Facial expression recognition based on local features and monogenic binary coding

Abstract

Fast developing facial expression reciognition is one of the significant recognition technologies for biological features with high applied value. In this study, a monogenic binary coding algorithm was considered to illustrate a good matching with local features through the analysis of monogenic signal theory and monogenic binary algorithm. Then, the results of the facial expression recognition simulation experiment of monogenic based classical facial expression database, the Japanese Female Facial Expression (JAFFE) Database, and the results of traditional Local Binary Patterns-Sparse Representation-based Classification (LBP-SRC) residual fusion method were compared to illustrate the efficiency of the monogenic binary coding algorithm in the aspect of facial recognition and to provide a basis for the application of the monogenic signal theory in facial expression.