Integrating Text and Face Detection for Finding Informative Poster Frames

Digital video is rapidly becoming an important source of information and entertainment, and is used in a host of multimedia applications. With the size of digital video collections growing to many thousands of hours, technology is needed to allow rapid browsing of videos. One way to summarize a video is to select poster frames to represent segments of the video. Previous techniques for extracting poster frames were based on scene segmentation, using color histograms or optical flow. To provide more informative poster frames, this work combines algorithms for extracting image content, specifically faces and on-screen text, with existing scene segmentation technology.