Face animation parameter extraction in real movie capturing environment

Facial Animation is one of the important problems in computer simulating of human face. Face modeling is needed to have an accurate animation. One of the methods for recording face movement is to use markers on the face key points to follow the actions by tracking these markers. MPEG4 standard, presented by the Moving Pictures Experts Group, has some parameters for facial animation. To obtain these parameters for facial modeling and animation, it is necessary to track the face movements. Using markers on the face key points and tracking the movements of the markers is a low cost method to determine the parameters, if the markers are placed on key points defined in a specific standard and accurate tracking is done, total movement of the face is covered. In this paper, we proposed a system for tracking markers which are placed on the face based on MPEG4 standard and examine this system in unstable film capturing conditions such as changing light, addition of Gaussian noise, blurring, compression, and filtering.

[1]  Fernando Pereira,et al.  MPEG-4 facial animation technology: survey, implementation, and results , 1999, IEEE Trans. Circuits Syst. Video Technol..

[2]  J. Todd Book Review: Digital image processing (second edition). By R. C. Gonzalez and P. Wintz, Addison-Wesley, 1987. 503 pp. Price: £29.95. (ISBN 0-201-11026-1) , 1988 .

[3]  Jun-yong Noh,et al.  A Survey of Facial Modeling and Animation Techniques , 2001 .

[4]  A Sarvan,et al.  Speech Driven MPEG-4 Facial Animation for Turkish , 2004 .

[5]  Jörn Ostermann,et al.  Talking faces - technologies and applications , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[6]  Jon Barker Tracking facial markers with an adaptive marker collocation model , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[7]  Aggelos K. Katsaggelos,et al.  Automatic facial expression recognition using facial animation parameters and multistream HMMs , 2006, IEEE Transactions on Information Forensics and Security.