Face Detection Based on the Manifold

  • Ruiping Wang
  • Jie Chen
  • Shengye Yan
  • Wen Gao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3546)


Data collection for both training and testing a classifier is a tedious but essential step towards face detection and recognition. It is a piece of cake to collect more than hundreds of thousands of examples from web and digital camera nowadays. How to train a face detector based on the collected immense face database? This paper presents a manifold-based method to select a training set. That is to say we learn the manifold from the collected enormous face database and then subsample and interweave the training set by the estimated geodesic distance in the low-dimensional manifold embedding. By the resulting training set, we train an AdaBoost-based face detector. The trained detector is tested on the MIT+CMU frontal face test set. The experimental results show that the proposed method based on the manifold is efficient to train a classifier confronted with the huge database.


Face Image Geodesic Distance Neural Information Processing System Face Database Random Subsampling 
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.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Advances in Neural Inform. Proc. Systems, vol. 14, pp. 585–591. MIT Press, Cambridge (2002)Google Scholar
  2. 2.
    Bernstein, M., de Silva, V., Langford, J., Tenenbaum, J.: Graph approximations to geodesics on embedded manifolds. Technical report, Stanford University (2000)Google Scholar
  3. 3.
    Brand, M.: Charting a manifold. In Advances in Neural Information. In: Proc. Systems, vol. 15, pp. 961–968. MIT Press, Cambridge (2003)Google Scholar
  4. 4.
    Chen, J., Chen, X., Gao, W.: Expand Training Set for Face Detection by GA Resampling. In: The 6th IEEE Intern. Conf. FG 2004, pp. 73–79 (2004)Google Scholar
  5. 5.
    Donoho, D.L., Grimes, C.: When does ISOMAP recover natural parameterization of families of articulated images? Technical Report 2002-27, Stanford University (2002)Google Scholar
  6. 6.
    Heisele, B., Poggio, T., Pontil, M.: Face Detection in Still Gray Images. CBCL Paper #187. MIT, Cambridge, MA (2000)Google Scholar
  7. 7.
    Hsu, R.L., Abdel-Mottaleb, M., Jain, A.K.: Face detection in color images. IEEE Trans. Pattern Anal. Machine Intell, 696–706 (2002)Google Scholar
  8. 8.
    Hundley, D.R., Kirby, M.J.: Estimation of topological dimension. In: Proc. SIAM International Conference on Data Mining (2003),
  9. 9.
    Jenkins, O.C., Mataric, M.J.: Automated derivation of behavior vocabularies for autonomous humanoid motion. In: Proc. of the Second Int’l Joint Conference on Autonomous Agents and Multiagent Systems, Melbourne, Australia (July 2003)Google Scholar
  10. 10.
    Law, M.H., Zhang, N., Jain, A.K.: Nonlinear Manifold Learning for Data Stream. In: Proc. of SIAM Data Mining, Florida, pp. 33–44 (2004)Google Scholar
  11. 11.
    Li, S.Z., Zhu, L., Zhang, Z., Blake, A., Zhang, H., Shum, H.-Y.: Statistical learning of multi-view face detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 67–81. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Liu, C., Shum, H.Y.: Kullback-Leibler Boosting. In: Proceedings of the 2003 IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2003 (2003)Google Scholar
  13. 13.
    Liu, C.J.: A Bayesian Discriminating Features Method for Face Detection. IEEE Trans. Pattern Anal. and Machine Intel., 725–740 (2003)Google Scholar
  14. 14.
