A Sequential Monte Carlo Method for Bayesian Face Recognition

  • Atsushi Matsui
  • Simon Clippingdale
  • Takashi Matsumoto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4109)


This paper proposes a Sequential Monte Carlo (SMC) learning algorithm for Bayesian probability distributions that describe model parameters in a video face recognition system based on deformable template matching. The new algorithm achieves significantly improved robustness of recognition against facial expressions and speech movements by comparison with a baseline batch MCMC (Markov Chain Monte Carlo) algorithm, at no additional computational cost. Experimental results demonstrate the effectiveness and computational efficiency of the new algorithm.


Feature Point Face Recognition Markov Chain Monte Carlo Method Face Model Gabor Wavelet 
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.


  1. 1.
    Clippingdale, S., Ito, T.: A Unified Approach to Video Face Detection, Tracking and Recognition. In: Proc. ICIP 1999, Kobe, Japan, pp. 662–666 (1999)Google Scholar
  2. 2.
    Clippingdale, S., Ito, T.: Partial automation of database acquisition in the FAVRET face tracking and recognition system using a bootstrap approach. In: Proc. MVA 2000, Tokyo, Japan, pp. 5–8 (2000)Google Scholar
  3. 3.
    Wiskott, L., Fellous, J.M., Krüger, N., von der Malsburg, C.: Face Recognition by Elastic Bunch Graph Matching. TR96-08, Institut für Neuroinformatik, Ruhr-Universitat Bochum (1996)Google Scholar
  4. 4.
    Doucet, A.: On Sequential Simulation-Based Methods for Bayesian Filtering. Technical report CUED/F-INFENG/TR-310, Cambridge University (1998)Google Scholar
  5. 5.
    Liu, J.S.: Monte Carlo Strategies in Scientific Computing, pp. 53–77. Springer, New York (2001)MATHGoogle Scholar
  6. 6.
    Andrieu, C., Freitas, C.N., Doucet, A., Jordan, M.I.: An Introduction to MCMC for Machine Learning. Machine Learning 50, 5–43 (2003)MATHCrossRefGoogle Scholar
  7. 7.
    Matsui, A., Clippingdale, S., Uzawa, F., Matsumoto, T.: Bayesian Face Recognition using a Markov Chain Monte Carlo Method. In: Proc. ICPR 2004, vol. 3, pp. 918–921 (2004)Google Scholar
  8. 8.
    Mardia, K.V., Jupp, P.: Directional Statistics, 2nd edn. John Wiley and Sons, Chichester (2000)MATHGoogle Scholar
  9. 9.
    Mackay, D.J.C.: Information Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)MATHGoogle Scholar
  10. 10.
    Matsumoto, T.: Marginal Likelihood Change Detection: Particle Filter Approach. In: Proc. International Workshop on Bayesian Inference and Maximum Entropy for Science and Engineering, AIP Conf. Proc., vol. 803, pp. 129–136 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Atsushi Matsui
    • 1
    • 2
  • Simon Clippingdale
    • 1
  • Takashi Matsumoto
    • 2
  1. 1.Science & Technical Research LaboratoriesNHK (Japan Broadcasting Corporation)TokyoJapan
  2. 2.Dept. of Electrical Engineering & BioscienceWaseda UniversityTokyoJapan

Personalised recommendations