Security Assurance Using Face Recognition & Detection System Based On Neural Networks

In this paper, we have proposed a new method of implementing an assurance system using the facial information of the people, this is a different approach to the conventional security system which uses biometric information or cryptography for assurance, here we use an efficient self-scaling face recognition system supported with a face detection system, the system is capable enough to extract the human faces from a real time video and to recognize the people using a face recognition system, we are designing the framework for face recognition system with a hybrid RBF neural network, the real advantage of the system lies in its capability to inculcate some basic features of the self organizing map (SOM) so that the system can scale on its own and it doesn´t get outdated with time, for the face detection system we use a content based face detection algorithm, the facial feature so detected is inputted into the face recognition system, if the person´s information is already present in the system, authentication can be accomplished, this system can be used in public places like airports and supermarkets, the information of criminals can be stored in the system and in case any of the criminals are detected by the system, the security personnel can be signaled, this system can also be implemented in robotics, the system can help the computer to identify individual users distinctly, our facial recognition system has been tested and found to be persistent in recognizing the individual even if the input facial image is of different gesture or holds some extra lineament like beard, moustache or spectacles so we can definitely state that the system is reliable and efficient