL|ImageRandomConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomNonRepeatingConstIteratorWithIndex | Randomly select pixels from a region of an image without replacement]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/LineIterator | Iterate over a line through an image]] || {{ITKDoxygenURL|LineIterator}} || Walks a Bresenham line through an image (with write access)<br />
|-<br />
| [[ITK/Examples/Iterators/LineConstIterator | Iterate over a line through an image without write access]] || {{ITKDoxygenURL|LineConstIterator}} || Walks a Bresenham line through an image (without write access)<br />
|-<br />
| [[ITK/Examples/Iterators/ImageBoundaryFacesCalculator | Iterate over the central region (non-boundary) separately from the face-regions (boundary)]] || {{ITKDoxygenURL|ImageBoundaryFacesCalculator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/NeighborhoodIterator | Iterate over a region of an image with a neighborhood (with write access)]] || {{ITKDoxygenURL|NeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstNeighborhoodIterator | Iterate over a region of an image with a neighborhood (without write access)]] || {{ITKDoxygenURL|ConstNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIterator | Iterate over a region of an image (with write access)]] || {{ITKDoxygenURL|ImageRegionIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIterator | Iterate over a region of an image (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstantBoundaryCondition | Make out of bounds pixels return a constant value]] || {{ITKDoxygenURL|ConstantBoundaryCondition}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (with write access)]] || {{ITKDoxygenURL|ImageRegionIteratorWithIndex}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIteratorWithIndex}} ||<br />
|}<br />
<br />
==Kernels==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Operators/GaussianOperator | Create a Gaussian kernel]] || {{ITKDoxygenURL|GaussianOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/GaussianDerivativeOperator | Create a Gaussian derivative kernel]] || {{ITKDoxygenURL|GaussianDerivativeOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/LaplacianOperator | Create a Laplacian kernel]] || {{ITKDoxygenURL|LaplacianOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/DerivativeOperator | Create a derivative kernel]] || {{ITKDoxygenURL|DerivativeOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/SobelOperator | Create the Sobel kernel]] || {{ITKDoxygenURL|SobelOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/ForwardDifferenceOperator | Create a forward difference kernel]] || {{ITKDoxygenURL|ForwardDifferenceOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/BackwardDifferenceOperator | Create a backward difference kernel]] || {{ITKDoxygenURL|BackwardDifferenceOperator}} || <br />
<br />
|}<br />
<br />
==Image Edges, Gradients, and Derivatives==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/SobelEdgeDetectionImageFilter | SobelEdgeDetectionImageFilter]] || {{ITKDoxygenURL|SobelEdgeDetectionImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/DerivativeImageFilter | Compute the derivative of an image in a particular direction]] || {{ITKDoxygenURL|DerivativeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientRecursiveGaussianImageFilter| Compute the gradient of an image by convolution with the first derivative of a Gaussian]] || {{ITKDoxygenURL|GradientRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeRecursiveGaussianImageFilter | Find the gradient magnitude of the image first smoothed with a Gaussian kernel]] || {{ITKDoxygenURL|GradientMagnitudeRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/RecursiveGaussianImageFilter | Find higher derivatives of an image]] || {{ITKDoxygenURL|RecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryContourImageFilter | Extract the boundaries of connected regions in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} || Blob boundary, border<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryBoundaries | Extract the inner and outer boundaries of blobs in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeImageFilter | Compute the gradient magnitude image]] || {{ITKDoxygenURL|GradientMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/LaplacianRecursiveGaussianImageFilter | Compute the Laplacian of Gaussian (LoG) of an image]] || {{ITKDoxygenURL|LaplacianRecursiveGaussianImageFilter}} ||<br />
|}<br />
<br />
==Smoothing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Smoothing/AntiAliasBinaryImageFilter | Anti alias a binary image]] || {{ITKDoxygenURL|AntiAliasBinaryImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinaryMinMaxCurvatureFlowImageFilter | BinaryMinMaxCurvatureFlow a binary image]] || {{ITKDoxygenURL|BinaryMinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MeanImageFilter | Mean filter an image]] || {{ITKDoxygenURL|MeanImageFilter}} || Replace each pixel by the mean of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/MedianImageFilter | Median filter an image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/RGBMedianImageFilter | Median filter an RGB image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/GaussianDerivativeOperator | Coefficients of the Gaussian Derivative ]] || {{ITKDoxygenURL|GaussianDerivativeOperator}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/DiscreteGaussianImageFilter | Smooth an image with a discrete Gaussian filter]] || {{ITKDoxygenURL|DiscreteGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinomialBlurImageFilter | Blur an image]] || {{ITKDoxygenURL|BinomialBlurImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BilateralImageFilter | Bilateral filter an image]] || {{ITKDoxygenURL|BilateralImageFilter}} || Edge preserving smoothing.<br />
|-<br />
| [[ITK/Examples/Smoothing/CurvatureFlowImageFilter | Smooth an image using curvature flow]] || {{ITKDoxygenURL|CurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MinMaxCurvatureFlowImageFilter | Smooth an image using min/max curvature flow]] || {{ITKDoxygenURL|MinMaxCurvatureFlowImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/SmoothingRecursiveGaussianImageFilter | Gaussian smoothing that works with image adaptors]] || {{ITKDoxygenURL|SmoothingRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/VectorGradientAnisotropicDiffusionImageFilter | Smooth an image while preserving edges]] || {{ITKDoxygenURL|VectorGradientAnisotropicDiffusionImageFilter}} || Anisotropic diffusion.<br />
|}<br />
<br />
==Morphology==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Morphology/BinaryErodeImageFilter | Erode a binary image]] || {{ITKDoxygenURL|BinaryErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryDilateImageFilter | Dilate a binary image]] || {{ITKDoxygenURL|BinaryDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryPruningImageFilter | Prune a binary image]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalOpeningImageFilter | Opening a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalOpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalClosingImageFilter | Closing a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalClosingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleDilateImageFilter | Dilate a grayscale image]] || {{ITKDoxygenURL|GrayscaleDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleErodeImageFilter | Erode a grayscale image]] || {{ITKDoxygenURL|GrayscaleErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/FlatStructuringElement | Erode a binary image using a flat (box) structuring element]] || {{ITKDoxygenURL|FlatStructuringElement}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryBallStructuringElement | An elliptical structuring element]] || {{ITKDoxygenURL|BinaryBallStructuringElement}} || <br />
|}<br />
<br />
==Curves==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Curves/ContourMeanDistanceImageFilter | Compute the mean distance between all points of two curves]] || {{ITKDoxygenURL|ContourMeanDistanceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Curves/PolyLineParametricPath | A data structure for a piece-wise linear curve]] || {{ITKDoxygenURL|PolyLineParametricPath}} || <br />
|}<br />
<br />
==Spectral Analysis==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/VnlFFTRealToComplexConjugateImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/CrossCorrelationInFourierDomain | Compute the cross-correlation of two images in the Fourier domain]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}}{{ITKDoxygenURL|VnlFFTComplexConjugateToRealImageFilter}} || || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/RealAndImaginaryToComplexImageFilter | Convert a real image and an imaginary image to a complex image]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|}<br />
<br />
==Utilities==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Utilities/CreateImageWithSameType | Create another instance of an image]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Create another instance of the same type of object]] || ||<br />
|-<br />
| [[ITK/Examples/Broken/Utilities/NonSmartPointers | Using non-smart pointers]] || {{ITKDoxygenURL|Image}}<br />
|-<br />
| [[ITK/Examples/Utilities/NumericSeriesFileNames | Create a list of file names]] || {{ITKDoxygenURL|NumericSeriesFileNames}} || <br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Copy a filter]] || {{ITKDoxygenURL|Object}} || Copy/duplicate a filter<br />
|-<br />
| [[ITK/Examples/Utilities/AzimuthElevationToCartesianTransform | Cartesian to AzimuthElevation and vice-versa]] || {{ITKDoxygenURL|AzimuthElevationToCartesianTransform}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/FixedArray | C-style array]] || {{ITKDoxygenURL|FixedArray}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/DeepCopy | Deep copy an image]] || || <br />
|-<br />
| [[ITK/Examples/Utilities/RandomPermutation | Permute a sequence of indices]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Utilities/MersenneTwisterRandomVariateGenerator | Random number generator]] || {{ITKDoxygenURL|MersenneTwisterRandomVariateGenerator}} || <br />
|-<br />
| [[ITK/Examples/Utilities/JetColormapFunctor | Map scalars into a jet colormap]] || {{ITKDoxygenURL|JetColormapFunctor}} || <br />
|-<br />
| [[ITK/Examples/Utilities/SimpleFilterWatcher | Monitor a filter]] || {{ITKDoxygenURL|SimpleFilterWatcher}} || See debug style information.<br />
|-<br />
| [[ITK/Examples/Utilities/TimeProbe | Time probe]] || {{ITKDoxygenURL|TimeProbe}} || Compute the time between points in code. Timer. Timing.<br />
|-<br />
| [[ITK/Examples/Utilities/ObserveEvent | Observe an event]] || {{ITKDoxygenURL|Command}} || <br />
|-<br />
| [[ITK/Examples/Utilities/VectorContainer | Vector container]] || {{ITKDoxygenURL|VectorContainer}} || <br />
|}<br />
<br />
==Statistics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/MovingHistogramImageFilter | Compute histograms in a sliding window.]] || {{ITKDoxygenURL|MovingHistogramImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterRGB | Compute a histogram from an RGB image.]] || {{ITKDoxygenURL|HistogramToImageFilterRGB}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterVectorImage | Compute a histogram from a itk::VectorImage.]] || {{ITKDoxygenURL|HistogramToImageFilterVectorImage}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterGrayscale | Compute a histogram from a grayscale image.]] || {{ITKDoxygenURL|HistogramToImageFilterGrayscale}} || <br />
|-<br />
| [[ITK/Examples/Statistics/Histogram | Compute a histogram from measurements.]] || {{ITKDoxygenURL|Histogram}} || <br />
|-<br />
| [[ITK/Examples/Statistics/StatisticsImageFilter | Compute min, max, variance and mean of an Image.]] || {{ITKDoxygenURL|StatisticsImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/GaussianDistribution | Create a Gaussian distribution]] || {{ITKDoxygenURL|GaussianDistribution}} || <br />
