Pattern classification using a mixture of factor analyzers

This paper describes a practical application of a mixture of factor analyzers (MFA) to pattern recognition. The MFA extracts locally linear manifolds underlying given high dimensional data. In this respect, the NFA-based approach is similar to the conventional subspace methods that approximate the data space with low dimensional linear subspaces. However, the MFA-based classifier, unlike the conventional subspace methods, can perform classification based on the Bayes decision rule due to its probabilistic formulation. Experimental results show that the MFA-based approach can obtain better classification performance than the conventional subspace methods.