Face Recognition by Regularized-LDA Using PRM

Face recognition has received an increased attention from several years in the field of image analysis, pattern recognition, and computer vision. In this paper we propose a method to the problem of face recognition. The proposed method consists of two stages. In the first stage regularized linear discriminant analysis is used to extract the most significant and discriminant features and then in the second stage, these features are used by probabilistic reasoning model for classification of unknown face images. Here two databases, the ORL database and the UMIST database are used for experiments and to show the performance of the proposed method.