Facial expression recognition based on local binary patterns and coarse-to-fine classification

Automatic facial expression recognition for novel individuals from static images is a challenge task to pattern analysis research community. In this paper, we present an effective method for this task. We analyze seven basic expressions: angry, disgust, fear, happiness, neutral, sadness and surprise. First, the local binary pattern (LBP) operator is used to extract face appearance features. Then a two-stage classification method is proposed. At the first (coarse classification) stage, two expression candidates from initial seven are selected. At the second (fine classification) stage, one of the two candidate classes is verified as final expression class. Our algorithm is tested on the JAFFE database and promising results are obtained.