Weight Compensated Motion Estimation for Facial Deformation Analysis

  • Jürgen Rurainsky
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5627)


Investigation of the motion performed by a person’s face while speaking is the target of this paper. Methods and results of the studied facial motions are presented and rigid and non-rigid motion are analyzed. In order to extract only facial deformation independent from head pose, we use a new and simple approach for separating rigid and non-rigid motion called Weight Compensated Motion Estimation (WCME). This approach weights the data points according to their influence to the desired motion model. A synthetic test as well as real data are used to demonstrate the performance of this approach. We also present results in the field of facial deformation analysis and used basis shapes as description form. These results can be used for recognition purposes by adding temporal changes to the overall process or adding natural deformations other than at the given database.


motion facial deformation personalized 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Perlman, S.: Contour Reality Capture System Unveiled. In: SIGGRAPH (July 2006)Google Scholar
  2. 2.
    Faraway, J.: Modeling continuous shape change for facial animation. Statistics and Computing 14(4), 357–363 (2004)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Trotman, C., Faraway, J.J.: Modeling facial movement: I. A dynamic analysis of differences based on skeletal characteristics. Journal of Oral and Maxillofacial Surgery 62(11), 1372–1379 (2004)CrossRefGoogle Scholar
  4. 4.
    Essa, I.A., Pentland, A.P.: Facial expression recognition using a dynamic model and motion energy. In: Proc. International Conference on Computer Vision (ICCV), Cambridge, MA, USA, pp. 360–367 (June 1995)Google Scholar
  5. 5.
    Kalberer, G., Gool, L.V.: Face animation based on observed 3D speech dynamics. In: Proceedings of the 14th Conference on Computer Animation, Nice, France, pp. 20–27 (November 2001)Google Scholar
  6. 6.
    Odisio, M., Bailly, G., Elisei, F.: Tracking talking faces with shape and appearance models. Speech Communication 44, 63–82 (2004)CrossRefGoogle Scholar
  7. 7.
    Eisert, P., Girod, B.: Analyzing Facial Expressions for Virtual Conferencing. IEEE Computer Graphics Applications: Special Issue: Computer Animation for Virtual Humans 18(5), 70–78 (1998)CrossRefGoogle Scholar
  8. 8.
    Li, H., Roivainen, P., Forchheimer, R.: 3-D Motion Estimation in Model-Based Facial Image Coding. IEEE Trans. Pattern Anal. Machine Intell. 15(6), 545–555 (1993)CrossRefGoogle Scholar
  9. 9.
    Yilmaz, A., Shafique, K., Shah, M.: Estimation of Rigid and Non-Rigid Facial Motion Using Anatomical Face Model. In: ICPR 2002: Proceedings of the 16th International Conference on Pattern Recognition (ICPR 2002), Washington, DC, USA, vol. 1, p. 10377 (2002)Google Scholar
  10. 10.
    Ploskas, N., Simitopoulos, D., Tzovaras, D., Triantafyllidis, G.A., Strintzis, M.G.: Rigid and non-rigid 3D motion estimation from multiview image sequence. Signal Processing: Image Communication 18(3), 185–202 (2003)Google Scholar
  11. 11.
    Huang, W., Zhang, Y., Wang, Y., Cheng, H.: 3D non-rigid motion estimation using the improved simulated annealing algorithm. In: Yeung, D.S., Liu, Z.-Q., Wang, X.-Z., Yan, H. (eds.) ICMLC 2005. LNCS, vol. 3930, pp. 5330–5335. Springer, Heidelberg (2006)Google Scholar
  12. 12.
    Bue, A.D., Lladó, X., Agapito, L.: Non-rigid Face Modelling Using Shape Priors. In: Cantú-Paz, E., et al. (eds.) GECCO 2003. LNCS, vol. 2723, pp. 96–107. Springer, Heidelberg (2003)Google Scholar
  13. 13.
    Oten, R., de Figueiredo, R.: Adaptive alpha-trimmed mean filters under deviations from assumed noise model. IEEE Transactions on Image Processing 13, 627–639 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Jürgen Rurainsky
    • 1
  1. 1.Fraunhofer Heinrich-Hertz-InstituteBerlinGermany

Personalised recommendations