SimpleITK/Advisory Review Board: Difference between revisions

From KitwarePublic
Jump to navigationJump to search
Line 72: Line 72:
* Resample the moving image using the computed transform
* Resample the moving image using the computed transform
* Write the resampled image out
* Write the resampled image out
=== Procedural ===
<pre>
// Open the fixed and moving images
itk::simple::ImageFileReader reader;
itk::simple::Image::Pointer fixedImage = reader.execute( "path/to/fixed.jpg" );
itk::simple::Image::Pointer movingImage = reader.execute( "path/to/moving.jpg" );
// Register the moving image to the fixed image
itk::simple::AffineRegistrator registrator;
itk::simple::AffineTransform transform;
transform = registrator.execute( fixedImage, movingImage );
// Resample the moving image
itk::simple::Resampler resampler;
movingImage = resampler.execute( movingImage, transform );
// Write out the resampled image
itk::simple::ImageFileWriter writer;
writer.ececute( movingImage, "path/to/output.png" );
</pre>


== Level Set ==
== Level Set ==

Revision as of 19:49, 2 September 2010

  • Harvey Cline, Kitware Inc.
  • Raghu Machiraju, The State University of Ohio
  • John Galeotti, CMU
  • Hans Johnson, University of Iowa
  • Fabrice de Chaumont, Pasteur Institute
  • New students in the UNC CISMM project (taylorr@cs.unc.edu)
  • Jesus Caban, NLM-NIH

ARB Prototype Code

Gaussian Blur

  • Open an image
  • Filter the image with a Gaussian blur using sigma = 2
  • Write the image back out

Option 1 - Fully procedural

// Read the image
itk::simple::ImageFileReader reader;
itk::simple::Image::Pointer im = reader.execute( "sample/path/to/image.jpg" );

// Apply Gaussian with sigma = 2
itk::simple::Gaussian filter;
im = filter.execute( im, 2 );

// Write out the image
itk::simple::ImageFileWriter writer;
writer.execute( im, "sample/path/to/output.png" );

Option 2 - Procedural with parameter setting

// Read the image
itk::simple::ImageFileReader reader;
reader.SetFilename( "sample/path/to/image.jpg" );
itk::simple::Image::Pointer im = reader.execute();

// Apply Gaussian with sigma = 2
itk::simple::Gaussian filter;
filter.SetSigma( 2 );
im = filter.execute( im );

// Write out the image
itk::simple::ImageFileWriter writer;
writer.SetFilename( "sample/path/to/output.png" );
writer.execute( im );

Option 3 - Pipelined

// Read the image
itk::simple::ImageFileReader reader;
reader.SetFilename( "sample/path/to/image.jpg" );

// Apply Gaussian with sigma = 2
itk::simple::Gaussian filter;
filter.SetSigma( 2 );
filter.SetInput( reader.getOutput() );

// Write out the image
itk::simple::ImageFileWriter writer;
writer.SetFilename( "sample/path/to/output.png" );
writer.SetInput( filter->GetOutput() );

// Update the pipieline
writer.Update();

Image Registration

  • Open two images (one fixed, one moving)
  • Register the moving image to the fixed image using affine registration
  • Resample the moving image using the computed transform
  • Write the resampled image out

Procedural

// Open the fixed and moving images
itk::simple::ImageFileReader reader;
itk::simple::Image::Pointer fixedImage = reader.execute( "path/to/fixed.jpg" );
itk::simple::Image::Pointer movingImage = reader.execute( "path/to/moving.jpg" );

// Register the moving image to the fixed image
itk::simple::AffineRegistrator registrator;
itk::simple::AffineTransform transform;
transform = registrator.execute( fixedImage, movingImage );

// Resample the moving image
itk::simple::Resampler resampler;
movingImage = resampler.execute( movingImage, transform );

// Write out the resampled image
itk::simple::ImageFileWriter writer;
writer.ececute( movingImage, "path/to/output.png" );

Level Set

Region Growing

Watershed

QuadEdgeMesh