Study On Face Detection And Tracking Algorithm

Real-time face detection and face tracking in complex background is a study field of Biometric features identification technique, It includes image obtain, image pretreatment, face detection and face tracking etc.In this paper we first introduce some methods of image pretreatment, then introduce some face detection methods. Aims at application, we mainly discuss face detection in two circumstance.(1)In the gray image, we use difference image in multi-frames, then get the edge of the face ,we make the raw-location to ensure the approximate position of the face, next ,we use the template of the face to occlude the pseudo face region and get the region which near the exact face region.(2)Use method of two template matching, first, we get the face template from many face average, second, we copy the eye section of the face template then get the eye template. In the course of face detection, we first use eye template to search face in image, if the result meet our request, then we can use the face template to search face further. Among the face tracking algorithm, we first use difference image to gain the raw-location, then in the limited position, we use two template matching to tracking face. In a relative complex background, with image size of 320 X 240,our system can get a speed of six to ten image per second, and the accurate rate is around 75%.In this paper, CCD vidicon grabbed the tracked images and all algorithms were accomplished by VC++ in Windows 98 environment.