[Insight-users] Calculating a Similarity Measure.

[Luis Ibanez]

Hi Josiane,

Please read the Chapter on deformable
registration in the SoftwareGuide.

   htt://www.itk.org/ItkSoftwareGuide.pdf

Chapter 8, pdf-page 241-340.

Pay particular attention to section 8.1
describing the basic registration framework
and to section 8.12 describing the deformable
registration methods.


You will find that the methods described in
DeformableRegistration1.cxx and Deformable
Registration2.cxx do not belong to the basic
registration framework in ITK.


The DemonsRegistrationfilter has its own
method for returning the metric used for
the registration. This is indeed a mean
squares metric.

You will find in line 79 of

    Insight/Examples/Registration/
              DeformableRegistration2.cxx

the following code

    std::cout << filter->GetMetric() << std::endl;

where "filter" is the DemonsRegistrationFilter.



--

If what you want is to evaluate the final quality
of the registration, what you could do is to take
the fixed image and the warpped moving image (the
output of the WarpImageFilter) and pass them as
input to your arbitrary metric, using an Identity
transform...


--

Before you continue, I would *strongly* suggest
you to read the chapter on registration from
the SoftwareGuide and the Tutorials on registration

     http://www.itk.org/HTML/Tutorials.htm

Basic registration framework
http://www.itk.org/CourseWare/Training/RegistrationMethodsOverview.pdf

Deformable registration
http://www.itk.org/CourseWare/Training/NonRigidRegistrationMethods.pdf

I'm affraid that you are miss-interpreting the way
Metrics, Transforms and RegistrationMethods work
together.


Please let us know if you have further questions
after your reading.


    Thanks



      Luis


--------------------------------------------------------
Josiane Yankam Njiwa--DEA Clarysse--Fin 11/04 wrote:

> Hi
> 
> I want to calculate similarity measure in the case of using
> DeformableRegistration1.cxx and DeformableRegistration2.cxx.
> For the second example, i try to connect a metric to the warp filter and
> it doesn't work. I don't how to use the fact that i have a registration
> procedure to get my similarity measure.
> I have read carefully the registration examples, but i haven't solve my
> problème.
> Thank for you help.
> 
> Josiane
> 
> 
> 
>