    Osuna, E., Freund, R., Girosi, F.: Training support vector machines: An application to face detection. In: Proc. IEEE Conf. on CVPR, pp. 130–136 (1997)Google Scholar
  15. 15.
    Papageorgiou, C.P., Oren, M., Poggio, T.: A general framework for object detection. In: Proc. 6th Int. Conf. Computer Vision, pp. 555–562 (1998)Google Scholar
  16. 16.
    Pettis, K., Bailey, T., Jain, A.K., Dubes, R.: An intrinsic dimensionality estimator from near-neighbor information. IEEE Trans. of Patt. Anal. and Machine Intel., 25–36 (1979)Google Scholar
  17. 17.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  18. 18.
    Roweis, S.T., Saul, L.K., Hinton, G.E.: Global coordination of local linear models. In: Advances in Neural Information Processing Systems, vol. 14, pp. 889–896. MIT Press, Cambridge (2002)Google Scholar
  19. 19.
    Rowley, H.A., Baluja, S., Kanade, T.: Neural Network-Based Face Detection. IEEE Tr. Pattern Analysis and Machine Intel., 23–38 (1998)Google Scholar
  20. 20.
    Rowley, H.A., Baluja, S., Kanade, T.: Rotation Invariant Neural Network-Based Face Detection. In: Conf. Computer Vision and Pattern Rec., pp. 38–44 (1998)Google Scholar
  21. 21.
    Schneiderman, H., Kanade, T.: A Statistical Method for 3D Object Detection Applied to Faces. In: Comp. Vision and Pattern Recog., pp. 746–751 (2000)Google Scholar
  22. 22.
    Sung, K.K., Poggio, T.: Example-Based Learning for View-Based Human Face Detection. IEEE Trans. on PAM, 39–51 (1998)Google Scholar
  23. 23.
    Viola, P., Jones, M.: Rapid Object Detection Using a Boosted Cascade of Simple Features. In: Conf. Comp. Vision and Pattern Recog., pp. 511-518 (2001)Google Scholar
  24. 24.
    Teh, Y.W., Roweis, S.T.: Automatic alignment of local representations. In: Advances in Neural Information Processing Systems, vol. 15, pp. 841–848. MIT Press, Cambridge (2003)Google Scholar
  25. 25.
    Tenenbaum, B.J., Silva, V., Langford, J.: A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science 290, 2319–2323 (2000)CrossRefGoogle Scholar
  26. 26.
    Verbeek, J.J., Vlassis, N., Krose, B.: Coordinating principal component analyzers. In: Proc. of International Conf. on Artificial Neural Networks, Spain, pp. 914–919 (2002)Google Scholar
  27. 27.
    Verbeek, J.J., Vlassis, N., Krose, B.: Fast nonlinear dimensionality reduction with topology preserving networks. In: Proc. 10th European Symposium on Artificial Neural Networks, pp. 193–198 (2002)Google Scholar
  28. 28.
    Xiao, R., Li, M.J., Zhang, H.J.: Robust Multipose Face Detection in Images. IEEE Trans on Circuits and Systems for Video Technology 14(1), 31–41 (2004)CrossRefMathSciNetGoogle Scholar
  29. 29.
    Yang, M.-H.: Face recognition using extended ISOMAP. In: ICIP, pp. 117–120 (2002)Google Scholar
  30. 30.
    Yang, M.H., Roth, D., Ahuja, N.: A SNoW-Based Face Detector. In: Advances in Neural Information Processing Systems, vol. 12, pp. 855–861. MIT Press, Cambridge (2000)Google Scholar
  31. 31.
    Yang, M.H., Kriegman, D., Ahuja, N.: Detecting Faces in Images: A Survey. IEEE Tr. Pattern Analysis and Machine Intelligence 24, 34–58 (2002)CrossRefGoogle Scholar
  32. 32.
    Zha, H., Zhang, Z.: Isometric embedding and continuum ISOMAP. In: ICML (2003),
  33. 33.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ruiping Wang
    • 1
  • Jie Chen
    • 1
  • Shengye Yan
    • 1
  • Wen Gao
    • 1
    • 2
  1. 1.ICT-ISVISION Joint R&D Lab for Face Recognition, Institute of Computing TechnologyChinese of Academy of SciencesBeijingChina
  2. 2.School of Computer Science and TechnologyHarbin Institute of TechnologyChina

Personalised recommendations