A novel feature extraction method for facial expression recognition

In this work, a novel facial feature extraction method is proposed for automatic facial expressions recognition, which detecting local texture information, global texture information and shape information of the face automatically to form the facial features. First, Active Appearance Model (AAM) is used to locate facial feature points automatically. Then, the local texture information in these feature points and the global texture feature information of the whole face area are extracted based on the Local Binary Pattern (LBP) techniques, and also the shape information of the face are detected. Finally, all the information are combined together to form the feature vector. The proposed feature extraction method is tested by the JAFFE database and experimental results show that it is promising.