[Insight-users] problem with itkVersorRigid3Dtransform

Luis Ibanez luis.ibanez at kitware.com
Sun Jul 11 09:59:01 EDT 2004


Hi Soumen,

Thanks for letting us know.

Yes, you should always us the VersorRigid3DTransformOptimizer
when you use the VersorRigidTransform.  The reason is that
Versor do not form a Vector space, and most other optimizer
assume that they are walking in a vector space.

Regards,



    Luis



-----------------
Soumen wrote:
> Hi!!!
> 
> Thnx for the reply.
> After downloading the recent ITK version the problem is solved.Actually I
> was using RegularStepGradientDecentOptimizer but in the recent version there
> is one called VersorRigid3DTransformOptimizer...using which solved the
> problem. But still couldnt figure out what was the problem with
> RegularStepGradientDecentOptimizer.
> Regrads
> 
> Soumen
> ----- Original Message -----
> From: "Luis Ibanez" <luis.ibanez at kitware.com>
> To: "Soumen" <soumend at magnum.barc.ernet.in>
> Cc: <insight-users at itk.org>
> Sent: Friday, July 09, 2004 8:22 PM
> Subject: Re: [Insight-users] problem with itkVersorRigid3Dtransform
> 
> 
> 
>>Hi Soumen,
>>
>>
>>What version of ITK are you using ?
>>
>>Please post a minimal code snippet where
>>you can reproduce this crashing behavior.
>>
>>
>>Thanks
>>
>>
>>    Luis
>>
>>
>>
>>-----------------
>>Soumen wrote:
>>
>>
>>>Hi all!!!
>>>
>>>
>>>I am trying to register two 3D images. Now if i use
>>>itkVersorRigid3Dtransform with mattesMImetric it works fine but crashes
>>>while exiting. But the same code with transform as
>>>CenteredAffineTransform works fine and exits gracefully. Now can anyone
>>>plz tell why this is happening?
>>>
>>>thnx
>>>
>>>soumen
>>>
>>>
>>>------------------------------------------------------------------------
>>>
>>>_______________________________________________
>>>Insight-users mailing list
>>>Insight-users at itk.org
>>>http://www.itk.org/mailman/listinfo/insight-users
>>
>>
>>
>>_______________________________________________
>>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