Face Animation Parameter Extraction in Real Video Environment

One of the challenging problems in machine vision and computer graphic is realistic face modeling and animation. Using markers on the face key points and tracking the movements of the markers is a low cost method to determine these parameters. Since MPEG4 standard has defined parameters for face modeling and animation, we place markers on the key points defined in MPEG-4 standard, and propose a system for accurate tracking of them. We examine the system in real movie capturing conditions. Various distortions such as change of lightening, Gaussian noise, blurring, compression, and temporal filtering are examined, and the system degradation in each case is reported.

[1]  Demetri Terzopoulos,et al.  Analysis and Synthesis of Facial Image Sequences Using Physical and Anatomical Models , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Lance Williams,et al.  Performance-driven facial animation , 1990, SIGGRAPH.

[3]  Sami Romdhani,et al.  Face identification across different poses and illuminations with a 3D morphable model , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[4]  Jörn Ostermann,et al.  Animation of synthetic faces in MPEG-4 , 1998, Proceedings Computer Animation '98 (Cat. No.98EX169).

[5]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[6]  Henrique S. Malvar,et al.  Making Faces , 2019, Topoi.

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

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

[9]  Peter Eisert,et al.  Analyzing Facial Expressions for Virtual Conferencing , 1998, IEEE Computer Graphics and Applications.

[10]  Timothy F. Cootes,et al.  Comparing Variations on the Active Appearance Model Algorithm , 2002, BMVC.