Motion tracking of human mouth by generalized deformable models

Abstract We propose and evaluate four trackers for tracking the shape, motion and deformation of a human mouth in video sequences. The trackers are suitable for use in very low bitrate video coding systems.

[1]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Ashok Samal,et al.  Automatic recognition and analysis of human faces and facial expressions: a survey , 1992, Pattern Recognit..

[3]  Kiyoharu Aizawa,et al.  Model-based image coding advanced video coding techniques for very low bit-rate applications , 1995, Proc. IEEE.

[4]  Michael Isard,et al.  3D position, attitude and shape input using video tracking of hands and lips , 1994, SIGGRAPH.

[5]  Syin Chan,et al.  Tracking of deformable contours by synthesis and match , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[6]  Roland T. Chin,et al.  Deformable contours: modeling and extraction , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .