[Insight-users] [Community] computing second derivative of deformation fields

[Matt McCormick]

Hi Anja,

Removing the selection with a RegionOfInterestImageFilter [1] should
achieve this task.

Hope this helps,
Matt


[1] http://www.itk.org/Doxygen/html/classitk_1_1RegionOfInterestImageFilter.html

On Fri, Oct 25, 2013 at 3:41 PM, Anja Ende <anja.ende at googlemail.com> wrote:
> Hello all,
>
> I am trying to code some registration stuff from scratch using itk. So, I
> have a dense deformation field and I can compute various similarity measures
> and now I want to regularize the deformation to ensure smooth deformations.
>
> From the literature, it seems one of the simple things to do is penalize the
> magnitude of the second derivative of the deformation. I see there are
> gradient filters available and I guess for the second derivative, I can pass
> the deformation field image to two gradient filters in succession and then
> compute the magnitude. However, I would like to use a mask in my
> computation. So areas under the mask should only be used and forward or
> backward differences should only be used at the edges, as appropriate.
>
> Is there a way to achieve this through existing filters?
>
> Thank you for any help you can give me.
>
>
> Cheers,
>
> Anja
>
> _____________________________________
> 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
>
> _______________________________________________
> Community mailing list
> Community at itk.org
> http://public.kitware.com/cgi-bin/mailman/listinfo/community
>