Face Recognition Based on Radial Basis Function Neural Networks

Abstract

The face recognition is an active subject in the area of computer pattern recognition, which has been a focus in reach for the last couple of decades because of its widely potential applications. A face recognition approach is put forward based on the RBF neural network. Also discussed are the problem of feature of a face image vector, the problem of normalization of the image-size, and the problem of training algorithm of hidden layerpsilas neural nodes. Experiments have been conducted on ORL face database. The results show that compared with BP neural network, the RBF neural network can decrease the error rate, the training time, and the recognition time efficiently.