[ITK-users] Optimization in deformable registration

Dženan Zukić dzenanz at gmail.com
Sun Dec 4 13:04:28 EST 2016


Hi Marie,

by looking at the documentation of Level-Set Motion Registration Filter
<https://itk.org/Doxygen/html/classitk_1_1LevelSetMotionRegistrationFilter.html>,
optimizer is not needed. The whole registration is set up as an iterative
process, executing motion equations at each iteration. You need to
experiment with it to see which number of iterations produces good results
for your case.

Regards,
Dženan

On Sun, Dec 4, 2016 at 9:15 AM, CocoM <cgo_2113 at hotmail.com> wrote:

> Hi everyone,
>
> Being fairly new in ITK, I have kind of a general question about deformable
> registration. I'm working with the LevelSetMotionRegistrationFilt
> er/Function
> classes and the example DeformableRegistration5, which is using them. I
> noticed this example doesn't use any optimizer class. It seems to be the
> same for the other PDEDeformable methods. So my question is : why? Is that
> because it's non parametric registration? And I guess there isn't any
> possibility to use an optimizer class in that kind of problem?
>
> Thanks a lot in advance,
>
> Marie
>
>
>
> --
> View this message in context: http://itk-insight-users.
> 2283740.n2.nabble.com/Optimization-in-deformable-
> registration-tp7589502.html
> Sent from the ITK Insight 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://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20161204/b5576364/attachment.html>


More information about the Insight-users mailing list