Face Recognition Based on SFLBP
Zhisheng Gao, HongZhao Yuan · 2010
Face recognition under variable illumination conditions is an unsolved problem. In this paper, we propose a novel face recognition method based on steerable filters and local binary pattern. First, the normalized face image is convoluted by a multiple orientation steerable filters to extract their corresponding steerable magnitude maps (SMM). Then, the features of face image is extracted by linked all the LBP features which are computed on each item in the SMM separately. Finally, SVM (Support Vector Machine) is used for classification. Experiments show that our method is some invariant face position, pose, illumination and expression variations. Recognition results on ORL and YALE face database show the effectiveness of the proposed approach.