FACE RECOGNITION USING NEURAL NETWORKS WITH MULTIPLE COMBINATIONS OF CATEGORIES

Neural networks trained via backpropagation are now widely applied in a pattern recognition method. However, since it becomes much more diff icult for a network to accomplish its task when the number of categori es increases, research on multiple network combination is active. Nove l learning and recognition processes are proposed here. It is shown th at by combining small-scale neural networks, the proposed method allow s exploitation of the potential capabilities of the networks. In the l earning process, multiple networks are trained with patterns organized in overlapping groups. During the recognition process, response is ob tained by making the networks compete with each other. In experiments involving recognition of individuals from various facial images and di fferent expressions, a recognition rate of higher than 96 percent was obtained for 20 individuals and 131 images. Furthermore, results of si mulations in which noise was added confirmed that the proposed method is robust with respect to pattern changes.