[Insight-users] Re: Landmark Based transform initializer

Karthik Krishnan Karthik.Krishnan at kitware.com
Fri May 20 13:00:29 EDT 2005


Hi Kevin,

The class as of now accepts only the Versor3DRigidTransform. I will add 
the corresponding 2D transform to it by tomorrow.
In 2D its pretty straightforward.

Thanks
regards
karthik


Kevin H. Hobbs wrote:

>On Thu, 2005-05-19 at 13:25 -0400, Kevin H. Hobbs wrote: 
>  
>
>>On Thu, 2005-05-19 at 12:01 -0400, Karthik Krishnan wrote:
>> We will try to add one for affine and corresponding rigid/affine ones for 2D, 
>>    
>>
>
>Will this class function at all for 2D images? Would 2D images with 2
>landmark points each, produce undefined, or just wrong, results?
>
>Something causes a segfault in the code using vtkLandmarkTransform that
>I posted yesterday,
>
>http://crab-lab.zool.ohiou.edu/kevin/Slice_Landmark_Registration/landmark_transform.cxx
>
>If I comment out line 55 or 59 so that the transform never gets to the
>reader, or is the identity transform, then the segfault goes away.
>
>I'm likely doing something stupid involving a 3D transform on 2D data.
>Does this mean the same thing would happen with the new ITK class?
>  
>
>------------------------------------------------------------------------
>
>_______________________________________________
>Insight-users mailing list
>Insight-users at itk.org
>http://www.itk.org/mailman/listinfo/insight-users
>  
>



More information about the Insight-users mailing list