Video-Based Face Recognition Algorithms

Traditional face recognition systems have relied on a gallery of still images for learning and a probe of still images for recognition. While the advantage of using motion information in face videos has been widely recognized, computational models for video-based face recognition have only recently gained attention. This chapter reviews some recent advances in this novel framework. In particular, the utility of videos in enhancing performance of image-based tasks (such as recognition or localization) will be summarized. Subsequently, spatiotemporal video-based face recognition systems based on particle filters, hidden Markov models , and system theoretic approaches will be presented. Further, some useful face databases employable by researchers interested in this field will be described. Finally, some open research issues will be proposed and discussed.