|-<br />
| [[ITK/Examples/Statistics/SampleToHistogramFilter | Create a histogram from a list of sample measurements]] || {{ITKDoxygenURL|SampleToHistogramFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ListSample | Create a list of sample measurements]] || {{ITKDoxygenURL|ListSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageToListSampleAdaptor | Create a list of samples from an image without duplicating the data]] || {{ITKDoxygenURL|ImageToListSampleAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Statistics/MembershipSample | Create a list of samples with associated class IDs]] || {{ITKDoxygenURL|MembershipSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ExpectationMaximizationMixtureModelEstimator_2D | 2D Gaussian Mixture Model Expectation Maximization]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || EM<br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_1D | 1D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_3D | 3D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTree | Spatial search]] || {{ITKDoxygenURL|KdTreeGenerator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ScalarImageKmeansImageFilter | Cluster the pixels in a greyscale image]] || {{ITKDoxygenURL|ScalarImageKmeansImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/NoiseImageFilter | Compute the local noise in an image]] || {{ITKDoxygenURL|NoiseImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageKmeansModelEstimator | Compute kmeans clusters of pixels in an image]] || {{ITKDoxygenURL|ImageKmeansModelEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKmeansEstimator | Compute kmeans clusters]] || {{ITKDoxygenURL|KdTreeBasedKmeansEstimator}} || <br />
|}<br />
<br />
==Spatial Objects==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpatialObjects/SpatialObjectToImageFilter | Convert a spatial object to an image ]] || {{ITKDoxygenURL|SpatialObjectToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/EllipseSpatialObject | Ellipse ]] || {{ITKDoxygenURL|EllipseSpatialObject}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/LineSpatialObject| Line spatial object]] || {{ITKDoxygenURL|LineSpatialObject}}, {{ITKDoxygenURL|LineSpatialObjectPoint}} || Specify a piecewise-linear object by specifying points along the line.<br />
|-<br />
| [[ITK/Examples/SpatialObjects/PlaneSpatialObject| Plane spatial object]] || {{ITKDoxygenURL|PlaneSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/SpatialObjects/BlobSpatialObject | Blob ]] || {{ITKDoxygenURL|BlobSpatialObject}} ||<br />
|}<br />
<br />
==Inspection==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Inspection/CheckerBoardImageFilter | Combine two images by alternating blocks of a checkerboard pattern]] || {{ITKDoxygenURL|CheckerBoardImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Inspection/PixelInspection | Printing a pixel value to the console]] || [http://www.itk.org/Doxygen/html/classitk_1_1Image.html#ad424c945604f339130b4ffe81b99738eGetPixel GetPixel] ||<br />
|}<br />
<br />
==Metrics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Metrics/MeanSquaresImageToImageMetric | Compute the mean squares metric between two images ]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} ||<br />
|}<br />
==Image Registration==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Registration/WarpImageFilter | Warp one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|WarpImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Registration/LandmarkBasedTransformInitializer | Rigidly register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|LandmarkBasedTransformInitializer}} ||<br />
|-<br />
| [[ITK/Examples/Registration/DeformationFieldTransform | Register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|DeformationFieldTransform}} ||<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethod | A basic global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|TranslationTransform}} || Translation only transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodAffine | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|AffineTransform}} || Full affine transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodBSpline | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|BSplineDeformableTransform}} || BSpline transform.<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformation | Mutual Information ]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|TranslationTransform}} || Global registration by maximizing the mutual information and using a translation only transform<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformationAffine | Mutual Information Affine]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|AffineTransform}} || Global registration by maximizing the mutual information and using an affine transform<br />
|}<br />
<br />
==Image Segmentation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Segmentation/ContourExtractor2DImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|ContourExtractor2DImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/WatershedImageFilter| Watershed segmentation]] ||{{ITKDoxygenURL|WatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/MorphologicalWatershedImageFilter| Morphological Watershed segmentation]] ||{{ITKDoxygenURL|MorphologicalWatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/EstimatePCAModel | Compute a PCA shape model from a training sample]] || {{ITKDoxygenURL|ImagePCAShapeModelEstimator}} ||<br />
Estimate the principal modes of variation of a shape from a training sample. Useful for shape guide segmentation.<br />
|-<br />
| [[ITK/Examples/Segmentation/MeanShiftClustering | Mean shift clustering]] || {{ITKDoxygenURL|SampleMeanShiftClusteringFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/kMeansClustering | KMeans Clustering]] || ||<br />
|-<br />
| [[ITK/Examples/Segmentation/MultiphaseChanAndVeseSparseFieldLevelSetSegmentation | Multiphase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseSparseFieldLevelSetSegmentation | Single-phase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseDenseFieldLevelSetSegmentation | Single-phase Chan And Vese Dense Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseDenseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/WishList/VoronoiDiagram2DGenerator | Voronoi diagram]] || {{ITKDoxygenURL|VoronoiDiagram2DGenerator}}, {{ITKDoxygenURL|VoronoiDiagram2D}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConnectedComponentImageFilter | Label connected components in a binary image]] || {{ITKDoxygenURL|ConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScalarConnectedComponentImageFilter | Label connected components in a grayscale image]] || {{ITKDoxygenURL|ScalarConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RelabelComponentImageFilter | Assign contiguous labels to connected regions of an image]] || {{ITKDoxygenURL|RelabelComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelContourImageFilter | Label the contours of connected components]] || {{ITKDoxygenURL|LabelContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ConfidenceConnectedImageFilter | Segment pixels with similar statistics using connectivity ]] || {{ITKDoxygenURL|ConfidenceConnectedImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToLabelMapFilter | Convert an itk::Image consisting of labeled regions to a LabelMap ]] || <br />
{{ITKDoxygenURL|LabelImageToLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToShapeLabelMapFilter | Convert an itk::Image consisting of labeled regions to a ShapeLabelMap ]] || {{ITKDoxygenURL|LabelImageToShapeLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ExtractLargestConnectedComponentFromBinaryImage | Extract the largest connected component from a Binary Image ]] || <br />
||<br />
|}<br />
<br />
==Meshes==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Meshes/Decimation | Decimation]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/AddPointsAndEdges | Add points and edges]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshNormalFilter | Compute normals of a mesh]] || {{ITKDoxygenURL|QuadEdgeMeshNormalFilter}} ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshParameterizationFilter | Planar parameterization of a mesh]] || {{ITKDoxygenURL|ParameterizationQuadEdgeMeshFilter}} || Compute linear parameterization of a mesh homeomorphic to a disk on the plane<br />
|-<br />
| [[ITK/Examples/Meshes/ConvertToVTK | Convert an itk::Mesh to a vtkUnstructuredGrid]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/WishList/WriteMeshToVTP | Write an itk::Mesh to a vtp (vtkPolyData) file]] || {{ITKDoxygenURL|VTKPolyDataWriter}} ||<br />
|}<br />
<br />
==Need Demo==<br />
This section consists of examples which compile and work, but a good demonstration image must be selected and added.<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/NeedDemo/ImageProcessing/AdaptiveHistogramEqualizationImageFilter | Adaptive histogram equalization]] || {{ITKDoxygenURL|AdaptiveHistogramEqualizationImageFilter}} ||<br />
|}<br />
<br />
<br />
==Wish List==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/ScalarImageToTextureFeaturesFilter | Compute texture features]] || {{ITKDoxygenURL|ScalarImageToTextureFeaturesFilter}} || How to interpret the output?<br />
|-<br />
| [[ITK/Examples/WishList/LevelSets/SignedDanielssonDistanceMapImageFilter | Compute the signed distance function over an image]] || {{ITKDoxygenURL|SignedDanielssonDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorImageResampleImageFilter | Resample an itk::VectorImage]] || ||<br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/OtsuMultipleThresholdsCalculator | Compute Otsu thresholds]] || {{ITKDoxygenURL|OtsuMultipleThresholdsCalculator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/MaskedImageToHistogramFilter | Compute the histogram of a masked region of an image]] || {{ITKDoxygenURL|MaskedImageToHistogramFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/PointSet/BSplineScatteredDataPointSetToImageFilter | Fit a spline to a point set]] || {{ITKDoxygenURL|BSplineScatteredDataPointSetToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Morphology/BinaryPruningImageFilter | BinaryPruningImageFilter]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/GaussianMixtureModelComponent | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|GaussianMixtureModelComponent}} ||<br />
|-<br />
| [[ITK/Examples/WishList/LevenbergMarquart| LevenbergMarquart]] || || <br />
|-<br />
| [[ITK/Examples/WishList/IterativeClosestPoints| IterativeClosestPoints]] || || <br />
|-<br />
| [[ITK/Examples/WishList/Operators/AllOperators| Demonstrate all operators]] || {{ITKDoxygenURL|NeighborhoodOperator}} || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/ColorNormalizedCorrelation| Color Normalized Correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/SpatialObjects/ContourSpatialObject| ContourSpatialObject]] || {{ITKDoxygenURL|ContourSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/Broken/SimpleOperations/MetaDataDictionary| Store non-pixel associated data in an image]] || {{ITKDoxygenURL|MetaDataDictionary}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/LevelSets| Level Sets]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation//RegionGrowing| Region Growing]] || || <br />
|-<br />
