[Insight-users] itk::Statistics::MixtureModelComponentBase class to deal with t-Student distribution.

[Ricardo Ferrari]

Dear itk-users,

I am planing to extend the itk::Statistics::MixtureModelComponentBase class
to deal with t-Student distribution.

My questions are:

a) Does anybody have done this already or worked on something similar ?

b) Since t-student distribution is not not part of the *exponential* families,
can I still use the itk base-classes of the Expectation-Maximization
algorithm used to estimate the parameters of Gaussian Mixture Models ?


I would appreciate any help on this topic.


Thank you,

Ricardo


PS: I would like to thank you all for the great and important tool provided
for the biomedical imaging community. The ITK library has been the tool
that I have been using for my research and teaching purposes.


---------
Ricardo J. Ferrari, Ph.D. - Assistant Professor
Federal University of São Carlos
Rod. Washington Luís, Km 235
Caixa Postal 676 - 13565-905 São Carlos-SP - Brazil
Work Phone: +55 (16) 3306-6607  ;  Fax: +55 (16) 3351-8233
http://www.dc.ufscar.br/
---------
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.itk.org/pipermail/insight-users/attachments/20130211/bde3c1a9/attachment.htm>