Face recognition on the base of local directional patterns

Abstract

Local directional pattern (LDP) based methods for frontal face recognition are considered in this paper. LDP based face feature extraction and comparison methods and their performance results are given. The method for normalizing illuminations of face images is given. The results of experimental research of the developed algorithms are presented. The positive properties of LDP operator and recognition algorithms are determined. The comparative analysis of the results of recognition, which uses local operators, is done.