Expectation Maximization of Gausian Mixture Models in VTK

Abstract

Expectation maximization (EM) is a common technique for estimating the parameters of a model after having collected observations of data generated by the model. We first explain the algorithm, then present our impelementation. We focus on estimation of the parameters of a Gaussian Mixture Model (GMM). The implementation is written in the VTK framework and is provided as a new class, vtkExpectationMaximization. The code is hosted here: http://github.com/daviddoria/ExpectationMaximization for the time being.

No source code files available for this publication.