A Method Of Face Detection Based On Support Vector Machine

Research efforts in face information processing include face detection, face tracking, face recognition as well as derivative analysis of pose and expression. Face detection is a key technology of the filed of face information processing.Precision and rate are two important aspects of a face detection system. It is generally hoped that the system has high precision and rate simultaneously. However in reality precision and rate are in conflict with each other. Therefore it is of significance to do researches on how to upgrade the system rate under the predefined precision.In order to solve the above problems, in this dissertation, we first sum up and analyze current typical algorithms on face detection, and then present a multistage detection and conformed method from coarse to fine in order to find faces. First ,we base on the geometry connection of eyes, mouth and the lowest points to preelect faces in the skin area. And the experimentations prove that the method debases the leak (of) faces; Then we convert the region of faces to gray faces and use the SVM classifiers to exactly detect the real faces. We put forward a detection method that the front face detection classifier detects the front faces, and the profile classifier detects the side faces. Also the experimentations show that this method can advance the veracity of detection without immolating the detection rate.