Traditional subspace methods for face recognition, from the original Eigenfaces technique to the recently introduced Laplacianfaces 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 Laplacianfaces method. Computer simulation shows that the proposed algorithm has better noise immunity and yields higher recognition rate compared with several conventional face recognition algorithms
Citation:
Xiaoyin Xu, Majid Ahmadi, "A Human Face Recognition System Using Neural Classifiers," cgiv, pp.354-357, Computer Graphics, Imaging and Visualisation (CGIV 2007), 2007