Advertisement

Abstract

Cascades of boosted classifiers have become increasingly popular in machine vision and have generated a lot of recent research. Most of it has focused on modifying the underlying Adaboost method and far less attention has been given to the problem of dimensioning the cascade, i.e. determining the number and the characteristics of the boosted classifiers. To a large extent, the designer of a cascade must set the parameters in the cascade using ad-hoc methods.

We propose to automatically build a cascade of classifiers, given just a family of weak classifiers a desired performance level and little more. First, a boosted classifier with the desired performance is built using any boosting method. This classifier is then “sliced” using dynamic programming into a cascade of classifiers in a nearly computation-cost-optimal fashion.

Keywords

Face Detection Validation Dataset Weak Classifier Computational Learn Theory Optimal Cascade 
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.

References

  1. 1.
    Aslam, J.A.: Improving algorithms for boosting. In: Annual Conf. on Computational Learning Theory, pp. 200–207. Morgan Kaufmann, San Francisco (2000)Google Scholar
  2. 2.
    Bellman, R.: Dynamic programming. Princeton University Press, Princeton (1957)zbMATHGoogle Scholar
  3. 3.
    Carmichael, O., Hebert, M.: Object recognition by a cascade of edge probes. In: BMVC, pp. 103–112 (2002)Google Scholar
  4. 4.
    Fan, W., Stolfo, S.J., Zhang, J., Chan, P.K.: AdaCost: misclassification costsensitive boosting. In: Intl. Conf. on Machine Learning, pp. 97–105 (1999)Google Scholar
  5. 5.
    Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: proc. International Conference on Machine Learning, pp. 148–156 (1996)Google Scholar
  6. 6.
    Mullin, M.D., Wu, J., Rehg, J.M.: Learning a rare event detection cascade by direct feature selection. In: NIPS (2003)Google Scholar
  7. 7.
    Jesorsky, O., Kirchberg, K.J., Frischholz, R.W.: Robust face detection using the hausdorff distance. In: Proc. Intl. Conf. on Audio- and Video-based Biometric Person Authentication, pp. 90–95 (2001)Google Scholar
  8. 8.
    Li, S., Zhang, Z., Zhu, L., Shum, H.-Y., Zhang, H.: Floatboost learning for classification. In: NIPS (2003)Google Scholar
  9. 9.
    Li, S.Z., Zhu, L., Zhang, Z.Q., Blake, A., Zhang, H.J., Shum, H.: 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
  10. 10.
    Lienhart, R., Kuranov, A., Pisarevsky, V.: Empirical analysis of detection cascades of boosted classifiers for rapid object detection. In: DAGM Pattern Recognition Symposium (2003)Google Scholar
  11. 11.
    Mannor, S., Meir, R.: Geometric bounds for generalization in boosting. In: Proc. Conference on Computational Learning Theory (2001)Google Scholar
  12. 12.
    McCane, B., Novins, K.: On training cascade face detectors. In: Image and Vision Computing , New Zealand (2003)Google Scholar
  13. 13.
    Merler, S., Furlanello, C., Larcher, B., Sboner, A.: Automatic model selection in cost-sensitive boosting. Information Fusion 4(1), 3–10 (2003)CrossRefGoogle Scholar
  14. 14.
    Provost, F.J., Fawcett, T.: Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions. In: International Conference on Knowledge Discovery and Data Mining (1997)Google Scholar
  15. 15.
    Rowley, H., Baluja, S., Kanade, T.: Rotation invariant neural network-based face detection. Technical Report CMU-CS-97-201, CMU (1997)Google Scholar
  16. 16.
    Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Trans. PAMI 20, 22–38 (1998)Google Scholar
  17. 17.
    Schapire, R.E., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Machine Learning 37(3), 297–336 (1999)zbMATHCrossRefGoogle Scholar
  18. 18.
    Schneiderman, H., Kanade, T.: A statistical method for 3D object detection applied to faces and cars. In: Proc. ICCV (2000)Google Scholar
  19. 19.
    Turney, P.D.: Cost-sensitive classification: Empirical evaluation of a hybrid genetic decision tree induction algorithm. Journal of Artificial Intelligence Research 2, 369–409 (1995)Google Scholar
  20. 20.
    Viola, P., Jones, M.: Fast and robust classification using asymmetric adaboost and a detector cascade. In: NIPS (2001)Google Scholar
  21. 21.
    Viola, P., Jones, M.: Robust real-time object detection. In: Proc. ICCV workshop on statistical and computational theories of vision (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Etienne Grossmann
    • 1
  1. 1.Center for Visualization and Virtual EnvironmentsUniversity of Kentucky 

Personalised recommendations