A Novel Based Approach for Face Recognition

Face Recognition has been an active area over many years in do main of pattern recognition, image processing and computer vision. In general, principal co mponent analysis, quadratic discriminant analysis, linear discriminant analysis, statistical approaches are used for processing face recognition. Generally this reduces the number of features to be evaluated for the particular image, but it will degrade the accuracy of recognition because some feature will be helpful to recognize the faces. In this paper, we proposed the SIFT and SVM is used to recognize the faces with calculation of the fiduciary points that are used to tackle the face recognition problem. Also, we co mpare the performance of the proposed method with different availab le data-sets and real time faces.