Real-time Facial Expression Recognition Based on Adaptive Canny Operator Edge Detection

In this paper, proposed a method of real-time facial expression recognition based on adaptive Canny operator edge detection. In this method, first used face location based on an adaptive skin color and structure model. Then, used facial expression feature extraction method based on adaptive Canny operator edge detection and AAM (Active Appearance Model) algorithm combined, which reduced the computational complexity and improved the accuracy of feature point location. During the using of Canny operator edge detection, the entire image was divided into multiple sub-images. And according to the edge gradient information of the sub-images, dynamic threshold was generated self-adaptively combined with the characteristics information of global edge gradient, which improved the edge detection results. Finally, used least -squares method to classify and identify the characteristics information. Experiments showed the effectiveness of this method in facial expression recognition and that it can meet the requirements in real-time systems.