[ITK-users] [ITK] intensity mapping between images

[Matt McCormick]

Hi Anja,

Yes, there is a nice implementation of b-spline based bias correction
[1].  Histogram equalization can also be useful [2].

Hope this helps,
Matt

[1] http://www.itk.org/Doxygen/html/classitk_1_1N4BiasFieldCorrectionImageFilter.html

[2] http://www.itk.org/Doxygen/html/classitk_1_1AdaptiveHistogramEqualizationImageFilter.html

On Thu, May 8, 2014 at 2:39 AM, Anja Ende <anja.ende at googlemail.com> wrote:
> Hello all,
>
> Something that one often does is use sum of square differences (SSD) as a
> measure of similarity between two images when performing image registration.
> One limiting assumption of SSD is that it assumes that the images differ by
> only Gaussian noise and that is usually not always the case.
>
> One thing that can be done is to determine a non-linear mapping between the
> image intensities by locally fitting a low order spline or polynomial. I was
> wondering if there is some filter in ITK to do this? Also, what about
> something like this non-linear intensity mapping along with some linear part
> (useful for also modelling the bias field in MRI images, for example).
>
> Hope someone can help me with this question.
>
> --
> Sincerely,
>
> 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
>