| [[ITK/Examples/Meshes/Subdivision| Mesh subdivision]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation/OtsuThresholdImageFilter| Separate foreground and background using Otsu's method]] || {{ITKDoxygenURL|OtsuThresholdImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/SimpleContourExtractorImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|SimpleContourExtractorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/RGBToVectorImageAdaptor| Present an image of RGBPixel pixels as an image of vectors]] || {{ITKDoxygenURL|RGBToVectorImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DCirclesImageFilter| HoughTransform2DCirclesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DCirclesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DLinesImageFilter| HoughTransform2DLinesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DLinesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Matlab/MatlabToITK| Write data from Matlab in a format readable by ITK]] || || <br />
|-<br />
| [[ITK/Examples/Matlab/ITKToMatlab| Write data from ITK in a format readable by Matlab]] || || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/EdgePotentialImageFilter| Compute edge potential]] ||{{ITKDoxygenURL|EdgePotentialImageFilter}} || <br />
|}<br />
<br />
==Included in the ITK Repository==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Included/Registration| Image registration]] || || <br />
|}<br />
<br />
==Matlab==<br />
{{ITKExamplesTable}}<br />
<br />
|}<br />
<br />
==Developer Examples==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Developer/Exceptions | Throw an exception]] || || <br />
|-<br />
| [[ITK/Examples/Developer/ImageSource | Produce an image programmatically.]] || {{ITKDoxygenURL|ImageSource}} || Nothing in, image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilter | Filter an image]] || {{ITKDoxygenURL|ImageToImageFilter}} || Image in, same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/OilPaintingImageFilter | Multi-threaded oil painting image filter]] || {{ITKDoxygenURL|ImageToImageFilter}} and {{ITKDoxygenURL|MinimumMaximumImageCalculator}} || A simple multi-threaded scenario (oil painting artistic filter). You can also use this class as-is (copy .h and .txx files into your project and use them).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputs | Write a filter with multiple inputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (same type), same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputsDifferentType | Write a filter with multiple inputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (different type), image (same type as first input) out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputs | Write a filter with multiple outputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (same type as first input).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputsDifferentType | Write a filter with multiple outputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (different types).<br />
|-<br />
| [[ITK/Examples/Developer/SetGetMacro | Get or set a member variable of an ITK class.]] || || SetMacro, GetMacro<br />
|-<br />
| [[ITK/Examples/Developer/OutputMacros | Output an error, a warning, or debug information.]] || || DebugMacro, ErrorMacro, WarningMacro<br />
|}<br />
<br />
==Problems==<br />
===Small Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFilledImageFunctionConditionalIterator | Iterate over an image starting at a seed and following a rule for connectivity decisions]] || {{ITKDoxygenURL|FloodFilledImageFunctionConditionalIterator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFillIterator | Traverse a region using a flood fill iterator]] || {{ITKDoxygenURL|FloodFilledSpatialFunctionConditionalIterator}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/GradientOfVectorImage | Compute the gradient of a vector image]] || {{ITKDoxygenURL|GradientImageFilter}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_Image | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_1D | Compute distributions of samples using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || Someone please confirm that this outputs the mean and the variance (i.e. I used a standard deviation of 30 to create the samples and the second estimated parameter is near 1000 (~30^2) . Is this correct?)<br />
|-<br />
| [[ITK/Examples/Broken/EdgesAndGradients/CannyEdgeDetectionImageFilter | Find edges in an image]] || {{ITKDoxygenURL|CannyEdgeDetectionImageFilter}} || How to set a reasonable Threshold for the output edges?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ImageToHistogramFilter | Compute the histogram of an image]] || {{ITKDoxygenURL|Statistics_1_1ImageToHistogramFilter}} || The last entry of the red histogram should contain several values, but it is 0?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/KmeansModelEstimator | Classifying pixels using KMeans]] || {{ITKDoxygenURL|KmeansModelEstimator}} || How to apply the labels of the filter to the input image?<br />
|-<br />
| [[ITK/Examples/Broken/Images/RegionGrowImageFilter | Basic region growing]] || {{ITKDoxygenURL|RegionGrowImageFilter}} || Just getting started with demo...<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConnectedThresholdImageFilter | Find connected components in an image]] || {{ITKDoxygenURL|ConnectedThresholdImageFilter}} || Just need to finish it.<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConvertPixelBuffer | Convert an image from one type to another]] || {{ITKDoxygenURL|ConvertPixelBuffer}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/InPlace | In-place filtering of an image]] || {{ITKDoxygenURL|InPlaceImageFilter}} || This only works for filters which derive from itkInPlaceImageFilter<br />
|-<br />
| [[ITK/Examples/Broken/Images/VTKImageToImageFilter | Convert a VTK image to an ITK image]] || {{ITKDoxygenURL|VTKImageToImageFilter}} || Seems to expect an input image with only 1 component? (i.e. greyscale)<br />
|}<br />
<br />
===Big Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Images/MeanSquaresImageToImageMetric | Find the best position of the moving image in the fixed image.]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} || Output (0,0) is incorrect.<br />
|-<br />
| [[ITK/Examples/Broken/Images/GradientImageFilter | Compute and display the gradient of an image]] || {{ITKDoxygenURL|GradientImageFilter}} || Blank output on the screen (the filter works fine). There should be a "DisplayVectorImage" added to itkQuickView that draws vector glyphs at specified pixels of an image.<br />
|}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/MergeLabelMapFilter&diff=44763ITK/Examples/ImageProcessing/MergeLabelMapFilter2012-01-06T00:54:01Z<p>Ccagataybilgin: </p>
<hr />
<div>==MergeLabelMapFilter.cxx==<br />
<source lang="cpp"><br />
#include "itkBinaryImageToShapeLabelMapFilter.h"<br />
#include "itkMergeLabelMapFilter.h"<br />
<br />
int main(int argc, char* argv[])<br />
{<br />
typedef itk::Image<int, 3> ImageType;<br />
<br />
//Binary Image to Shape Label Map. <br />
typedef itk::BinaryImageToShapeLabelMapFilter<ImageType> BI2SLMType;<br />
typedef BI2SLMType::OutputImageType LabelMapType;<br />
typedef BI2SLMType::LabelObjectType LabelObjectType;<br />
<br />
typedef itk::MergeLabelMapFilter<LabelMapType> MergerType;<br />
typename MergerType::Pointer merger = MergerType::New();<br />
<br />
int noObjects = 4;<br />
<br />
for (int i = 1; i <= noObjects; i++)<br />
{<br />
LabelMapType::Pointer labelMap = LabelMapType::New();<br />
LabelObjectType::Pointer labelObject = LabelObjectType::New();<br />
<br />
labelObject->SetLabel(1);<br />
labelMap->AddLabelObject(labelObject);<br />
labelMap->Update();<br />
<br />
merger->SetInput(i - 1, labelMap);<br />
}<br />
<br />
merger->Update();<br />
std::cout << "number of objects: "<br />
<< merger->GetOutput()->GetNumberOfLabelObjects() << "\n";<br />
std::cout << "number of expected objects: " << noObjects << "\n";<br />
<br />
return EXIT_SUCCESS;<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|MergeLabelMapFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/MergeLabelMapFilter&diff=44762ITK/Examples/ImageProcessing/MergeLabelMapFilter2012-01-06T00:51:47Z<p>Ccagataybilgin: </p>
<hr />
<div>==MergeLabelMapFilter.cxx==<br />
<source lang="cpp"><br />
#include "itkBinaryImageToShapeLabelMapFilter.h"<br />
#include "itkMergeLabelMapFilter.h"<br />
<br />
int<br />
main(int argc, char* argv[])<br />
{<br />
// Input and Output image types<br />
typedef itk::Image<int, 3> ImageType;<br />
<br />
//Binary Image to Shape Label Map. <br />
typedef itk::BinaryImageToShapeLabelMapFilter<ImageType> BI2SLMType;<br />
typedef BI2SLMType::OutputImageType LabelMapType;<br />
typedef BI2SLMType::LabelObjectType LabelObjectType;<br />
<br />
typedef itk::MergeLabelMapFilter<LabelMapType> MergerType;<br />
typename MergerType::Pointer merger = MergerType::New();<br />
<br />
int noObjects = 4;<br />
<br />
for (int i = 1; i <= noObjects; i++)<br />
{<br />
LabelMapType::Pointer labelMap = LabelMapType::New();<br />
LabelObjectType::Pointer labelObject = LabelObjectType::New();<br />
<br />
labelObject->SetLabel(1);<br />
labelMap->AddLabelObject(labelObject);<br />
labelMap->Update();<br />
<br />
merger->SetInput(i - 1, labelMap);<br />
}<br />
<br />
merger->Update();<br />
std::cout << "number of objects: "<br />
<< merger->GetOutput()->GetNumberOfLabelObjects() << "\n";<br />
std::cout << "number of expected objects: " << noObjects << "\n";<br />
<br />
return EXIT_SUCCESS;<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|MergeLabelMapFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/MergeLabelMapFilter&diff=44761ITK/Examples/ImageProcessing/MergeLabelMapFilter2012-01-06T00:50:51Z<p>Ccagataybilgin: </p>
<hr />
<div>==ShapeOpeningLabelMapFilter.cxx==<br />
<source lang="cpp"><br />
#include "itkBinaryImageToShapeLabelMapFilter.h"<br />
#include "itkMergeLabelMapFilter.h"<br />
<br />
int<br />
main(int argc, char* argv[])<br />
{<br />
// Input and Output image types<br />
typedef itk::Image<int, 3> ImageType;<br />
<br />
//Binary Image to Shape Label Map. <br />
typedef itk::BinaryImageToShapeLabelMapFilter<ImageType> BI2SLMType;<br />
typedef BI2SLMType::OutputImageType LabelMapType;<br />
typedef BI2SLMType::LabelObjectType LabelObjectType;<br />
<br />
typedef itk::MergeLabelMapFilter<LabelMapType> MergerType;<br />
typename MergerType::Pointer merger = MergerType::New();<br />
<br />
int noObjects = 4;<br />
<br />
for (int i = 1; i <= noObjects; i++)<br />
{<br />
LabelMapType::Pointer labelMap = LabelMapType::New();<br />
LabelObjectType::Pointer labelObject = LabelObjectType::New();<br />
<br />
labelObject->SetLabel(1);<br />
labelMap->AddLabelObject(labelObject);<br />
labelMap->Update();<br />
<br />
merger->SetInput(i - 1, labelMap);<br />
}<br />
<br />
merger->Update();<br />
std::cout << "number of objects: "<br />
<< merger->GetOutput()->GetNumberOfLabelObjects() << "\n";<br />
std::cout << "number of expected objects: " << noObjects << "\n";<br />
<br />
return EXIT_SUCCESS;<br />
}<br />
<br />
</source><br />
<br />
{{ITKCMakeLists|ShapeOpeningLabelMapFilter}}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples/ImageProcessing/MergeLabelMapFilter&diff=44760ITK/Examples/ImageProcessing/MergeLabelMapFilter2012-01-06T00:48:59Z<p>Ccagataybilgin: </p>
<hr />
<div>Demo text - permissions problem.<br />
<br />
#include "itkBinaryImageToShapeLabelMapFilter.h"<br />
#include "itkMergeLabelMapFilter.h"<br />
<br />
int<br />
main(int argc, char* argv[])<br />
{<br />
// Input and Output image types<br />
typedef itk::Image<int, 3> ImageType;<br />
<br />
//Binary Image to Shape Label Map. <br />
typedef itk::BinaryImageToShapeLabelMapFilter<ImageType> BI2SLMType;<br />
typedef BI2SLMType::OutputImageType LabelMapType;<br />
typedef BI2SLMType::LabelObjectType LabelObjectType;<br />
<br />
typedef itk::MergeLabelMapFilter<LabelMapType> MergerType;<br />
typename MergerType::Pointer merger = MergerType::New();<br />
<br />
int noObjects = 4;<br />
<br />
for (int i = 1; i <= noObjects; i++)<br />
{<br />
LabelMapType::Pointer labelMap = LabelMapType::New();<br />
