The real-time implementation of embedded image processing applications needs a fast processor. Eye recognition is an important part of image processing systems such as driver fatigue detection system and eye gaze detection system. In these systems, a fast and accurate real-time implementation of face and eye tracking is required. Hence, a new approach to determine and track face and eye on live images is proposed in this paper. This proposed method is implemented and successfully tested in laboratory for various real-time images with and without glasses captured through Logitech USB Camera of 1600 x 1200 pixels @ 30 fps. The method is developed on 1 GHz open multimedia applications platform (OMAP) processor and the algorithm is developed using OpenCV libraries. The success rate of the proposed algorithm shows that the hardware has sufficient speed and accuracy, which can be used in real time.
展开▼