Science and Development Network (SciDev.Net)
This paper proposes a means of using facial color to enhance conventional face detectors. To a detect face rapidly, the proposed approach adopts a color filtering based efficient region scanning method. The scanning method skips over regions that do not contain possible faces, based on a facial color membership function. By integrating the proposed face detector with a kernel based object tracker, a real-time face detection and tracking application is implemented for mobile devices. The proposed method considerably reduces the overall computation time and reduces the number of false positives.