[Insight-users] Mask, weight, ignore or reduce DOF in a registration process

[brian avants]

hi

yes - it is possible within the v4 registration framework.

http://www.itk.org/Doxygen/html/classitk_1_1ObjectToObjectOptimizerBase.html

SetWeights()<http://www.itk.org/Doxygen/html/classitk_1_1ObjectToObjectOptimizerBase.html#abc8e029387fef0d851dbf8cb0ec075e0>
allows
setting of a per-local-parameter weighting array. If unset, the weights are
treated as identity. Weights are multiplied by the gradient at the same
time scaling is applied. Weights are different than scales, and may be
used, for example, to easily mask out a particular parameter during
optimzation to hold it constant. Or they may be used to apply another kind
of prior knowledge.

there is an example in :

ITKv4/Modules/Numerics/Optimizersv4/test/itkGradientDescentOptimizerv4Test.cxx:
 itkOptimizer->SetWeights( weights );


brian




On Mon, May 6, 2013 at 9:59 AM, parseval <cabkai at web.de> wrote:

> Hello,
>
> does anybody know if it is possible to reduce the DOF or parameter search
> space for a given/knwon itk transformation or optimizer:
>
> For example I use a 3DEuler transformation and a gradient-descent optimizer
> but I don't want to search all 6 free parameters and lets say I want to
> ignore the translation in y direction.  So actually I only search in 5 DOF.
> With the setScales I can weight the free parameters, but is there a
> different way to weight a free parameter with approx. "zero".  (And of
> course if I really set the scale = 0, it crashs !)
>
> Is it possible with a simple trick, without writing a new transform class ?
> Many thanks and best regards,
> Parseval
> --> my first post. Please dont' hit me !
>
>
>
>
>
>
>
> --
> View this message in context:
> http://itk-users.7.n7.nabble.com/Mask-weight-ignore-or-reduce-DOF-in-a-registration-process-tp31346.html
> Sent from the ITK - Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> 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
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130506/33ea09c1/attachment.htm>