Key frame selection to represent a video

This paper describes a technique to automatically extract a single key frame from a video sequence. The technique is designed for a system to search video on the World Wide Web. For each video returned by a query, a thumbnail image that illustrates its content is displayed to summarize the results. The proposed technique is composed of three steps. Shot boundaries detection, shot selection, and key frame extraction within the selected shot. The shot and key frame are selected based on measures of motion and spatial activity and the likeliness to include people. The latter is determined by skin-color detection and face detection. Simulation results on a large set of video from the Internet, including movie trailers, sports, news, and animation, show the efficiency of the method. Furthermore, this is achieved at a very low complexity cost.