New face recognition method based on local binary pattern histogram

Abstract

Face recognition is one of the most important tasks in computer vision and biometrics where many algorithms have been developed. The Local Binary Pattern (LBP) has been proved to be effective for facial image representation and analysis, but it is too local to be robust. In this paper, we present an improved method for face recognition named Elongated Multi-Block Local Ternary Pattern (EMBLTP), which is based on Local Binary Pattern (LBP).The proposed method is tested on Yale face database and compared with different variants of LBP. Experimental results show that, the classification rate of the proposed method is appreciable.