IMPLEMENTATION OF FACE RECOGNITION SYSTEM BASED ON ELASTIC BUNCH GRAPH MATCHING

The face is regarded as the primary means of identifying the person of a written document based on the implicit assumption that a person’s face changes slowly and is very difficult to erase, alter or forge without detection. As face is now a days the primary mechanism both for authentication and authorization in legal transactions, the need for efficient automated solutions for face reorganization has increased. This Project offers algorithm for the offline image reorganization system in which artificial neural network is used to confirm the genuineness of faces. We approach the problem in two steps. Initially a set of face images are obtained from the subject and fed to the system. These face images are preprocessed Then the preprocessed images are used to extract relevant geometric parameters that can identify faces of different persons. These are used to train the system. The mean value of these features is obtained. In the next step the face image to be verified is fed to the system. It is preprocessed to be suitable for extracting features. It is fed to the system and various features are extracted from them. These values are then compared with the mean features that were used to train the system. The distance is calculated and a suitable threshold per user is chosen. Depending on whether the input face image satisfies the threshold condition the system either accepts or rejects the face image. Perform pattern matching with the test data set present in the hidden layer of neural network. Using outcome produced by the output layer of the neural network announces that image is match or not.