RBF NEURAL NETWORKS APPLIED TO FACE TRACKING AND RECOGNITION

This paper describes a trainable system capable of detecting and tracking faces in video sequences. In developing this system, we have used a RBF neural network to locate and categorize faces of different dimensions. The face tracker can be applied to a video communication system which allows the users to move freely in front of the camera while communicating. The system works at several stages. At £rst, we extract useful parameters by a low-pass £ltering to compress data and we compose our codebook vectors. Then, the RBF neural network realizes detection and tracking of faces.