[Insight-users] RegistrationFunctions and Filters

[Jordi Inglada]

Hi,

Thanks for this! 

Open source is great. 

People doing open source are the greatest!

As I said in my previous message, I think I have managed to solve my
problem, but I will have a look at your code.

Thanks again.

Jordi

Le mercredi 24 septembre 2008 à 08:45 -0400, brian avants a écrit :
> hi jordi
> 
> the attached registration functions will work for you, i think.
> the functions expect that you will pass images that are in the
> same domain.  that is, you should warp the moving image to
> the fixed space, then compute the derivative, or vice versa.
> 
> these come from a non-rigid registration toolkit that we are
> developing and is also open-source.  the probabilistic registration
> function is actually cross-correlation.   needs a name change.
> 
> hope this helps - let me know if you have questions.   implementations
> are similar to those described by Peter Rogelj, G. Hermosillo, and
> in a media 2008 paper by avants, et al.
> 
> brian avants
> 
> 
> 
> On Wed, Sep 24, 2008 at 8:31 AM, Luis Ibanez <luis.ibanez at kitware.com> wrote:
> >
> > Hi Jordi,
> >
> >
> > You may want to look at the code in:
> >
> >          Insight/Examples/Registration
> >
> >
> > There is not really a RegistrationFilter in ITK, at least
> > not for the generic image registration framework.
> >
> > The closest to it, is the ImageRegistrationMethod class,
> > that you will see used in most of the examples in the
> > directory above.
> >
> >
> > What you want to do is to connect to this class one of
> > the following metrics:
> >
> > http://www.itk.org/Insight/Doxygen/html/classitk_1_1NormalizedCorrelationImageToImageMetric.html
> > http://www.itk.org/Insight/Doxygen/html/classitk_1_1MattesMutualInformationImageToImageMetric.html
> > http://www.itk.org/Insight/Doxygen/html/classitk_1_1MutualInformationImageToImageMetric.html
> >
> >
> > For a full list of Metrics, please look at:
> > http://www.itk.org/Insight/Doxygen/html/group__RegistrationMetrics.html
> >
> >
> > In the ITK Software Guide
> >
> >  http://www.itk.org/ItkSoftwareGuide.pdf
> >
> > in the "Image Registration" Chapter, you will find many
> > examples on how to use the registration framework.
> >
> >
> > Are you looking in particular for a Deformable registration method ?
> >
> >
> >  Please let us know
> >
> >
> >      Thanks
> >
> >
> >        Luis
> >
> >
> > ===================
> > Jordi Inglada wrote:
> >>
> >> Dear all,
> >>
> >> I am looking for a working example of a RegistrationFilter using either
> >> an MIRegistrationFunction or an NCCRegistrationFunction.
> >>
> >> I cannot find any in the Insight examples.
> >> I have been struggling with a MIRegistrationFunction and a
> >> PDEDeformableRegistrationFilter using the
> >> SetDifferenceFunction( metricFunction ) method, but all I get is a
> >> segfault.
> >>
> >> I have also tried the CurvatureRegistrationFilter, but the
> >> MIRegistrationFunction can work with it since it does not have a
> >> GetMetric method.
> >>
> >> Can anybody give me a hint on this?
> >>
> >> Thank you,
> >>
> >> Jordi
> >>
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org
> > http://www.itk.org/mailman/listinfo/insight-users
> >
-- 
CNES - DCT/SI/AP - BPI 1219
18, avenue Edouard Belin
31401 Toulouse Cedex 09 - France
Tel. +33.(0)5.61.27.33.97 - Fax. +33.(0)5.61.28.31.09