Facial Expressions Animation and Lip Tracking Using Facial Characteristic Points and Deformable Model

Face and facial expressions play essential roles in interpersonal communication. Most of the current works on the facial expression recognition attempt to recognize a small set of the prototypic expressions such as happy, surprise, anger, sad, disgust and fear. However the most of the human emotions are communicated by changes in one or two of discrete features. In this paper, we develop a facial expressions synthesis system, based on the facial characteristic points (FCP's) tracking in the frontal image sequences. Selected FCP's are automatically tracked using a crosscorrelation based optical flow. The proposed synthesis system uses a simple deformable facial features model with a few set of control points that can be tracked in original facial image sequences.

Authors:

• Hadi Seyedarabi
• Ali Aghagolzadeh
• Sohrab Khanmohammadi

Keywords:

• Deformable face model
• facial animation
• facialcharacteristic points
• optical flow.

References:

[1] P. Ekman and W.V. Friesen, Facial Action Coding System (FACS),
Consulting Psychologists Press, Inc., 1978.
[2] Z. Wu,P. S. Aleksic and A. K. Katsaggelos," Lip Tracking for MPEG-4
Facial Animation," in Proc. 4th IEEE Int. Conf. on Multimodal
Interfaces,ICMI'02,
[3] P. Eisert, T. Wiegand and B. G. Fellow," Model-Aided Coding: A New
Approach to Facial Animation into Motion Compensated Video Coding,"
IEEE Trans. On Circuits and Systems for Video Technology, vol. 10, No.
3, April 2000.
[4] S. T. Worral, A. H. Sadka, and A. M. Kondoz, "3-D Facial Animationfor
Very Low Bit Rate Mobile Video," in Proc. IEE Int. Conf. on 3G Mobile
Communication Technologies, May 2002.
[5] F. Erol, "Modeling and Animating Personalized Faces," M.Sc. Thesis,
Bilkent university, January 2002.
[6] T. Kanade, J. Cohn and Y. Tian. Comprehensive database for facial
expression analysis, 2000.
[7] H. Seyedarabi, A. Aghagolzadeh and S. Khanmohammadi, "Facial
Expressions Recognition from Static Images using Neural Networks and
Fuzzy logic," The 2nd Iranian Conference on Machine Vision and Image
processing (MVIP2003),vol.1 pp 7-12, Tehran, 2003.
[8] H. Seyedarabi, A. Aghagolzadeh and S. Khanmohammadi, "Facial
Expressions Recognition from Image Sequences using Cross-correlation
Based Optical-Flow and Radial Basis Neural Networks," The 12th Iranian
Conference on Electrical Engineering,(ICEE 2004), vol.1 pp 165-
170,Mashhad, 2004 .
[9] H. Seyedarabi, A. Aghagolzadeh and S. Khanmohammadi, "Recognition
of Six Basic Facial Expressions by Feature-Points Tracking using RBF
Neural Networks and Fuzzy Inference System," The IEEE International
conference on Multimedia & Expo (ICME2004), Taipei, Taiwan ,June
2004.
[10] Ali Aghagolzadeh, Hadi Seyedarabi and Sohrab Khanmohammadi ,"
Single and Composite Action Units Classification in Facial Expressions
by Feature-Points Tracking and RBF Neural Networks", Ukrainian Int.
conf. on signal/Image processing,UkrObraz 2004, October 2004, Kiev,
Ukraine.