Non-intrusive Person Authentication for Access Control by Visual Tracking and Face Recognition

Face recognition systems typically operate robustly only within highly constrained environments. This paper describes work aimed at performing face recognition in more unconstrained environments such as occur in security applications based on closed-circuit television (CCTV). The system described detects and tracks several people as they move through complex scenes. It uses a single, fixed camera and extracts segmented face sequences which can be used to perform face recognition or verification. Example sequences are given to illustrate performance. An application in non-intrusive access control is discussed.

[1]  Andrew Zisserman,et al.  Cooperating motion processes , 1991 .

[2]  Andrew Zisserman,et al.  Cooperating Motion Processes , 1991, BMVC.

[3]  J. H. Duncan,et al.  On the Detection of Motion and the Computation of Optical Flow , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Stephen M. Smith,et al.  A scene segmenter; visual tracking of moving vehicles , 1993 .

[5]  Jörg Kopecz,et al.  ZN-Face: A system for access control using automated face recognition , 1995, SNN Symposium on Neural Networks.

[6]  Takeo Kanade,et al.  Human Face Detection in Visual Scenes , 1995, NIPS.

[7]  Shaogang Gong,et al.  Face Tracking and Pose Representation , 1996, BMVC.

[8]  Hilary Buxton,et al.  Towards unconstrained face recognition from image sequences , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[9]  Trevor Darrell,et al.  Active face tracking and pose estimation in an interactive room , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Shaogang Gong,et al.  Tracking faces , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.