LabelObjectType::Pointer labelObject = LabelObjectType::New();<br />
<br />
labelObject->SetLabel(1);<br />
labelMap->AddLabelObject(labelObject);<br />
labelMap->Update();<br />
<br />
merger->SetInput(i - 1, labelMap);<br />
}<br />
<br />
merger->Update();<br />
std::cout << "number of objects: "<br />
<< merger->GetOutput()->GetNumberOfLabelObjects() << "\n";<br />
std::cout << "number of expected objects: " << noObjects << "\n";<br />
<br />
return EXIT_SUCCESS;<br />
}</div>Ccagataybilginhttps://public.kitware.com/Wiki/index.php?title=ITK/Examples&diff=44753ITK/Examples2012-01-05T22:55:28Z<p>Ccagataybilgin: /* Blob Detection, Labeling, and Properties */</p>
<hr />
<div>These are fully independent, compilable examples, developed with these [[ITK/Examples/Goals|goals]] in mind. There is significant overlap in the examples, but they are each intended to illustrate a different concept and be fully stand alone compilable.<br />
Please add examples in your areas of expertise!<br />
You can checkout the entire set of examples from this repository: <br />
http://gitorious.org/itkwikiexamples/itkwikiexamples<br />
<pre>git clone git://gitorious.org/itkwikiexamples/itkwikiexamples.git ITKWikiExamples</pre><br />
<br />
==About the Examples==<br />
* [http://www.itk.org/Wiki/images/e/e6/ITK_Examples_Iowa_Meeting_2010_11-8-2010.odp Official announcement]<br />
===ItkVtkGlue===<br />
ITK and VTK are very separate toolkits - ITK for image processing and VTK for data visualization. It is often convenient to use the two together - namely, to display an ITK image on the screen. The ItkVtkGlue kit serves exactly this purpose. Also provided inside ItkVtkGlue is a QuickView class to allow a 2 line display of an ITK image.<br />
<br />
If you download the entire ITK Wiki Examples Collection, the ItkVtkGlue directory will be included and configured. If you wish to just build a few examples, then you will need to [http://gitorious.org/itkwikiexamples/itkwikiexamples/blobs/raw/143b4a80c6f5bbe44edbcbeccaa9c05b83042d65/ItkVtkGlue.tar.gz download ItkVtkGlue] and build it.<br />
<br />
===[[ITK/Examples/Instructions/ForUsers|Information for Wiki Examples Users]]===<br />
If you just want to use the Wiki Examples, [[ITK/Examples/Instructions/ForUsers|go here]]. You will learn how to search for examples, build a few examples and build all of the examples.<br />
<br />
===[[ITK/Examples/Instructions/ForDevelopers|Information for Wiki Examples Developers]]===<br />
If you want to contribute examples [[ITK/Examples/Instructions/ForDevelopers|go here]]. You will learn how to add a new example and the guidelines for writing an example.<br />
<br />
===[[ITK/Examples/Instructions/ForAdministrators|Information for Wiki Examples Administrators]]===<br />
If you are a Wiki Example Administrator or want to learn more about the process [[ITK/Examples/Instructions/ForAdministrators|go here]]. You will learn how the Wiki Examples repository is organized, how the repository is synced to the wiki and how to add new topics, tests and regression baselines.<br />
<br />
==Simple Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RequestedRegion | Apply a filter only to a specified region of an image ]] || || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/WidthHeight | Get the width and height of an image ]] || || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/VariableLengthVector | Variable length vector ]] || {{ITKDoxygenURL|VariableLengthVector}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TranslationTransform | Translate an image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|ResampleImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/NumericTraits | Get some basic information about a type]] || {{ITKDoxygenURL|NumericTraits}}|| Zero<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ScalarToRGBColormapImageFilter | Apply a color map to an image]] || {{ITKDoxygenURL|ScalarToRGBColormapImageFilter}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/CustomColormap | Create and apply a custom colormap]] || {{ITKDoxygenURL|CustomColormapFunction}}|| <br />
|-<br />
| [[ITK/Examples/SimpleOperations/TryCatch | Catch an ITK exception]] || || Try/Catch blocks<br />
|-<br />
| [[ITK/Examples/SimpleOperations/BresenhamLine | Get the points on a Bresenham line between two points]] || {{ITKDoxygenURL|BresenhamLine}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/Offset | Add an offset to a pixel index]] || {{ITKDoxygenURL|Offset}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenPoints | Distance between two points]] || {{ITKDoxygenURL|Point}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/DistanceBetweenIndices | Distance between two indices]] || {{ITKDoxygenURL|Point}}, {{ITKDoxygenURL|Index}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/CreateVector | Create a vector]] || {{ITKDoxygenURL|Vector}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/GetNameOfClass | Get the name/type/class of an object ]] || || GetNameOfClass()<br />
|-<br />
| [[ITK/Examples/Images/Index | An object which holds the index of a pixel ]] || {{ITKDoxygenURL|Index}} || <br />
|-<br />
| [[ITK/Examples/Images/Size | An object which holds the size of an image ]] || {{ITKDoxygenURL|Size}} || <br />
|-<br />
| [[ITK/Examples/Images/ImageRegion | An object which holds the index (start) and size of a region of an image ]] || {{ITKDoxygenURL|ImageRegion}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/Transparency | Make part of an image transparent]] || {{ITKDoxygenURL|RGBAPixel}} || Transparency, RGBA, alpha<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionIntersection | Determine if one region is fully inside another region]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/PixelInsideRegion | Determine if a pixel is inside of a region]] || {{ITKDoxygenURL|ImageRegion}} || IsInside()<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RegionOverlap | Determine the overlap of two regions]] || {{ITKDoxygenURL|ImageRegion}} || Region intersection, crop a region<br />
|-<br />
| [[ITK/Examples/SimpleOperations/ImageDuplicator | Duplicate an image]] || {{ITKDoxygenURL|ImageDuplicator}} || <br />
|-<br />
| [[ITK/Examples/SimpleOperations/RandomImageSource | Produce an image of noise]] || {{ITKDoxygenURL|RandomImageSource}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/SetPixels | Set specified pixels to specified values]] || {{ITKDoxygenURL|Image}} ||<br />
|-<br />
| [[ITK/Examples/SimpleOperations/RGBPixel | Create an RGB image]] || {{ITKDoxygenURL|RGBPixel}} ||<br />
|}<br />
<br />
==Mathematical Operations==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/CovariantVector | Create a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || This is the object which should be used to represent a mathematical vector.<br />
|-<br />
| [[ITK/Examples/Math/CovariantVectorNorm | Compute the norm of a covariant vector]] || {{ITKDoxygenURL|CovariantVector}} || In-place and non-inplace norms.<br />
|-<br />
| [[ITK/Examples/Math/Matrix | Matrix ]] || {{ITKDoxygenURL|Matrix}} || <br />
|-<br />
| [[ITK/Examples/Math/Pi | Mathematical constant pi = 3.14 ]] || {{ITKDoxygenURL|Math}} || <br />
|-<br />
| [[ITK/Examples/Math/DotProduct | Dot product (inner product) of two vectors ]] || {{ITKDoxygenURL|Vector}} || <br />
|}<br />
<br />
==Trigonometric Filters==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Math/Trig/SinImageFilter | Compute the sine of each pixel.]] || {{ITKDoxygenURL|SinImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Math/Trig/Atan2ImageFilter | Compute the arctangent of each pixel.]] || {{ITKDoxygenURL|Atan2ImageFilter}}<br />
|}<br />
<br />
==Image Functions==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Functions/NeighborhoodOperatorImageFunction | Multiply a kernel with an image at a particular location]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunction | GaussianBlurImageFunction ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/GaussianBlurImageFunctionFilter | GaussianBlurImageFunctionFilter ]] || {{ITKDoxygenURL|GaussianBlurImageFunction}} || <br />
|-<br />
| [[ITK/Examples/Functions/MedianImageFunction| Compute the median of an image at a pixels (in a regular neighborhood)]] || {{ITKDoxygenURL|MedianImageFunction}} || <br />
|}<br />
<br />
==Point Set==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/PointSet/CreatePointSet | Create a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/ReadPointSet | Read a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/WritePointSet | Write a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|-<br />
| [[ITK/Examples/PointSet/BoundingBox | Get the bounding box of a PointSet ]] || {{ITKDoxygenURL|PointSet}} || <br />
|}<br />
<br />
==Input/Output (IO)==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/IO/ReadVectorImage| Read an image file with an unknown number of components]] || {{ITKDoxygenURL|ImageFileReader}},{{ITKDoxygenURL|VectorImage}} || <br />
|-<br />
| [[ITK/Examples/IO/ImportImageFilter| Convert a C-style array to an itkImage]] || {{ITKDoxygenURL|ImportImageFilter}} || <br />
|-<br />
| [[ITK/Examples/IO/ReadUnknownImageType | Read an image file without knowing its type before hand]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileWriter | Write an image]] || {{ITKDoxygenURL|ImageFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/ImageFileReader | Read an image]] || {{ITKDoxygenURL|ImageFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/TIFFImageIO | Write a TIFF image]] || {{ITKDoxygenURL|TIFFImageIO}} || This is a general demonstration of how to use a specific writer rather than relying on the ImageFileWriter to choose for you.<br />
|-<br />
| [[ITK/Examples/IO/ImageToVTKImageFilter | Display an ITK image]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileWriter | Write a transform to a file]] || {{ITKDoxygenURL|TransformFileWriter}} ||<br />
|-<br />
| [[ITK/Examples/IO/TransformFileReader | Read a transform from a file]] || {{ITKDoxygenURL|TransformFileReader}} ||<br />
|-<br />
| [[ITK/Examples/IO/VolumeFromSlices | Create a 3D volume from a series of 2D images]] || {{ITKDoxygenURL|ImageSeriesReader}} || Uses NumericSeriesFileNames to generate a list of file names<br />
|-<br />
| [[ITK/Examples/IO/itkVtkImageConvertDICOM | Uses a custom user matrix to align the image with DICOM physical space]] || {{ITKDoxygenURL|ImageToVTKImageFilter}} || <br />
|}<br />
<br />
==DICOM==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/DICOM/ResampleDICOM | Resample a DICOM series]] || {{ITKDoxygenURL|GDCMImageIO}} || Resample a DICOM series with user-specified spacing.<br />
|}<br />
<br />
