Preprocessing for Local Bianry Pattern Based Face Recognition

Abstract

This paper studies the pre-processing methods on Local Binary Pattern (LBP) for face recognition. Three methods are well investigated, such as Gaussian smoothing, histogram equalization and Sobel operator. The extensive experiments on FERET database show that the best recognition rate increase is achieved by combination of histogram equalization, Gaussian smoothing, and Sobel with LBP. The conclusion achieved in the paper is useful for real face recognition system.