Understanding 3D Emotions Through Compact Anthropometric Autoregressive Models

  • Charlotte Ghys
  • Nikos Paragios
  • Bénédicte Bascle
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4291)


Reproducing realistic facial expressions is an important challenge in human computer interaction. In this paper we propose a novel method of modeling and recovering the transitions between different expressions through the use of an autoregressive process. In order to account for computational complexity, we adopt a compact face representation inspired from MPEG-4 standards while in terms of expressions a well known Facial Action Unit System (FACS) comprising the six dominant ones is considered. Then, transitions between expressions are modeled through a time series according to a linear model. Explicit constraints driven from face anthropometry and points interaction are inherited in this model and minimize the risk of producing non-realistic configurations. Towards optimal animation performance, a particular hardware architecture is used to provide the 3D depth information of the corresponding facial elements during the learning stage and the Random Sampling Consensus algorithm for the robust estimation of the model parameters. Promising experimental results demonstrate the potential of such an approach.


Facial Expression Face Model Learning Stage Active Appearance Model Facial Animation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    ISO/IEC IS 14496-2 Visual (1999)Google Scholar
  2. 2.
    Blanz, V., Vetter, T.: A Morphable Model for the Synthesis of 3d Faces. In: SIGGRAPH, pp. 187–194 (1999)Google Scholar
  3. 3.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-Based Object Tracking. In: Pattern Analysis Machine Intelligence, vol. 25, pp. 564–575 (2003)Google Scholar
  4. 4.
    Cootes, T., Edwards, G., Taylor, C.: Active Appearance Models. In: Pattern Analysis and Machine Intelligence (2001)Google Scholar
  5. 5.
    DeCarlo, D., Metaxas, D.: Optical Flow Constraints on Deformable Models with Applications to Face Tracking. International Journal of Computer Vision ( July 2000)Google Scholar
  6. 6.
    Ekman, P., Friesen, W.V.: Facial Action Coding System, Palo Alto (1978)Google Scholar
  7. 7.
    Faugeras, O.: Three-Dimensional Computer Vision: A Geometric Viewpoint. MIT Press, Cambridge (1993)Google Scholar
  8. 8.
    Fischler, M.A., Bolles, R.C.: Random Sample Concensus: a Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM 24, 381–395 (1981)CrossRefMathSciNetGoogle Scholar
  9. 9.
    Forchheimer, R., Pandzic, I.S., et al.: MPEG-4 Facial Animation: the Standards, Implementations and Applications. John Wiley & Sons, Chichester (2002)Google Scholar
  10. 10.
    Huber, P.: Robust Estimation of Location Parameter. In: Annals of Mathematical Statistics (1964)Google Scholar
  11. 11.
    Ilic, S., Fua, P.: Generic Deformable Implicit Mesh Models for Automated Reconstruction. In: ICCV workshop on Higher-Level Knowledge in 3D Modelling and Motion Analysis, Nice, France (October 2003)Google Scholar
  12. 12.
    Liu, Z., Zhang, Z., Jacobs, C., Cohen, M.: Rapid Modeling of Animated Faces from Video. In: International Conference on Visual Computing, 2005, pp. 58–67 (September 2005)Google Scholar
  13. 13.
    Magnenat-Thalmann, N., Primeau, E., Thalmann, D.: Abstract Muscle Action Procedures for Human Face Animation. The Visual Computer 3 (1987)Google Scholar
  14. 14.
    Parke, F.I.: Computer Generated Animation of Faces. In: ACM National Conference, pp. 451–457 (1972)Google Scholar
  15. 15.
    Wang, C.L.Y., Forsey, D.R.: Langwidere: A New Facial Animation System. In: Computer Animation, pp. 59–68 (1994)Google Scholar
  16. 16.
    Xiao, J., Baker, S., Matthews, I., Kanade, T.: Real-time Combined 2d+3d Active Appearance Models. In: Conference on Computer Vision and Pattern Recognition (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Charlotte Ghys
    • 1
    • 2
  • Nikos Paragios
    • 1
  • Bénédicte Bascle
    • 2
  1. 1.MAS – Ecole Centrale ParisChatenay-MalabryFrance
  2. 2.Orange – France Telecom R&DLannionFrance

Personalised recommendations