Face Recognition using Neural Network and Eigenvalues with Distinct Block Processing

–Human face recognition has been employed in different commercial and law enforcement applications. It has also been employed for mug shots matching, bank-store security, crowd surveillance, expert identification, witness face reconstruction, electronics mug shots book, and electronic lineup. A face recognition system based on principal component analysis and neural networks has been developed. The system consists of three stages; preprocessing, principal component analysis, and recognition. In preprocessing stage, normalization illumination, and head orientation were performed. Principal component analysis is applied to obtained the aspects of face which are important for identification. Eigenvectors and eigenfaces are calculated from the initial face image set with the help of distinct block processing. New faces are projected onto the space expanded by eigenfaces and represented by weighted sum of the eigenfaces. These weights are used to identify the faces.Neural network is used to create the face database and recognize and authenticate the face by using these weights. In this paper, a separate network was developed for each person. The input face has been projected onto the eigenface space first and new descriptor is obtained. The new descriptor is used as input to each person’s network, trained earlier. The one with maximum output is selected and reported as the equivalent image.