[ITK-users] Finding 4 neighbors of a label object‏

[Niels Gerkien]

Hi guys,
I managed to get the 4-neighbors pixels following Bradley tips, using a BinaryDilateImageFilter with a cross structuring element and subtracting the binary image from the image resulting from the dilation. Now I would need your help for another task. Now that I know where my different sets of 4-neighbors and their contours are, I need to extract the minimum intensity value of each contours and the mean value of each set from the original image. What is the best way to do so? Sorry for all these questions, but I just started studying these things!!
Thanks a lot,Niels 
From: nielsgerkien80 at outlook.com
To: blowekamp at mail.nih.gov
Date: Wed, 21 May 2014 16:18:33 +0000
CC: insight-users at itk.org
Subject: Re: [ITK-users] Finding 4 neighbors of a label object‏




Thank you very much Brad!!

Subject: Re: [ITK-users] Finding 4 neighbors of a label object‏
From: blowekamp at mail.nih.gov
Date: Wed, 21 May 2014 08:12:41 -0400
CC: insight-users at itk.org
To: nielsgerkien80 at outlook.com

Hello,
I would look into using the BinaryDilateImageFilter[1] and the BinaryErodeImageFilter[2] with a Cross Flat structuring element[3].
And then there is the BinaryMorphologicalOpeningImageFilter[4] which could be used to remove these unwanted voxel.
I'd recommend trying to uses the filters in an interactive environment such an SimpleITK with ipython to explore the parameters and understand what they do.
Hope that helps,Brad
[1] http://www.itk.org/Doxygen/html/classitk_1_1BinaryDilateImageFilter.html[2] http://www.itk.org/Doxygen/html/classitk_1_1BinaryErodeImageFilter.html[3] http://www.itk.org/Doxygen/html/classitk_1_1FlatStructuringElement.html[4] http://www.itk.org/Doxygen/html/classitk_1_1BinaryMorphologicalOpeningImageFilter.html
On May 21, 2014, at 8:01 AM, Niels Gerkien <nielsgerkien80 at outlook.com> wrote:Hello everybody,
I would need your help on one thing. I have a 3D binary image coming from a binary thresholding. Now, considering the set of four-connected voxels, I need to find all the voxels that do not belong to these sets, but are 4-neighbors of a voxel belonging to this set. I also need to do it for different images obtained using different thresholds in the binary thresholding. Do you know if there is a fast way to do so? I tried creating a label map and then looking for all the voxels that do not belong to a label object and are next to a label voxel, but it takes a really long time. Especially for thresholds that give me many label objects.
I really appreciate your help!!
Niels_____________________________________
Powered by www.kitware.com

Visit other Kitware open-source projects at
http://www.kitware.com/opensource/opensource.html

Kitware offers ITK Training Courses, for more information visit:
http://www.kitware.com/products/protraining.php

Please keep messages on-topic and check the ITK FAQ at:
http://www.itk.org/Wiki/ITK_FAQ

Follow this link to subscribe/unsubscribe:
http://www.itk.org/mailman/listinfo/insight-users
 		 	   		  

_____________________________________
Powered by www.kitware.com

Visit other Kitware open-source projects at
http://www.kitware.com/opensource/opensource.html

Kitware offers ITK Training Courses, for more information visit:
http://www.kitware.com/products/protraining.php

Please keep messages on-topic and check the ITK FAQ at:
http://www.itk.org/Wiki/ITK_FAQ

Follow this link to subscribe/unsubscribe:
http://www.itk.org/mailman/listinfo/insight-users 		 	   		  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20140522/d31038d7/attachment.html>