==Blob Detection, Labeling, and Properties==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ManuallyRemovingLabels | Remove labels from a LabelMap]] || {{ITKDoxygenURL|LabelMap}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ObjectByObjectLabelMapFilter | Apply an operation to every label object in a label map]] || {{ITKDoxygenURL|ObjectByObjectLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ShapeOpeningLabelMapFilter | Keep only regions that meet a specified threshold of a specified property]] || {{ITKDoxygenURL|ShapeOpeningLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelShapeKeepNObjectsImageFilter | Keep only regions that rank above a certain level of a particular property]] || {{ITKDoxygenURL|LabelShapeKeepNObjectsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapOverlayImageFilter | Color labeled regions in an image]] || {{ITKDoxygenURL|LabelMapOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelGeometryImageFilter | Get geometric properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelGeometryImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelStatisticsImageFilter | Get statistical properties of labeled regions in an image]] || {{ITKDoxygenURL|LabelStatisticsImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/LabelMapContourOverlayImageFilter | Color the boundaries of labeled regions in an image]] || {{ITKDoxygenURL|LabelMapContourOverlayImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToLabelMapFilter | Label binary regions in an image]] || {{ITKDoxygenURL|BinaryImageToLabelMapFilter}} || Also demonstrates how to obtain which pixels belong to each label.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryImageToShapeLabelMapFilter | Label binary regions in an image and get their properties]] || {{ITKDoxygenURL|BinaryImageToShapeLabelMapFilter}} || Region bounding box, centroid, etc.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelMapToLabelImageFilter | Convert a LabelMap to a normal image with different values representing each region]] || {{ITKDoxygenURL|LabelMapToLabelImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MergeLabelMapFilter | Merges several labelmaps]] || {{ITKDoxygenURL|MergeLabelMapFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LabelOverlayImageFilter | Overlay a LabelMap on an image]] || {{ITKDoxygenURL|LabelOverlayImageFilter}} || <br />
|}<br />
<br />
==Image Processing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThinningImageFilter | Skeletonize/thin an image]] || {{ITKDoxygenURL|BinaryThinningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScaleTransform | Scale an image]] || {{ITKDoxygenURL|ScaleTransform}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ResampleImageFilter | Resample (stretch or compress) an image]] || {{ITKDoxygenURL|ResampleImageFilter}} || Upsample, downsample, resize<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/MutualInformationImageToImageFilter | Compute the mutual information between two image]] || {{ITKDoxygenURL|MutualInformationImageToImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianSharpeningImageFilter | Sharpen an image]] || {{ITKDoxygenURL|LaplacianSharpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/DivideImageFilter | Pixel-wise division of two images]] || {{ITKDoxygenURL|DivideImageFilter}} || Divide images<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ApproximateSignedDistanceMapImageFilter | Compute a distance map from objects in a binary image]] || {{ITKDoxygenURL|ApproximateSignedDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeToConstantImageFilter | Scale all pixels so that their sum is a specified constant]] || {{ITKDoxygenURL|NormalizeToConstantImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMinimaImageFilter | RegionalMinimaImageFilter]] || {{ITKDoxygenURL|RegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionalMaximaImageFilter | RegionalMaximaImageFilter]] || {{ITKDoxygenURL|RegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ZeroCrossingImageFilter| Find zero crossings in a signed image]] || {{ITKDoxygenURL|ZeroCrossingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/RecursiveMultiResolutionPyramidImageFilter| Construct a multiresolution pyramid from an image]] || {{ITKDoxygenURL|RecursiveMultiResolutionPyramidImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddConstantToImageFilter| Add a constant to every pixel in an image]] || {{ITKDoxygenURL|AddImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractConstantFromImageFilter| Subtract a constant from every pixel in an image]] || {{ITKDoxygenURL|SubtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquareImageFilter| Square every pixel in an image]] || {{ITKDoxygenURL|SquareImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Upsampling| Upsampling an image]] || {{ITKDoxygenURL|BSplineInterpolateImageFunction}} {{ITKDoxygenURL|ResampleImageFilter}} || Interpolate missing pixels in order to upsample an image. Note this only works on scalar images.<br />
|-<br />
| [[ITK/Examples/Images/FlipImageFilter | Flip an image over specified axes]] || {{ITKDoxygenURL|FlipImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/VectorRescaleIntensityImageFilter | Apply a transformation to the magnitude of vector valued image pixels]] || {{ITKDoxygenURL|VectorRescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/NeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image]] || {{ITKDoxygenURL|NeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Images/MaskNeighborhoodOperatorImageFilter | Apply a kernel to every pixel in an image that is non-zero in a mask]] || {{ITKDoxygenURL|MaskNeighborhoodOperatorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LaplacianImageFilter | Compute the Laplacian of an image]] || {{ITKDoxygenURL|LaplacianImageFilter}} || Input image type must be double or float<br />
|-<br />
| [[ITK/Examples/Images/ConstantPadImageFilter | Pad an image with a constant value]] || {{ITKDoxygenURL|ConstantPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/MirrorPadImageFilter | Pad an image using mirroring over the boundaries]] || {{ITKDoxygenURL|MirrorPadImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Images/WrapPadImageFilter | Pad an image by wrapping]] || {{ITKDoxygenURL|WrapPadImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/IntensityWindowingImageFilter| IntensityWindowingImageFilter]] || {{ITKDoxygenURL|IntensityWindowingImageFilter}} || Apply a linear intensity transform from a specified input range to a specified output range.<br />
|-<br />
| [[ITK/Examples/Images/ShrinkImageFilter | Shrink an image]] || {{ITKDoxygenURL|ShrinkImageFilter}} || Downsample an image<br />
|-<br />
| [[ITK/Examples/Images/NormalizedCorrelationImageFilter | Normalized correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/NormalizedCorrelationImageFilterMasked | Normalized correlation of a masked image]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyByConstantImageFilter | Multiply every pixel in an image by a constant]] || {{ITKDoxygenURL|MultiplyImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SquaredDifferenceImageFilter | Compute the squared difference of corresponding pixels in two images]] || {{ITKDoxygenURL|SquaredDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsoluteValueDifferenceImageFilter | Compute the absolute value of the difference of corresponding pixels in two images]] || {{ITKDoxygenURL|AbsoluteValueDifferenceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddPixelAccessor | Add a constant to every pixel without duplicating the image in memory (an accessor)]] || {{ITKDoxygenURL|AddPixelAccessor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMaximaImageFilter | ValuedRegionalMaximaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMaximaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ValuedRegionalMinimaImageFilter | ValuedRegionalMinimaImageFilter]] || {{ITKDoxygenURL|ValuedRegionalMinimaImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaximumImageFilter | Pixel wise compare two input images and set the output pixel to their max]] || {{ITKDoxygenURL|MaximumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumImageFilter | Pixel wise compare two input images and set the output pixel to their min]] || {{ITKDoxygenURL|MinimumImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AndImageFilter | Binary AND two images]] || {{ITKDoxygenURL|AndImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/OrImageFilter | Binary OR two images]] || {{ITKDoxygenURL|OrImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/XorImageFilter | Binary XOR (exclusive OR) two images]] || {{ITKDoxygenURL|XorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryNotImageFilter | Invert an image using the Binary Not operation]] || {{ITKDoxygenURL|BinaryNotImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/Compose3DCovariantVectorImageFilter | Compose a vector image (with 3 components) from three scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/NthElementImageAdaptor | Extract a component/channel of an itkImage with pixels with multiple components]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || Use built in functionality to extract a component of an itkImage with CovariantVector components. Note this does not work for itkVectorImages - see VectorIndexSelectionCastImageFilter instead.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ImageAdaptorExtractVectorComponent | Present an image by first performing an operation]] || {{ITKDoxygenURL|ImageAdaptor}} || A demonstration of how to present an image pixel as a function of the pixel. In this example the functionality of NthElementImageAdaptor is demonstrated.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ProcessingNthImageElement | Process the nth component/element/channel of a vector image]] || {{ITKDoxygenURL|NthElementImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConvolutionImageFilter | Convolve an image with a kernel]] || {{ITKDoxygenURL|ConvolutionImageFilter}} || Convolution.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ExtractImageFilter | Crop an image by specifying the region to keep]] || {{ITKDoxygenURL|ExtractImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/CropImageFilter | Crop an image by specifying the region to throw away]] || {{ITKDoxygenURL|CropImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/AbsImageFilter | Compute the absolute value of an image]] || {{ITKDoxygenURL|AbsImageFilter}} || magnitude<br />
|-<br />
| [[ITK/Examples/ImageProcessing/InvertIntensityImageFilter | Invert an image]] || {{ITKDoxygenURL|InvertIntensityImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskImageFilter | Apply a mask to an image]] || {{ITKDoxygenURL|MaskImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/MaskNegatedImageFilter | Apply the inverse of a mask to an image]] || {{ITKDoxygenURL|MaskNegatedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/SigmoidImageFilter | Pass image pixels through a sigmoid function]] || {{ITKDoxygenURL|SigmoidImageFilter}} || The qualitative description of how Alpha and Beta affect the function from the ITK Software Guide and the associated images would be nice to add to the doxygen.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|ThresholdImageFilter}} || The result is the original image but with the values below (or above) the threshold "clamped" to an output value.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryThresholdImageFilter | Threshold an image]] || {{ITKDoxygenURL|BinaryThresholdImageFilter}} || The result is a binary image (inside the threshold region or outside the threshold region).<br />
|-<br />
