Automatic focusing technique for face detection and face contour tracking

Human face contour represents an important and useful information for face analysis. Here, we propose an improvement to the conventional active contour model, called Snake, and apply it in the application of face biometric; i.e. automatic detection and tracking of complex face contour. Fast and efficient motion detection and estimation methods are introduced. The obtained motion information is used to reduce the number of sub-images to search. It is also used solve the Snake initialization problem faced in the original implementation. In video and image sequences, the motion information can be used to accelerate the Snake tracking. The motion compensated technique is shown to reduce significantly the computation time needed to minimize Snake energy. Thus, the proposed improvement offers a practical approach to real-time face contour detection and tracking system.