论文信息 - TRACKING A FACE IN A KNOWLEDGE-BASED ANALYSIS-SYNTHESIS CODER

TRACKING A FACE IN A KNOWLEDGE-BASED ANALYSIS-SYNTHESIS CODER

An algorithm for tracking a face in a knowledge–based analysis–synthesis coder (KBASC) is described. After motion compensation of the head, eye and mouth center positions of a person in an image are estimated. Then, the position of the face model is corrected using the estimated positions of eyes and mouth. Experimental results show that the proposed algorithm allows a more accurate tracking of a face in a KBASC compared to tracking only with motion compensation of the head.

Liang Zhang

[1] Kiyoharu Aizawa,et al. Analysis and synthesis of facial image sequences in model-based image coding , 1994, IEEE Trans. Circuits Syst. Video Technol..

[2] Jörn Ostermann,et al. Automatic adaptation of a face model in a layered coder with an object-based analysis-synthesis layer and a knowledge-based layer , 1997, Signal Process. Image Commun..

[3] Jörn Ostermann,et al. Object-based analysis-synthesis coding based on the source model of moving rigid 3D objects , 1994, Signal Process. Image Commun..

[4] Haibo Li,et al. Two-view facial movement estimation , 1994, IEEE Trans. Circuits Syst. Video Technol..