Pyramid Representation for Face Recognition

In this paper we propose a new face recognition system based on a biologically-inspired filtering method. Our work differs from previous proposals in (1) the multi-stage filtering method employed, in (2) the pyramid structure used, and most importantly, in (3) the prototype construction scheme to determine the models stored in memory. The method is much simpler than previous proposals and relatively inexpensive computationally, while attaining error rates as low as 5%, very close to the best reported results. 1 Introduction Automatic face recognition is an extremely important task. Boosted by commercial demands for face recognition systems, a wide range of proposals has been advanced in the the present decade. Starting with the influential Eigenfaces approach by Turk and Pentland [10], a number of approaches have attained high levels of performance in face databases, in many cases with recognition rates over 90%. Besides the successful Eigenfaces approach, researchers have proposed th..