Facial expression recognition based on histogram sequence of local Gabor binary patterns

During the driving, the good emotion can benefit the vehicle safety. The good emotion will result in the certain facial expressions and vice versa. The facial expression is used as a useful cue to perform the surveillance of driverpsilas status. Considering the characteristics of driving safety, the facial expressions of anger, happiness, sadness and fear are investigated. The main contribution of this paper is to present a new facial expression recognition method based on the histogram sequence of local Gabor binary patterns. First, the Gabor coefficients maps (GCM) are extracted by convolving the face image with the multi-scale and multi-orientation Gabor filters. Then, the local binary pattern operator is performed on each GCM to extract the local Gabor binary pattern. Next, the face image is described using the histogram sequence of all these local Gabor binary patterns. Finally, the multi-class support vector machine (SVM) is used to perform the feature classification. The experimental results show that the facial expression recognition algorithm proposed in this paper is effective and superior to the other similar methods both in the recognition rate and speed.