A New Paradigm of Face Recognition Using Multi-class Classifier

Abstract

Eminent applications for security and law enforcement have enhanced significant importance of automatic face recognition. Face recognition is one of the most convenient ways for identification and recognition of a person in considerable large database. The face recognition complications are due to change in illumination of light sources, variations in pose as well as facial expressions. This paper will present a novel approach of hybrid face recognition technique. The face recognition system is developed with PCA and SVM as multi class classifier. The experiments of the proposed method have been conducted on ORL data sets. The experiment result is presented and discussed, which shows the effectiveness of the strategy described.