Learning to Detect Objects of Many Classes Using Binary Classifiers

  • Ramana Isukapalli
  • Ahmed Elgammal
  • Russell Greiner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)


Viola and Jones [VJ] demonstrate that cascade classification methods can successfully detect objects belonging to a single class, such as faces. Detecting and identifying objects that belong to any of a set of “classes”, many class detection, is a much more challenging problem. We show that objects from each class can form a “cluster” in a “classifier space” and illustrate examples of such clusters using images of real world objects. Our detection algorithm uses a “decision tree classifier” (whose internal nodes each correspond to a VJ classifier) to propose a class label for every sub-image W of a test image (or reject it as a negative instance). If this W reaches a leaf of this tree, we then pass W through a subsequent VJ cascade of classifiers, specific to the identified class, to determine whether W is truly an instance of the proposed class. We perform several empirical studies to compare our system for detecting objects of any of M classes, to the obvious approach of running a set of M learned VJ cascade classifiers, one for each class of objects, on the same image. We found that the detection rates are comparable, and our many-class detection system is about as fast as running a single VJ cascade, and scales up well as the number of classes increases.


Test Image Class Label Training Image Face Detection Positive Instance 
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.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, pp. 264–271 (2003)Google Scholar
  2. 2.
    Fan, X.: Efficient multiclass object detection by a hierarchy of classifiers. In: CVPR (2003)Google Scholar
  3. 3.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. In: Computational Learning Theory: Eurocolt (1995)Google Scholar
  4. 4.
    Grossmann, E.: Adatree: boosting a weak classifier into a decision tree. In: IEEE Workshop on Learning in Computer Vision and Patter Recognition (2004)Google Scholar
  5. 5.
    Isukapalli, R., Greiner, R.: Use of Off-line Dynamic Programming for Efficient Image Interpretation. In: IJCAI, Acapulco, Mexico (August 2003)Google Scholar
  6. 6.
    Li, F.F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In: Proceedings of the Workshop on Generative Model Based Vision, Washington, DC (June 2004)Google Scholar
  7. 7.
    Lin, Y., Liu, T.: Robust face detection with multi-class boosting. In: CVPR, pp. 680–687 (2005)Google Scholar
  8. 8.
    Liu, C., Shum, H.: Kullback-Leibler Boosting. In: CVPR, pp. 587–594 (2003)Google Scholar
  9. 9.
    Ong, E.-J., Bowden, R.: A boosted classifier tree for hand shape detection. In: International Conference on Automatic Face and Gesture Recognition, pp. 889–894 (2004)Google Scholar
  10. 10.
    Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Transactions on Patten Analysis and Machine Intelligence, PAMI (1998)Google Scholar
  11. 11.
    Roth, D., Yang, M., Ahuja, N.: A snowbased face detector. In: NIPS (2000)Google Scholar
  12. 12.
    Schneiderman, H., Kanade, T.: A statistical method for 3d object detection applied to faces and cars. In: ICCV (2000)Google Scholar
  13. 13.
    Sun, J., Rehg, J.M., Bobick, A.: Automatic cascade training with perturbation bias. In: CVPR (2004)Google Scholar
  14. 14.
    Torralba, A., Murphy, K., Freeman, W.T.: Sharing features: efficient boosting procedures for multiclass object detection. In: CVPR (2004)Google Scholar
  15. 15.
    Viola, P., Jones, M.: Fast and robust classification using asymmetric adaboost and a detector cascade. In: CVPR (2001)Google Scholar
  16. 16.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)Google Scholar
  17. 17.
    Viola, P., Jones, M.: Robust real-time face detection. In: IJCV (2004)Google Scholar
  18. 18.
    Wu, J., Rehg, J.M., Mullin, M.D.: Learning a rare event detection cascade by direct feature selection. In: NIPS (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ramana Isukapalli
    • 1
  • Ahmed Elgammal
    • 2
  • Russell Greiner
    • 3
  1. 1.Lucent Technologies, Bell Labs InnovationsWhippanyUSA
  2. 2.Rutgers UniversityNew BrunswickUSA
  3. 3.University of AlbertaEdmontonUSA

Personalised recommendations