Component Analysis Based Facial Expression Recognition

The Intelligence of Human-Computer Interaction is one of the hot researching areas. Facial expression recognition is an important part of human-computer interaction. At present, the research of facial expression recognition has entered an era of a new climax. In real-time facial expression recognition system, the paper presents an expression feature extraction method that combined canny operator edge detection with the AAM(active appearance model) algorithm. During the Canny edge detection, the adaptively generated high and low thresholds, increased the capability of noise suppression, and the time complexity of the algorithm is less than the traditional canny operator. Finally, by using leas squares method, we can classify and identify the feature information