基于视频的人脸识别研究进展

State-of-the-Art on Video-Based Face Recognition

近年来基于视频的人脸识别已成为人脸识别领域最为活跃的研究方向之一.如何充分利用视频中人脸的时间和空间信息克服视频中人脸分辨率低,尺度变化范围大,光照、姿态变化比较剧烈以及时常发生遮挡等困难是研究的重点.文中对近期(主要近5年)基于视频的人脸识别研究进行了详细的介绍和讨论,在对相关方法分类的基础上,分析了各类方法中典型技术的优缺点,并概况介绍了常用的视频人脸数据库和实验结果,最后展望了基于视频人脸识别未来的发展方向和趋势.

Recently, video-based face recognition has become one of the hottest topics in the domain of face recognition. How to fully utilize both spatial and temporal information in video to overcome the difficulties existing in the video-based face recognition, such as low resolution of face images in video, large variations of. face scale, radical changes of illumination and pose as well as occasionally occlusion of different parts of faces, is the focus. The paper reviews most existing typical methods for video-based face recognition （especially for the last 5 years） and analyses their respective pros and cons. Two commonly used video face databases and some experimental results are given. The prospects for future development and suggestions for further research works are put forward in the end.