A Human Face Recognition System Using Neural Classifiers

Abstract

Traditional subspace methods for face recognition, from the original eigenfaces technique to the recently introduced Laplacian faces method, measure the similarity between images after projecting them onto a face subspace. In this paper, we present a robust face recognition system that uses a neural classifier and Laplacian faces method. Computer simulation shows that the proposed algorithm has better noise immunity and yields higher recognition rate compared with several conventional face recognition algorithms.