| [[ITK/Examples/ImageProcessing/UnaryFunctorImageFilter | Apply a custom operation to each pixel in an image]] || {{ITKDoxygenURL|UnaryFunctorImageFilter}} || Perform a custom operation on every pixel in an image. This example rotates the vector-valued pixels by 90 degrees.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilter | Apply a predefined operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/ImageProcessing/BinaryFunctorImageFilterCustom | Apply a custom operation to corresponding pixels in two images]] || {{ITKDoxygenURL|BinaryFunctorImageFilter}} || This example computes the squared difference between corresponding pixels.<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MinimumMaximumImageCalculator | Find the minimum and maximum value (and the position of the value) in an image]] || {{ITKDoxygenURL|MinimumMaximumImageCalculator}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/AddImageFilter | Add two images together]] || {{ITKDoxygenURL|AddImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/SubtractImageFilter | Subtract two images]] || {{ITKDoxygenURL|SubtractImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PasteImageFilter | Paste a part of one image into another image]] || {{ITKDoxygenURL|PasteImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_CreateVolume | Stack multiple 2D images into a 3D image]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/TileImageFilter_SideBySide | Tile multiple images side by side]] || {{ITKDoxygenURL|TileImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/MultiplyImageFilter | Multiply two images together]] || {{ITKDoxygenURL|MultiplyImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RegionOfInterestImageFilter | Extract a portion of an image (region of interest)]] || {{ITKDoxygenURL|RegionOfInterestImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RescaleIntensityImageFilter | Rescale the intensity values of an image to a specified range]] || {{ITKDoxygenURL|RescaleIntensityImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/NormalizeImageFilter | Normalize an image]] || {{ITKDoxygenURL|NormalizeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/CastImageFilter | Cast an image from one type to another]] || {{ITKDoxygenURL|CastImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ClampImageFilter | Cast an image from one type to another but clamp to the output value range]] || {{ITKDoxygenURL|ClampImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/PermuteAxesImageFilter | Switch the axes of an image]] || {{ITKDoxygenURL|PermuteAxesImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/LinearInterpolateImageFunction | Linearly interpolate a position in an image]] || {{ITKDoxygenURL|LinearInterpolateImageFunction}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/HammingWindowFunction | HammingWindowFunction]] || {{ITKDoxygenURL|HammingWindowFunction}} ||<br />
|}<br />
<br />
==Vector Images==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorMagnitudeImageFilter | Compute the magnitude of each pixel in a vector image to produce a magnitude image]] || {{ITKDoxygenURL|VectorMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImage | Create a vector image]] || {{ITKDoxygenURL|VectorImage}} || An image with an ND vector at each pixel<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Create a vector image from a collection of scalar images]] || {{ITKDoxygenURL|ComposeImageFilter}} || Combine, layer<br />
|-<br />
| [[ITK/Examples/VectorImages/VectorImageToImageAdaptor | View a component of a vector image as if it were a scalar image]] || {{ITKDoxygenURL|VectorImageToImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/VectorImages/VectorIndexSelectionCastImageFilter | Extract a component/channel of a vector image]] || {{ITKDoxygenURL|VectorIndexSelectionCastImageFilter}} || This works with VectorImage as well as Image<Vector><br />
|-<br />
| [[ITK/Examples/VectorImages/VectorResampleImageFilter | Translate a vector image]] || {{ITKDoxygenURL|TranslationTransform}}, {{ITKDoxygenURL|VectorResampleImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/JoinImageFilter | Join images, stacking their components]] || {{ITKDoxygenURL|JoinImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/ImageToVectorImageFilter | Stack scalar images into a VectorImage]] || {{ITKDoxygenURL|ImageToVectorImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/VectorImages/NeighborhoodIterator | NeighborhoodIterator on a VectorImage]] || {{ITKDoxygenURL|VectorImage}} {{ITKDoxygenURL|NeighborhoodIterator}}||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorCastImageFilter | Cast a VectorImage to another type of VectorImage]] || {{ITKDoxygenURL|VectorImage}} ||<br />
|}<br />
<br />
==Iterating Over (Traversing) An Image==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator_Manual | Iterate over a region of an image with a shaped neighborhood]] || Create the shape manually {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ShapedNeighborhoodIterator | Iterate over a region of an image with a shaped neighborhood]] || Create the shape from a StructuringElement {{ITKDoxygenURL|ShapedNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionExclusionConstIteratorWithIndex | Iterator over an image skipping a specified region]] || {{ITKDoxygenURL|ImageRegionExclusionConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomConstIteratorWithIndex | Randomly select pixels from a region of an image]] || {{ITKDoxygenURL|ImageRandomConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/ImageRandomNonRepeatingConstIteratorWithIndex | Randomly select pixels from a region of an image without replacement]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Iterators/LineIterator | Iterate over a line through an image]] || {{ITKDoxygenURL|LineIterator}} || Walks a Bresenham line through an image (with write access)<br />
|-<br />
| [[ITK/Examples/Iterators/LineConstIterator | Iterate over a line through an image without write access]] || {{ITKDoxygenURL|LineConstIterator}} || Walks a Bresenham line through an image (without write access)<br />
|-<br />
| [[ITK/Examples/Iterators/ImageBoundaryFacesCalculator | Iterate over the central region (non-boundary) separately from the face-regions (boundary)]] || {{ITKDoxygenURL|ImageBoundaryFacesCalculator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/NeighborhoodIterator | Iterate over a region of an image with a neighborhood (with write access)]] || {{ITKDoxygenURL|NeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstNeighborhoodIterator | Iterate over a region of an image with a neighborhood (without write access)]] || {{ITKDoxygenURL|ConstNeighborhoodIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIterator | Iterate over a region of an image (with write access)]] || {{ITKDoxygenURL|ImageRegionIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIterator | Iterate over a region of an image (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIterator}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ConstantBoundaryCondition | Make out of bounds pixels return a constant value]] || {{ITKDoxygenURL|ConstantBoundaryCondition}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (with write access)]] || {{ITKDoxygenURL|ImageRegionIteratorWithIndex}} ||<br />
|-<br />
| [[ITK/Examples/Iterators/ImageRegionConstIteratorWithIndex | Iterate over a region of an image with efficient access to the current index (without write access)]] || {{ITKDoxygenURL|ImageRegionConstIteratorWithIndex}} ||<br />
|}<br />
<br />
==Kernels==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Operators/GaussianOperator | Create a Gaussian kernel]] || {{ITKDoxygenURL|GaussianOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/GaussianDerivativeOperator | Create a Gaussian derivative kernel]] || {{ITKDoxygenURL|GaussianDerivativeOperator}} ||<br />
|-<br />
| [[ITK/Examples/Operators/LaplacianOperator | Create a Laplacian kernel]] || {{ITKDoxygenURL|LaplacianOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/DerivativeOperator | Create a derivative kernel]] || {{ITKDoxygenURL|DerivativeOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/SobelOperator | Create the Sobel kernel]] || {{ITKDoxygenURL|SobelOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/ForwardDifferenceOperator | Create a forward difference kernel]] || {{ITKDoxygenURL|ForwardDifferenceOperator}} || <br />
|-<br />
| [[ITK/Examples/Operators/BackwardDifferenceOperator | Create a backward difference kernel]] || {{ITKDoxygenURL|BackwardDifferenceOperator}} || <br />
<br />
|}<br />
<br />
==Image Edges, Gradients, and Derivatives==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/SobelEdgeDetectionImageFilter | SobelEdgeDetectionImageFilter]] || {{ITKDoxygenURL|SobelEdgeDetectionImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/DerivativeImageFilter | Compute the derivative of an image in a particular direction]] || {{ITKDoxygenURL|DerivativeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientRecursiveGaussianImageFilter| Compute the gradient of an image by convolution with the first derivative of a Gaussian]] || {{ITKDoxygenURL|GradientRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeRecursiveGaussianImageFilter | Find the gradient magnitude of the image first smoothed with a Gaussian kernel]] || {{ITKDoxygenURL|GradientMagnitudeRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/RecursiveGaussianImageFilter | Find higher derivatives of an image]] || {{ITKDoxygenURL|RecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryContourImageFilter | Extract the boundaries of connected regions in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} || Blob boundary, border<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/BinaryBoundaries | Extract the inner and outer boundaries of blobs in a binary image]] || {{ITKDoxygenURL|BinaryContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/GradientMagnitudeImageFilter | Compute the gradient magnitude image]] || {{ITKDoxygenURL|GradientMagnitudeImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/EdgesAndGradients/LaplacianRecursiveGaussianImageFilter | Compute the Laplacian of Gaussian (LoG) of an image]] || {{ITKDoxygenURL|LaplacianRecursiveGaussianImageFilter}} ||<br />
|}<br />
<br />
==Smoothing==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Smoothing/AntiAliasBinaryImageFilter | Anti alias a binary image]] || {{ITKDoxygenURL|AntiAliasBinaryImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/MeanImageFilter | Mean filter an image]] || {{ITKDoxygenURL|MeanImageFilter}} || Replace each pixel by the mean of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/MedianImageFilter | Median filter an image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/RGBMedianImageFilter | Median filter an RGB image]] || {{ITKDoxygenURL|MedianImageFilter}} || Replace each pixel by the median of its neighborhood<br />
|-<br />
| [[ITK/Examples/Smoothing/DiscreteGaussianImageFilter | Smooth an image with a discrete Gaussian filter]] || {{ITKDoxygenURL|DiscreteGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BinomialBlurImageFilter | Blur an image]] || {{ITKDoxygenURL|BinomialBlurImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/BilateralImageFilter | Bilateral filter an image]] || {{ITKDoxygenURL|BilateralImageFilter}} || Edge preserving smoothing.<br />
|-<br />
| [[ITK/Examples/Smoothing/CurvatureFlowImageFilter | Smooth an image using curvature flow]] || {{ITKDoxygenURL|CurvatureFlowImageFilterType}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/MinMaxCurvatureFlowImageFilter | Smooth an image using min/max curvature flow]] || {{ITKDoxygenURL|MinMaxCurvatureFlowImageFilterType}} ||<br />
|-<br />
| [[ITK/Examples/Smoothing/SmoothingRecursiveGaussianImageFilter | Gaussian smoothing that works with image adaptors]] || {{ITKDoxygenURL|SmoothingRecursiveGaussianImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Smoothing/VectorGradientAnisotropicDiffusionImageFilter | Smooth an image while preserving edges]] || {{ITKDoxygenURL|VectorGradientAnisotropicDiffusionImageFilter}} || Anisotropic diffusion.<br />
|}<br />
<br />
==Morphology==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Morphology/BinaryErodeImageFilter | Erode a binary image]] || {{ITKDoxygenURL|BinaryErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryDilateImageFilter | Dilate a binary image]] || {{ITKDoxygenURL|BinaryDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryPruningImageFilter | Prune a binary image]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalOpeningImageFilter | Opening a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalOpeningImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryMorphologicalClosingImageFilter | Closing a binary image]] || {{ITKDoxygenURL|BinaryMorphologicalClosingImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleDilateImageFilter | Dilate a grayscale image]] || {{ITKDoxygenURL|GrayscaleDilateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/GrayscaleErodeImageFilter | Erode a grayscale image]] || {{ITKDoxygenURL|GrayscaleErodeImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Morphology/FlatStructuringElement | Erode a binary image using a flat (box) structuring element]] || {{ITKDoxygenURL|FlatStructuringElement}} || <br />
