Face recognition system based on neural networks and fuzzy logic

A face recognition system has been developed by integrating a neural network back error propagation learning algorithm with fuzzy logic technique in order to improve the decision making process. The upper and lower parts of the human face features are extracted for the face recognition process. Different weights are imposed on the features and in this study the upper-face feature has been given more weight than the lower-face feature by using a fuzzy logic technique. This system has been proven effective in developing a security system with high recognition rate for different human facial expressions. The security system reliability is improved further by employing smartcard technology as a first level protection in the system. Online recognition evaluation has shown that this security system is capable of identifying an authorized card owner and denying any potential intruder to the system. The system implemented on a PC was found to work satisfactorily; however the execution time needs to be improved