An Efficient Head Pose Determination and its Application to Face Recognition Using Multi-pose Face DB and SVM

This paper proposes an efficient head pose determination method and its application to face recognition on a multi-pose face DB in order to solve the pose variation-related problem. The first step is to detect a facial region using Adaboost. Next, after undergoing preprocessing on the detected face, a mask covers it. At the detected facial region, the pose is determined by relations of the position of centroid points on the eyes and lip regions, which are detected by using the ellipse fitting method. Finally, we select Pose DB and SVM Classification that correspond to the point determined in input facial images. Then, we perform face recognition based on the learning data of the subject present in SVM Classification. It was found that recognition performance has been improved through the comparative experiment of the proposed method and the multi-view face recognition of the template matching algorithm using multi-view low-capacity DB.