|-<br />
| [[ITK/Examples/Morphology/BinaryBallStructuringElement | An elliptical structuring element]] || {{ITKDoxygenURL|BinaryBallStructuringElement}} || <br />
|}<br />
<br />
==Curves==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Curves/ContourMeanDistanceImageFilter | Compute the mean distance between all points of two curves]] || {{ITKDoxygenURL|ContourMeanDistanceImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Curves/PolyLineParametricPath | A data structure for a piece-wise linear curve]] || {{ITKDoxygenURL|PolyLineParametricPath}} || <br />
|}<br />
<br />
==Spectral Analysis==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/VnlFFTRealToComplexConjugateImageFilter | Compute the FFT of an image]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}} || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/CrossCorrelationInFourierDomain | Compute the cross-correlation of two images in the Fourier domain]] || {{ITKDoxygenURL|VnlFFTRealToComplexConjugateImageFilter}}{{ITKDoxygenURL|VnlFFTComplexConjugateToRealImageFilter}} || || <br />
|-<br />
| [[ITK/Examples/SpectralAnalysis/RealAndImaginaryToComplexImageFilter | Convert a real image and an imaginary image to a complex image]] || {{ITKDoxygenURL|ComposeImageFilter}} || <br />
|}<br />
<br />
==Utilities==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Utilities/CreateImageWithSameType | Create another instance of an image]] || ||<br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Create another instance of the same type of object]] || ||<br />
|-<br />
| [[ITK/Examples/Broken/Utilities/NonSmartPointers | Using non-smart pointers]] || {{ITKDoxygenURL|Image}}<br />
|-<br />
| [[ITK/Examples/Utilities/NumericSeriesFileNames | Create a list of file names]] || {{ITKDoxygenURL|NumericSeriesFileNames}} || <br />
|-<br />
| [[ITK/Examples/Utilities/CreateAnother | Copy a filter]] || {{ITKDoxygenURL|Object}} || Copy/duplicate a filter<br />
|-<br />
| [[ITK/Examples/Utilities/AzimuthElevationToCartesianTransform | Cartesian to AzimuthElevation and vice-versa]] || {{ITKDoxygenURL|AzimuthElevationToCartesianTransform}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/FixedArray | C-style array]] || {{ITKDoxygenURL|FixedArray}} ||<br />
|-<br />
| [[ITK/Examples/Utilities/DeepCopy | Deep copy an image]] || || <br />
|-<br />
| [[ITK/Examples/Utilities/RandomPermutation | Permute a sequence of indices]] || {{ITKDoxygenURL|ImageRandomNonRepeatingConstIteratorWithIndex}} || <br />
|-<br />
| [[ITK/Examples/Utilities/MersenneTwisterRandomVariateGenerator | Random number generator]] || {{ITKDoxygenURL|MersenneTwisterRandomVariateGenerator}} || <br />
|-<br />
| [[ITK/Examples/Utilities/JetColormapFunctor | Map scalars into a jet colormap]] || {{ITKDoxygenURL|JetColormapFunctor}} || <br />
|-<br />
| [[ITK/Examples/Utilities/SimpleFilterWatcher | Monitor a filter]] || {{ITKDoxygenURL|SimpleFilterWatcher}} || See debug style information.<br />
|-<br />
| [[ITK/Examples/Utilities/TimeProbe | Time probe]] || {{ITKDoxygenURL|TimeProbe}} || Compute the time between points in code. Timer. Timing.<br />
|-<br />
| [[ITK/Examples/Utilities/ObserveEvent | Observe an event]] || {{ITKDoxygenURL|Command}} || <br />
|-<br />
| [[ITK/Examples/Utilities/VectorContainer | Vector container]] || {{ITKDoxygenURL|VectorContainer}} || <br />
|}<br />
<br />
==Statistics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/MovingHistogramImageFilter | Compute histograms in a sliding window.]] || {{ITKDoxygenURL|MovingHistogramImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterRGB | Compute a histogram from an RGB image.]] || {{ITKDoxygenURL|HistogramToImageFilterRGB}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterVectorImage | Compute a histogram from a itk::VectorImage.]] || {{ITKDoxygenURL|HistogramToImageFilterVectorImage}} || <br />
|-<br />
| [[ITK/Examples/Statistics/HistogramToImageFilterGrayscale | Compute a histogram from a grayscale image.]] || {{ITKDoxygenURL|HistogramToImageFilterGrayscale}} || <br />
|-<br />
| [[ITK/Examples/Statistics/Histogram | Compute a histogram from measurements.]] || {{ITKDoxygenURL|Histogram}} || <br />
|-<br />
| [[ITK/Examples/Statistics/StatisticsImageFilter | Compute min, max, variance and mean of an Image.]] || {{ITKDoxygenURL|StatisticsImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/GaussianDistribution | Create a Gaussian distribution]] || {{ITKDoxygenURL|GaussianDistribution}} || <br />
|-<br />
| [[ITK/Examples/Statistics/SampleToHistogramFilter | Create a histogram from a list of sample measurements]] || {{ITKDoxygenURL|SampleToHistogramFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ListSample | Create a list of sample measurements]] || {{ITKDoxygenURL|ListSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageToListSampleAdaptor | Create a list of samples from an image without duplicating the data]] || {{ITKDoxygenURL|ImageToListSampleAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Statistics/MembershipSample | Create a list of samples with associated class IDs]] || {{ITKDoxygenURL|MembershipSample}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ExpectationMaximizationMixtureModelEstimator_2D | 2D Gaussian Mixture Model Expectation Maximization]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || EM<br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_1D | 1D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKMeansClustering_3D | 3D KMeans Clustering]] || {{ITKDoxygenURL|KdTreeBasedKMeansClustering}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTree | Spatial search]] || {{ITKDoxygenURL|KdTreeGenerator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ScalarImageKmeansImageFilter | Cluster the pixels in a greyscale image]] || {{ITKDoxygenURL|ScalarImageKmeansImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/NoiseImageFilter | Compute the local noise in an image]] || {{ITKDoxygenURL|NoiseImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Statistics/ImageKmeansModelEstimator | Compute kmeans clusters of pixels in an image]] || {{ITKDoxygenURL|ImageKmeansModelEstimator}} || <br />
|-<br />
| [[ITK/Examples/Statistics/KdTreeBasedKmeansEstimator | Compute kmeans clusters]] || {{ITKDoxygenURL|KdTreeBasedKmeansEstimator}} || <br />
|}<br />
<br />
==Spatial Objects==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/SpatialObjects/SpatialObjectToImageFilter | Convert a spatial object to an image ]] || {{ITKDoxygenURL|SpatialObjectToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/EllipseSpatialObject | Ellipse ]] || {{ITKDoxygenURL|EllipseSpatialObject}} ||<br />
|-<br />
| [[ITK/Examples/SpatialObjects/LineSpatialObject| Line spatial object]] || {{ITKDoxygenURL|LineSpatialObject}}, {{ITKDoxygenURL|LineSpatialObjectPoint}} || Specify a piecewise-linear object by specifying points along the line.<br />
|-<br />
| [[ITK/Examples/SpatialObjects/PlaneSpatialObject| Plane spatial object]] || {{ITKDoxygenURL|PlaneSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/SpatialObjects/BlobSpatialObject | Blob ]] || {{ITKDoxygenURL|BlobSpatialObject}} ||<br />
|}<br />
<br />
==Inspection==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Inspection/CheckerBoardImageFilter | Combine two images by alternating blocks of a checkerboard pattern]] || {{ITKDoxygenURL|CheckerBoardImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Inspection/PixelInspection | Printing a pixel value to the console]] || [http://www.itk.org/Doxygen/html/classitk_1_1Image.html#ad424c945604f339130b4ffe81b99738eGetPixel GetPixel] ||<br />
|}<br />
<br />
==Metrics==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Metrics/MeanSquaresImageToImageMetric | Compute the mean squares metric between two images ]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} ||<br />
|}<br />
==Image Registration==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Registration/WarpImageFilter | Warp one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|WarpImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Registration/LandmarkBasedTransformInitializer | Rigidly register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|LandmarkBasedTransformInitializer}} ||<br />
|-<br />
| [[ITK/Examples/Registration/DeformationFieldTransform | Register one image to another using manually specified landmarks ]] || {{ITKDoxygenURL|DeformationFieldTransform}} ||<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethod | A basic global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|TranslationTransform}} || Translation only transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodAffine | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|AffineTransform}} || Full affine transform.<br />
|-<br />
| [[ITK/Examples/Registration/ImageRegistrationMethodBSpline | A global registration of two images ]] || {{ITKDoxygenURL|ImageRegistrationMethod}}, {{ITKDoxygenURL|BSplineDeformableTransform}} || BSpline transform.<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformation | Mutual Information ]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|TranslationTransform}} || Global registration by maximizing the mutual information and using a translation only transform<br />
|-<br />
| [[ITK/Examples/Registration/MutualInformationAffine | Mutual Information Affine]] || {{ITKDoxygenURL|MutualInformationImageToImageMetric}}, {{ITKDoxygenURL|AffineTransform}} || Global registration by maximizing the mutual information and using an affine transform<br />
|}<br />
<br />
==Image Segmentation==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Segmentation/ContourExtractor2DImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|ContourExtractor2DImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/WatershedImageFilter| Watershed segmentation]] ||{{ITKDoxygenURL|WatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/MorphologicalWatershedImageFilter| Morphological Watershed segmentation]] ||{{ITKDoxygenURL|MorphologicalWatershedImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/EstimatePCAModel | Compute a PCA shape model from a training sample]] || {{ITKDoxygenURL|ImagePCAShapeModelEstimator}} ||<br />
Estimate the principal modes of variation of a shape from a training sample. Useful for shape guide segmentation.<br />
|-<br />
| [[ITK/Examples/Segmentation/MeanShiftClustering | Mean shift clustering]] || {{ITKDoxygenURL|SampleMeanShiftClusteringFilter}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/kMeansClustering | KMeans Clustering]] || ||<br />
|-<br />
| [[ITK/Examples/Segmentation/MultiphaseChanAndVeseSparseFieldLevelSetSegmentation | Multiphase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseSparseFieldLevelSetSegmentation | Single-phase Chan And Vese Sparse Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseSparseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/SinglephaseChanAndVeseDenseFieldLevelSetSegmentation | Single-phase Chan And Vese Dense Field Level Set Segmentation]] || {{ITKDoxygenURL|ScalarChanAndVeseDenseLevelSetImageFilter}}, {{ITKDoxygenURL|ScalarChanAndVeseLevelSetFunction}} ||<br />
|-<br />
