Exemplar-Based Face Recognition from Video

  • Volker Krüger
  • Shaohua Zhou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2353)


A new exemplar-based probabilistic approach for face recognition in video sequences is presented. The approach has two stages: First, Exemplars, which are selected representatives from the raw video, are automatically extracted from gallery videos. The exemplars are used to summarize the gallery video information. In the second part, exemplars are then used as centers for probabilistic mixture distributions for the tracking and recognition process. A particle method is used to compute the posteriori probabilities. Probabilistic methods are attractive in this context as they allow a systematic handling of uncertainty and an elegant way for fusing temporal information.

Contrary to some previous video-based approaches, our approach is not limited to a certain image representation. It rather enhances known ones, such as the PCA, with temporal fusion and uncertainty handling. Experiments demonstrate the effectiveness of each of the two stages. We tested this approach on more than 100 training and testing sequences, with 25 different individuals.


Surveillance Video-based Face Recognition Exemplar-based Learning 


  1. 1.
    T. Choudhury, B. Clarkson, T. Jebara, and A. Pentland. Multimodal person recognition using unconstrained audio and video. In Proc. Int. Conf. on Audio-and Video-based Biometric Person Authentication, pages 176–181, Washington, D.C., March 22–23, 1999.Google Scholar
  2. 2.
    A. Doucet, S. Godsill, and C. Andrieu. On sequential monte carlo sampling methods for bayesian filtering. Statistics and Computing, 10:197–209, 2000.CrossRefGoogle Scholar
  3. 3.
    B. Frey and N. Jojic. Learning graphical models if images, videos and their spatial transformations. In Proc. Conf. Uncertainty in Artificial Intelligence, 2000.Google Scholar
  4. 4.
    B. Fritzke. Growing cell structures-a self-organizing network for unsupervised and supervised learning. Neural Networks, 7:1441–1460, 1995.CrossRefGoogle Scholar
  5. 5.
    D. Gavrila and V. Philomin. Real-time object detection for ”smart” vehicles. In Proc. Int. Conf. on Computer Vision, pages 87–93, Korfu, Greece, 1999.Google Scholar
  6. 6.
    A. Howell and H. Buxton. Towards unconstrained face recognition from image sequences. In Proc. British Machine Vision Conference, pages 455–464, Edinburgh, 1996.Google Scholar
  7. 7.
    M. Isard and A. Blake. Condensation-conditional density propagation for visual tracking. Int. J. of Computer Vision, 1998.Google Scholar
  8. 8.
    G. Kitagawa. Monta carlo filter and smoother for non-gaussian nonlinear state space models. J. Computational and Graphical Statistics, 5:1–25, 1996.MathSciNetGoogle Scholar
  9. 9.
    B. Li and R. Chellappa. Simultanious tracking and verification via sequential posterior estimation. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, SC, June 13–15, 2000.Google Scholar
  10. 10.
    J. Liu and R. Chen. Sequential monte carlo for dynamic systems. Journal of the American Statistical Association, 93:1031–1041, 1998.Google Scholar
  11. 11.
    D. Lowe. Radial basis function networks. In M. Arbib, editor, The Handbook of Brain Theory and Neural Networks, pages 779–782. MIT-Press, 1995.Google Scholar
  12. 12.
    T. Martinez and K. Schulten. Topology representing networks. Neural Networks, 7:505–522, 1994.Google Scholar
  13. 13.
    S. McKenna and S. Gong. Non-intrusive person authentication for access control by visual tracking and face recognition. In Proc. Int. Conf. on Audio-and Video-based Biometric Person Authentication, pages 177–183, Crans-Montana, Switzerland, 1997.Google Scholar
  14. 14.
    B. Moghaddam and A. Pentland. Probabilistic visual learning for object detection. IEEE Trans. Pattern Analysis and Machine Intelligence, 17:696–710, 1997.CrossRefGoogle Scholar
  15. 15.
    P. Phillips, H. Moon, S. Rizvi, and P. Rauss. The feret evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern Analysis and Machine Intelligence, 22:1090–1103, 2000.CrossRefGoogle Scholar
  16. 16.
    J. Steffens, E. Elagin, and H. Neven. Personspotter-fast and robust system for human detection, tracking and recognition. In Proc. Int. Conf. on Automatic Face and Gesture Recognition, pages 516–521, Nara, Japan, April 14–16, 1998.Google Scholar
  17. 17.
    K. Toyama and A. Blake. Probabilistic tracking in a metric space. In Proc. Int. Conf. on Computer Vision, volume 2, pages 50–59, Vancouver, Canada, 9–12 July, 2001.Google Scholar
  18. 18.
    H. Wechsler, V. Kakkad, J. Huang, S. Gutta, and V. Chen. Automatic video-based person authentication using th rbf network. In Proc. Int. Conf. on Audio-and Video-based Biometric Person Authentication, pages 85–92, Crans-Montana, Switzerland, 1997.Google Scholar
  19. 19.
    L. Wiskott, J. M. Fellous, N. Krüger, and C. v. d. Malsburg. Face recognition and gender determination. In Proc. Int. Workshop on Automatic Face and Gesture Recognition, Zurich, Switzerland, June 26–28, 1995.Google Scholar
  20. 20.
    W. Zhao, R. Chellappa, and N. Nandhakumar. Discriminant analysis fo principal components for face recognition. In Nara, Japan, April 14–16, pages 336–341, 1998.Google Scholar
  21. 21.
    S. Zhou, V. Krüger, and R. Chellappa. Face recognition from video: A CONDENSATION approach. In Proc. Int. Conf. on Automatic Face and Gesture Recognition, Washington, DC, USA, May 21–22, 2002. Accepted for publication.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Volker Krüger
    • 1
  • Shaohua Zhou
    • 1
  1. 1.Center for Automation ResearchUniversity of MarylandCollege ParkUSA

Personalised recommendations