[Insight-developers] Example and Documentation for Statistical Pattern Classification

[Jisung Kim]

Hi.

I checked in an example and a documentation for
statistical pattern classification.

The example is in the
Example/GaussianMinimumErrorClassification directory.
It is an implementation of Bayesian minimum error
classifier
that uses Gaussian density functions for 
class-conditional probabilities.

The documentation is now a chapter of the Users Guide 
which is in the InsightDocuments/User/UsersGuide
directory (you have to check out the InsightDocuments
repository using cvs). You can find the same thing on
my web page 
http://caddlab.rad.unc.edu/~jisung/StatisticalPatternClassificationHowto/StatisticalPatternClassificationHowto.html

I think the quick way to how the statistical pattern
classification components works together is look at
the 
"component connection diagram" for the Gaussian
minimum 
error classifier at the end of the document (in the 
"Example: Gaussian Minimum Error Classifier"
subsection 
<http://caddlab.rad.unc.edu/~jisung/StatisticalPatternClassificationHowto/node8.html>)

Still the document needs more works. It is intended to
be a short tutorial for someone who doesn't know much
about statistical classification, just like me :) So,
it is not a complete reference for ITK statistics 
components. It explains basic concepts and how
existing
components used (or connected) to be a classifier.

Merry Christmas,

Jisung



__________________________________________________
Do You Yahoo!?
Check out Yahoo! Shopping and Yahoo! Auctions for all of
your unique holiday gifts! Buy at http://shopping.yahoo.com
or bid at http://auctions.yahoo.com