Abstract-Accurate detection of eyes plays an important role in human-machine interfaces. In this paper, according to some physical characteristics, a new designed device for the new real-time and effective eye detection method is proposed. In this device, two physical characteristics are applied, they are the Red-eye effect and the 850-property observed in the experiments. The detecting approach includes four steps, pretreating, matching by SURF (Speeded Up Robust Features), finding the difference and getting the points of the eyes. After these four steps, the positions of the eyes are obtained, and whether eye exists in the picture or not could also be judged. To speed up the detection, the matching parameters are recorded and adjusted periodically.

No abstract

Vision based hand tracking is an important area of human machine interaction (HCI) and virtual reality techniques. However, it is still a great challenge. Due to the complicated environment and various hand appearances, it is difficult to realize stable and long-term tracking. In this paper, we proposed an effective approach to detect and track hand with a normal webcam. An integrating multi-cue detector with skin color and hand classifier is used to initialize the tracking region and find appearance information during tracking. Also a median flow tracker is integrated which utilizing the motion information to enhance the accuracy in short-term. We realize an automatic system of stable and long-term hand tracking, which can detect and track pre-trained frontal view hand gesture. Experiments show the good performance of our approach.