[Insight-users] Mesaure quality of registration?

[motes motes]

Thanks for the reference! But why not just output the value of the metric?
When the registration is "perfect" the value of the metric is 0 and then
grows when the quality of the registration drops.



On Sat, Aug 8, 2009 at 7:22 PM, Luis Ibanez <luis.ibanez at kitware.com> wrote:

> Hi Motes,
>
> You may find interesting the following Insight Journal paper:
>
> http://www.insight-journal.org/browse/publication/166
> "A Framework for Comparison and Evaluation of Nonlinear
>  Intra-Subject Image Registration Algorithms"
>
> by
> Urschler M., Kluckner S., Bischof H.
>
>
>
>     Regards,
>
>
>            Luis
>
>
> -------------------------------------------------------
> 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
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20090810/566f6ad5/attachment.htm>