Lock-control is one of the most important security. This paper presents a face identification system for the lock-control. This system is robust for the fluctuation of the size and incline of face and lighting condition. There are two main processes in the face identification: 1) extraction of a face from input image and normalization of the size and incline of the face image, 2) matching of facial features (eye, nose and mouth) which is robust for lighting fluctuation. In order to achieve high reliability, the normalization process searches inner corners of eyes and then applies affine transformation to the face image according to the positions of the detected inner corners. The matching is performed on facial features by new template matching which uses 'sectionally adaptive correlation' for robustness against lighting fluctuation. Thresholds of the matching are determined by statistical estimation. When the system identifies a registered person, if unlocks the door. We have implemented this system and tarried out same experiments. The results show good feasibility of the lock control system and its robustness against lighting fluctuation.
展开▼
