Multi-view Face Detection in Video

摘要

A multi-view face detection method in video is proposed in this paper. The method is capable of locating human faces over a broad range of views in videos with complex scenes. Firstly, an improved frame difference is used to acquire promising regions of the image. Then it uses the presence of skin-tone pixels to locate faces. Finally, shape, edge pattern and facespecific features are used to verify the candidate face regions. The experimental results show that the proposed algorithm has high speed and low errordetection rate, so it can be used in the real-time video surveillance system. The main distinguishing contribution of this work is being able to detect faces irrespective of their poses, including frontal-view and side-view, whereas contemporary systems deal with frontal-view faces only. The other novel aspects of the work lie in its accuracy of acquiring the candidate area to segment objects from background with the help of motion information and skin information.