MULTILAYER PERCEPTRON, RADIAL BASIS FUNCTION NETWORK, AND SELF-ORGANIZING MAP IN THE PROBLEM OF FACE RECOGNITION

Miloš Oravec

   In this contribution, one and two-stage neural networks methods for face recognition are presented. For two-stage systems, the Kohonen self-organizing map is used as a feature extractor and multiplayer perceptron (MLP) or radial basis function (RBF) network are used as classifiers. The results of such recognition are compared with face recognition using a one-stage multilayer perceptron and radial basis function network classifiers.

Keywords: face recognition, feature extraction, classification, multilayer perceptron, radial-basis function network, self-organizing map

[full-paper]