[Proposal }FACE RECOGNITION USING NEURAL NETWORK

ABSTRACT

Face recognition is a challenging computer vision problem. Given a still image or an image sequence, the goal of face recognition is to locate all regions that contain a face regardless of any transformation and lighting condition. There are two main categories that may serve as a solution for this problem: feature~ based and image~based approaches. In this project, we have used an image~based and learning oriented solution. We have also tried to locate and detect different facial features. We have paid attention to eye because in facial feature extraction system eye recognition is taken as a reference. We have also used a feature based approach that uses human face model constructed from relative geometrical relation among facial organs on a face for this purpose. Recognition is performed by projecting a new image into the subspace spanned by the eigenfaces and then classifying the face by comparing its position in face space with the positions of known individuals. Thus performing the complete steps in matching any face to the face database becomes a useful application in banking system, organization implementing secure entrance of people, authentication to access into certain privileged domain or facilities.