[Insight-users] Mesaure quality of registration?

[Karthik Krishnan]

Unless the transform is invertible (and BSpline deformable transform isn't),
you'll have to measure either the mismatch of the each registered images
with baseline image - or - compare the deformation fields that result from
the 2 BSpline transforms.

For the latter, you can look at the following paper :

----
McCane, B., Novins, K., Crannitch, D. and Galvin, B., On Benchmarking
Optical Flow, Computer Vision and Image Understanding, 84(1), pp 126-143,
2001

Please see Section 5 titled Error Metrics in [1]. It provides 2 metrics to
compare deformation fields. It also surveys other metrics used to compare
deformation fields in literature and illustrates their shortcomings.

Their methods are openly available at
http://sourceforge.net/projects/of-eval/files/
----


--
karthik

On Mon, Aug 3, 2009 at 10:23 AM, motes motes <mort.motes at gmail.com> wrote:

> Based on some of the examples from the itkSoftwareguide I have implemented
> a BSplineDeformable registration application. I deform the 3D brain scans :
>
> http://public.kitware.com/pub/itk/Data/BrainWeb/BrainPart1.tgz
>
> and use those as the moving image input to the registration method. One way
> to measure the quality of the registration is to compute the difference
> images. But are there some more strict way to compute a measure and then
> compare that measure with another implementation of the BSplineDeformable
> registration application?
>
> I have read that some use intersections of the overlap but any other ideas
> or examples are most welcome!
>
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> 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
>
>


-- 
Karthik Krishnan
R&D Engineer,
Kitware Inc.
Ph: 518 881 4919
Fax: 518 371 4573
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20090805/150c3d83/attachment.htm>