[Insight-users] Unable to run ItkImageGaussianModelEstimator example

[Luis Ibanez]

Hi Ramakrishna,

Could you please give us more details on the kind of
processing you want to perform.

 From your previous posting we guessed that you were
interested on classified clusters in a parameteric
space. However from your last message it seems that
your data is directly in the image space and you want
to separate objects in the image space as opposed to
clusters in a parametric space.

Are your objects already segmented  ?

Could you post a representative image on the web, so
we can have a better idea of what you want to achieve.

If what you are targeting is shape analysis in the
image space, you may have better chances using
mathematical morphology operators and/or level set
filters (e.g. taking advantage of the curvature
scaling).


Please let us know,


   Regards,


     Luis


----------------------
CSPL wrote:
> Dear Mr.Sayan,
>  
> I want to split the objects on shape basis.The shape is convex.I have 
> gone through the Itk classe ItkImageGaussianModelEstimator.I got one 
> exmple to run .I want to know the output of the example.It is giving 
> exception in itkImageGaussianEstimator class update function.I have set 
> the parameters as follows..How to create train image.Please give me 
> suggestion to run the application properly.
> Example is  Insight\Examples\Segmentation\GibbsPriorImageFilter1.cxx.
>  
>   typedef itk::ImageGaussianModelEstimator<VecImageType,
>     MembershipFunctionType, ClassImageType>
>     ImageGaussianModelEstimatorType;
>  
>   ImageGaussianModelEstimatorType::Pointer
>     applyEstimateModel = ImageGaussianModelEstimatorType::New(); 
>  
>   applyEstimateModel->SetNumberOfModels(3);
>   applyEstimateModel->SetInputImage(vecImage);
>   applyEstimateModel->SetTrainingImage(trainingimagereader->GetOutput()); 
>  
> 
>  
>   //Run the gaussian classifier algorithm
>   try
>   {
>  applyEstimateModel->Update();///here program is getting exception.
>   }
>   catch(itk::ExceptionObject &exp)
>   {
>    std::cerr<<"Exception caught"<<std::endl;
>    std::cerr<<exp<<std::endl;
>   }
>  
> 
> Thanking you,
> Regards,
> Ramakrishna