Discrete Choice Models for Static Facial Expression Recognition

  • Gianluca Antonini
  • Matteo Sorci
  • Michel Bierlaire
  • Jean-Philippe Thiran
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4179)


In this paper we propose the use of Discrete Choice Analysis (DCA) for static facial expression classification. Facial expressions are described with expression descriptive units (EDU), consisting in a set of high level features derived from an active appearance model (AAM). The discrete choice model (DCM) is built considering the 6 universal facial expressions plus the neutral one as the set of the available alternatives. Each alternative is described by an utility function, defined as the sum of a linear combination of EDUs and a random term capturing the uncertainty. The utilities provide a measure of likelihood for a combinations of EDUs to represent a certain facial expression. They represent a natural way for the modeler to formalize her prior knowledge on the process. The model parameters are learned through maximum likelihood estimation and classification is performed assigning each test sample to the alternative showing the maximum utility. We compare the performance of the DCM classifier against Linear Discriminant Analysis (LDA), Generalized Discriminant Analysis (GDA), Relevant Component Analysis (RCA) and Support Vector Machine (SVM). Quantitative preliminary results are reported, showing good and encouraging performance of the DCM approach both in terms of recognition rate and discriminatory power.


Support Vector Machine Facial Expression Linear Discriminant Analysis Face Image Discrete Choice 
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.
    Lien, J.: Automatic recognition of facial expressions using hidden markov models and estimation of expression intensity (1998)Google Scholar
  2. 2.
    Ye, J., Zhan, Y., Song, S.: Facial expression features extraction based on gabor wavelet transformation. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 10–13 (2004)Google Scholar
  3. 3.
    Padgett, C., Cottrell, G.: Representing face images for emotion classification. MIT Press, Cambridge (1997)Google Scholar
  4. 4.
    Bartlett, M.: Face image analysis by unsupervised learning and redundancy reduction (1998)Google Scholar
  5. 5.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 681–685 (2001)CrossRefGoogle Scholar
  6. 6.
    Lanitis, A., Taylor, C.J., Cootes, T.F.: Automatic interpretation and coding of face images using flexible models. IEEE Trans. Pattern Anal. Mach. Intell. 19, 743–756 (1997)CrossRefGoogle Scholar
  7. 7.
    Stegmann, M.B.: Active appearance models: Theory, extensions and cases. Master’s thesis, Informatics and Mathematical Modelling, Technical University of Denmark, DTU, Richard Petersens Plads, Building 321, DK-2800 Kgs. Lyngby (2000)Google Scholar
  8. 8.
    Antonini, G., Venegas, S., Bierlaire, M., Thiran, J.P.: Behavioral priors for detection and tracking of pedestrians in video sequences. International Journal of Computer Vision (to appear, 2005)Google Scholar
  9. 9.
    Sorci, M., Antonini, G., Thiran, J.P.: Relevant component analysis for static facial expression recognition. Technical Report TR_ITS_2005.33, Signal Processing Institute, Ecole Polytechnique Federale de Lausanne (2005)Google Scholar
  10. 10.
    Ekman, P., Friesen, W.V.: Facial Action Coding System Investigator’s Guide. Consulting Psycologist Press, Palo Alto (1978)Google Scholar
  11. 11.
    Horvitz, E.J., Breese, J.S., Henrion, M.: Decision theory in expert systems and artificial intelligence. International Journal of Approximate Reasoning 2, 247–302 (1988)CrossRefGoogle Scholar
  12. 12.
    McFadden, D.: Modelling the choice of residential location. In: Karlquist, A., et al. (eds.) Spatial interaction theory and residential location, Amsterdam, North-Holland, pp. 75–96 (1978)Google Scholar
  13. 13.
    Ben-Akiva, M.E., Lerman, S.R.: Discrete Choice Analysis: Theory and Application to Travel Demand. MIT Press, Cambridge (1985)Google Scholar
  14. 14.
    Abboud, D., Davoine, F.: Appearance factorization based facial expression recognition and synthesis. ICPR (4), 163–166 (2004)Google Scholar
  15. 15.
    Bierlaire, M.: BIOGEME: a free package for the estimation of discrete choice models. In: Proceedings of the 3rd Swiss Transportation Research Conference, Ascona, Switzerland (2003),
  16. 16.
    Train, K.: Discrete Choice Methods with Simulation. Cambridge University Press, University of California (2003)MATHCrossRefGoogle Scholar
  17. 17.
    Lawrence, C.T., Zhou, J.L., Tits, A.: A c code for solving (large scale) constrained nonlinear (minimax) optimization problems, generating iterates satisfying all inequality constraints. Technical Report TR-94-16rl, Institute for Systems Research, University of Maryland, College Park, MD 20742 (1997)Google Scholar
  18. 18.
    Cover, T.M., Thomas, J.A.: Elements of information theory. Wiley, Chichester (1991)MATHCrossRefGoogle Scholar
  19. 19.
    Ben-Akiva, M., Bolduc, D.: Multinomial probit with a logit kernel and a general parametric specification of the covariance structure (1996); Working Paper, Department of Civil Engineering, MITGoogle Scholar
  20. 20.
    Kanade, T., Cohn, J., Tian, Y.L.: Comprehensive database for facial expression analysis. In: Proceedings of the 4th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2000), pp. 46–53 (2000)Google Scholar
  21. 21.
    Sujith, K.R., Ramanan, G.V.: Procrustes analysis and moore-penrose inverse based classifiers for face recognition. In: Li, S.Z., Sun, Z., Tan, T., Pankanti, S., Chollet, G., Zhang, D. (eds.) IWBRS 2005. LNCS, vol. 3781, pp. 59–66. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gianluca Antonini
    • 1
  • Matteo Sorci
    • 1
  • Michel Bierlaire
    • 2
  • Jean-Philippe Thiran
    • 1
  1. 1.Ecole Polytechnique Federale de Lausanne, Signal Processing InstituteEcublensSwitzerland
  2. 2.Ecole Polytechnique Federale de Lausanne, Operation Research GroupEcublensSwitzerland

Personalised recommendations