Expression Recognition Based on VLBP and Optical Flow Mixed Features

As sole feature extraction method cannot reflect comprehensive face emotional information in expression recognition, this article proposes one kind expression recognition method based on VLBP and optical flow mixed features. In this method, firstly it extracts block vlbp features of eye region. Then it detects feature points of mouth region automatically and extracts optical flow feature vector of these points. After that, in the recognition state, it uses fuzzy buried Markov model to compute expression probability for each region, finally applies the contribution weights obtained in the training stage to carry on the weighted-fusion and obtains the classification result. The experiment shows that our method get higher recognition rate than the methods which extract pure VLBP features or pure Optical Flow features from original image. And our method can be used for real-time facial expression recognition because of its high process speed.