[Insight-users] Re: About the Mutual information metric

[Luis Ibanez]

Hi Zhimin,

There are actually four different implementations
of the MutualInformation metric in ITK.

For a full list of the image metrics, please look at
the Doxygen documentation:

http://www.itk.org/Insight/Doxygen/html/modules.html


In particular to:

http://www.itk.org/Insight/Doxygen/html/group__RegistrationMetrics.html




You will find the following implementations of Mutual Information:

Viola-Wells
http://www.itk.org/Insight/Doxygen/html/classitk_1_1MutualInformationHistogramImageToImageMetric.html

Mattes
http://www.itk.org/Insight/Doxygen/html/classitk_1_1MattesMutualInformationImageToImageMetric.html

Kullback Leibler
http://www.itk.org/Insight/Doxygen/html/classitk_1_1KullbackLeiblerCompareHistogramImageToImageMetric.html


Normalized Mutual Information
http://www.itk.org/Insight/Doxygen/html/classitk_1_1NormalizedMutualInformationHistogramImageToImageMetric.html




All of them are based on building an estimation of the Joint Histogram.
What is different among them is the way the joint histogram is
estimated, and how the derivatives of the metric are computed.


If you are interested in developing new metrics related to
Mutual Information we will be happy to add them to the
toolkit.



Please let us know if you have further questions.



    Thanks



      Luis



-------------------
Jimmy Wong wrote:

> Dear Luis,
> 
> So far, there are only two metric for mutual information in registration 
> frame work, right? Does ITK provide the mutual information metric which 
> is based on the joint histogram?
> 
> Do let me know if there is one.
> 
> Thank you.
> 
> Zhimin
> 
> 
> 
>