An Improved LBP Method for Face Recognition

摘要

In order to improve the accuracy of human face recognition and reduce the computational complexity, we proposed a based Low Resolution Completed Local Binary Pattern method. Firstly, we used the preprocessed face images to extract the low resolution image during the filtering operation; then CLBP operator is used to extract the face gray image histogram; and fused into a CLBP histogram for comparison; finally the face image will be identified according to the proximity principle. The experimental results on ORL and AR show that the method has a better recognition effect, with shorter, more robust.