Proposals:Refactoring Statistics Framework 2007 Background

The main components of a classification framework are

1. Input
   1. Image
   2. Data points
2. Membership function
   1. Distance functions
   2. Can be manually set or automatically generated from the sample data
   3. Estimators are available to generate membership functions ( ImageModelEstimatorBase, ImageGuassianModelEstimator,ExpectationMaximizationMixtureModelEstimator )
   4. Some classes are named with Estimator suffix but they do more than just estimating membership functions
      1. itkKdTreeBasedKmeansEstimator
3. Decison Rule (Classifier ): such as

Typical scenario

1. Use an estimator to generate class models for input data.
2. Use the generated class models, distance function and a decision rule to determine which class your

input belongs to.