[Insight-users] RGBGibbsPriorFilter

[Luis Ibanez]

Hi Barry,

Yes, as you pointed out,
This filter is not up to the standards of ITK.

This is a very old contribution to the toolkit, that predates the
code quality control process that we have now in place for
accepting contributions.

Our process today is a lot more stringent:
http://www.itk.org/Wiki/ITK_Procedure_for_Contributing_New_Classes_and_Algorithms

Normally we would avoid moving a class that has been in the toolkit
for a long time, due to Backward Compatibility concerns, but
if you have established that the class is not functional we could
remove it, or at least move it out to the Code/Review directory.

Please note that we are also looking forward to a large scale
reorganization of the toolkit for ITK 4.0.

That will be an opportunity to get rid of many dead-weight classes,
as well as for removing any known Patented methods from the
toolkit.


     Regards,


           Luis


------------------------------------------------
On Mon, Oct 5, 2009 at 11:31 PM, Barry Branham <bhb at branham.ws> wrote:
> I have a project to segment the left ventricle endo and epi walls from MRI
> images.  After reading the ItkSoftwareGuide.pdf, the book "Insight into
> Images" and various papers on segmentation, several by Dimitris Metaxas and
> Ting Chen. I decided to try the hybrid method using Gibbs Prior and
> Deformable models.
>
> I've found several issues with RGBGibbsPriorFilter:
>
> 1. Although advertised as for 2 or 3D, It didn't work on 2D images (which I
> need because my images are 8mm apart).  I had to add an ImageDimension check
> in Allocate() and set m_ImageDepth = 1 if Dim==2.
>
> 2. Has ''#define RGBGibbsPriorFilterNeedsDebugging 1' and only does energy
> minimization if not #defined.  So are left with labeling based on membership
> functions from the classifier.
>
> 3. Has 'SetTrainingImage()', but doesn't use it.
>
> 4. Allocates a 'm_MediumImage', but doesn't use it.
>
> 5. Only uses the membership value of the first membership (seed) function,
> so can only use one seed.
>
> 6. Calls the classifier Update() function, gets the resulting classified
> image, then relabels it
> using membership function 1 (1st seed) so classifier results are ignored.
>
> I conclude that RGBGibbsFilter is unfinished.  I don't understand how it's
> not in the Review category.  Can anyone comment on this or know if anyone
> has done further work on this filter?
>
> Thanks,
> Barry Branham
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> 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
>