| [[ITK/Examples/Segmentation/WishList/VoronoiDiagram2DGenerator | Voronoi diagram]] || {{ITKDoxygenURL|VoronoiDiagram2DGenerator}}, {{ITKDoxygenURL|VoronoiDiagram2D}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ConnectedComponentImageFilter | Label connected components in a binary image]] || {{ITKDoxygenURL|ConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/ScalarConnectedComponentImageFilter | Label connected components in a grayscale image]] || {{ITKDoxygenURL|ScalarConnectedComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageProcessing/RelabelComponentImageFilter | Assign contiguous labels to connected regions of an image]] || {{ITKDoxygenURL|RelabelComponentImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelContourImageFilter | Label the contours of connected components]] || {{ITKDoxygenURL|LabelContourImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ConfidenceConnectedImageFilter | Segment pixels with similar statistics using connectivity ]] || {{ITKDoxygenURL|ConfidenceConnectedImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToLabelMapFilter | Convert an itk::Image consisting of labeled regions to a LabelMap ]] || <br />
{{ITKDoxygenURL|LabelImageToLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/LabelImageToShapeLabelMapFilter | Convert an itk::Image consisting of labeled regions to a ShapeLabelMap ]] || {{ITKDoxygenURL|LabelImageToShapeLabelMapFilter}} ||<br />
|-<br />
| [[ITK/Examples/ImageSegmentation/ExtractLargestConnectedComponentFromBinaryImage | Extract the largest connected component from a Binary Image ]] || <br />
||<br />
|}<br />
<br />
==Meshes==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Meshes/Decimation | Decimation]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/AddPointsAndEdges | Add points and edges]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshNormalFilter | Compute normals of a mesh]] || {{ITKDoxygenURL|QuadEdgeMeshNormalFilter}} ||<br />
|-<br />
| [[ITK/Examples/Meshes/QuadEdgeMeshParameterizationFilter | Planar parameterization of a mesh]] || {{ITKDoxygenURL|ParameterizationQuadEdgeMeshFilter}} || Compute linear parameterization of a mesh homeomorphic to a disk on the plane<br />
|-<br />
| [[ITK/Examples/Meshes/ConvertToVTK | Convert an itk::Mesh to a vtkUnstructuredGrid]] || ||<br />
|-<br />
| [[ITK/Examples/Meshes/WishList/WriteMeshToVTP | Write an itk::Mesh to a vtp (vtkPolyData) file]] || {{ITKDoxygenURL|VTKPolyDataWriter}} ||<br />
|}<br />
<br />
==Need Demo==<br />
This section consists of examples which compile and work, but a good demonstration image must be selected and added.<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/NeedDemo/ImageProcessing/AdaptiveHistogramEqualizationImageFilter | Adaptive histogram equalization]] || {{ITKDoxygenURL|AdaptiveHistogramEqualizationImageFilter}} ||<br />
|}<br />
<br />
<br />
==Wish List==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/ScalarImageToTextureFeaturesFilter | Compute texture features]] || {{ITKDoxygenURL|ScalarImageToTextureFeaturesFilter}} || How to interpret the output?<br />
|-<br />
| [[ITK/Examples/WishList/LevelSets/SignedDanielssonDistanceMapImageFilter | Compute the signed distance function over an image]] || {{ITKDoxygenURL|SignedDanielssonDistanceMapImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/VectorImages/VectorImageResampleImageFilter | Resample an itk::VectorImage]] || ||<br />
|-<br />
| [[ITK/Examples/WishList/Segmentation/OtsuMultipleThresholdsCalculator | Compute Otsu thresholds]] || {{ITKDoxygenURL|OtsuMultipleThresholdsCalculator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Statistics/MaskedImageToHistogramFilter | Compute the histogram of a masked region of an image]] || {{ITKDoxygenURL|MaskedImageToHistogramFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/PointSet/BSplineScatteredDataPointSetToImageFilter | Fit a spline to a point set]] || {{ITKDoxygenURL|BSplineScatteredDataPointSetToImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Morphology/BinaryPruningImageFilter | BinaryPruningImageFilter]] || {{ITKDoxygenURL|BinaryPruningImageFilter}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/GaussianMixtureModelComponent | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|GaussianMixtureModelComponent}} ||<br />
|-<br />
| [[ITK/Examples/WishList/LevenbergMarquart| LevenbergMarquart]] || || <br />
|-<br />
| [[ITK/Examples/WishList/IterativeClosestPoints| IterativeClosestPoints]] || || <br />
|-<br />
| [[ITK/Examples/WishList/Operators/AllOperators| Demonstrate all operators]] || {{ITKDoxygenURL|NeighborhoodOperator}} || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/ColorNormalizedCorrelation| Color Normalized Correlation]] || {{ITKDoxygenURL|NormalizedCorrelationImageFilter}} || <br />
|-<br />
| [[ITK/Examples/WishList/SpatialObjects/ContourSpatialObject| ContourSpatialObject]] || {{ITKDoxygenURL|ContourSpatialObject}} || <br />
|-<br />
| [[ITK/Examples/Broken/SimpleOperations/MetaDataDictionary| Store non-pixel associated data in an image]] || {{ITKDoxygenURL|MetaDataDictionary}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/LevelSets| Level Sets]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation//RegionGrowing| Region Growing]] || || <br />
|-<br />
| [[ITK/Examples/Meshes/Subdivision| Mesh subdivision]] || || <br />
|-<br />
| [[ITK/Examples/Segmentation/OtsuThresholdImageFilter| Separate foreground and background using Otsu's method]] || {{ITKDoxygenURL|OtsuThresholdImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Segmentation/SimpleContourExtractorImageFilter| Extract contours from an image]] || {{ITKDoxygenURL|SimpleContourExtractorImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/RGBToVectorImageAdaptor| Present an image of RGBPixel pixels as an image of vectors]] || {{ITKDoxygenURL|RGBToVectorImageAdaptor}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DCirclesImageFilter| HoughTransform2DCirclesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DCirclesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Conversions/HoughTransform2DLinesImageFilter| HoughTransform2DLinesImageFilter]] || {{ITKDoxygenURL|HoughTransform2DLinesImageFilter}} || <br />
|-<br />
| [[ITK/Examples/Matlab/MatlabToITK| Write data from Matlab in a format readable by ITK]] || || <br />
|-<br />
| [[ITK/Examples/Matlab/ITKToMatlab| Write data from ITK in a format readable by Matlab]] || || <br />
|-<br />
| [[ITK/Examples/WishList/ImageProcessing/EdgePotentialImageFilter| Compute edge potential]] ||{{ITKDoxygenURL|EdgePotentialImageFilter}} || <br />
|}<br />
<br />
==Included in the ITK Repository==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Included/Registration| Image registration]] || || <br />
|}<br />
<br />
==Matlab==<br />
{{ITKExamplesTable}}<br />
<br />
|}<br />
<br />
==Developer Examples==<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Developer/Exceptions | Throw an exception]] || || <br />
|-<br />
| [[ITK/Examples/Developer/ImageSource | Produce an image programmatically.]] || {{ITKDoxygenURL|ImageSource}} || Nothing in, image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilter | Filter an image]] || {{ITKDoxygenURL|ImageToImageFilter}} || Image in, same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/OilPaintingImageFilter | Multi-threaded oil painting image filter]] || {{ITKDoxygenURL|ImageToImageFilter}} and {{ITKDoxygenURL|MinimumMaximumImageCalculator}} || A simple multi-threaded scenario (oil painting artistic filter). You can also use this class as-is (copy .h and .txx files into your project and use them).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputs | Write a filter with multiple inputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (same type), same type of image out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleInputsDifferentType | Write a filter with multiple inputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Two images in (different type), image (same type as first input) out.<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputs | Write a filter with multiple outputs of the same type.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (same type as first input).<br />
|-<br />
| [[ITK/Examples/Developer/ImageFilterMultipleOutputsDifferentType | Write a filter with multiple outputs of different types.]] || {{ITKDoxygenURL|ImageToImageFilter}} || Images in, two images out (different types).<br />
|-<br />
| [[ITK/Examples/Developer/SetGetMacro | Get or set a member variable of an ITK class.]] || || SetMacro, GetMacro<br />
|-<br />
| [[ITK/Examples/Developer/OutputMacros | Output an error, a warning, or debug information.]] || || DebugMacro, ErrorMacro, WarningMacro<br />
|}<br />
<br />
==Problems==<br />
===Small Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFilledImageFunctionConditionalIterator | Iterate over an image starting at a seed and following a rule for connectivity decisions]] || {{ITKDoxygenURL|FloodFilledImageFunctionConditionalIterator}} ||<br />
|-<br />
| [[ITK/Examples/WishList/Iterators/FloodFillIterator | Traverse a region using a flood fill iterator]] || {{ITKDoxygenURL|FloodFilledSpatialFunctionConditionalIterator}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/ImageProcessing/GradientOfVectorImage | Compute the gradient of a vector image]] || {{ITKDoxygenURL|GradientImageFilter}} || How to do this?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_Image | Compute distributions of image pixels using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ExpectationMaximizationMixtureModelEstimator_1D | Compute distributions of samples using GMM EM]] || {{ITKDoxygenURL|ExpectationMaximizationMixtureModelEstimator}} || Someone please confirm that this outputs the mean and the variance (i.e. I used a standard deviation of 30 to create the samples and the second estimated parameter is near 1000 (~30^2) . Is this correct?)<br />
|-<br />
| [[ITK/Examples/Broken/EdgesAndGradients/CannyEdgeDetectionImageFilter | Find edges in an image]] || {{ITKDoxygenURL|CannyEdgeDetectionImageFilter}} || How to set a reasonable Threshold for the output edges?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/ImageToHistogramFilter | Compute the histogram of an image]] || {{ITKDoxygenURL|Statistics_1_1ImageToHistogramFilter}} || The last entry of the red histogram should contain several values, but it is 0?<br />
|-<br />
| [[ITK/Examples/Broken/Statistics/KmeansModelEstimator | Classifying pixels using KMeans]] || {{ITKDoxygenURL|KmeansModelEstimator}} || How to apply the labels of the filter to the input image?<br />
|-<br />
| [[ITK/Examples/Broken/Images/RegionGrowImageFilter | Basic region growing]] || {{ITKDoxygenURL|RegionGrowImageFilter}} || Just getting started with demo...<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConnectedThresholdImageFilter | Find connected components in an image]] || {{ITKDoxygenURL|ConnectedThresholdImageFilter}} || Just need to finish it.<br />
|-<br />
| [[ITK/Examples/Broken/Images/ConvertPixelBuffer | Convert an image from one type to another]] || {{ITKDoxygenURL|ConvertPixelBuffer}} ||<br />
|-<br />
| [[ITK/Examples/Broken/Images/InPlace | In-place filtering of an image]] || {{ITKDoxygenURL|InPlaceImageFilter}} || This only works for filters which derive from itkInPlaceImageFilter<br />
|-<br />
| [[ITK/Examples/Broken/Images/VTKImageToImageFilter | Convert a VTK image to an ITK image]] || {{ITKDoxygenURL|VTKImageToImageFilter}} || Seems to expect an input image with only 1 component? (i.e. greyscale)<br />
|}<br />
<br />
===Big Problems===<br />
{{ITKExamplesTable}}<br />
|-<br />
| [[ITK/Examples/Broken/Images/MeanSquaresImageToImageMetric | Find the best position of the moving image in the fixed image.]] || {{ITKDoxygenURL|MeanSquaresImageToImageMetric}} || Output (0,0) is incorrect.<br />
|-<br />
| [[ITK/Examples/Broken/Images/GradientImageFilter | Compute and display the gradient of an image]] || {{ITKDoxygenURL|GradientImageFilter}} || Blank output on the screen (the filter works fine). There should be a "DisplayVectorImage" added to itkQuickView that draws vector glyphs at specified pixels of an image.<br />
|}</div>Ccagataybilgin