A Rapidly Trainable and Global Illumination Invariant Object Detection System

  • Sri-Kaushik Pavani
  • David Delgado-Gomez
  • Alejandro F. Frangi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)

Abstract

This paper addresses the main difficulty in adopting Viola-Jones-type object detection systems: their training time. Large training times are the result of having to repeatedly evaluate thousands of Haar-like features (HFs) in a database of object and clutter class images. The proposed object detector is fast to train mainly because of three reasons. Firstly, classifiers that exploit a clutter (non-object) model are used to build the object detector and, hence, they do not need to evaluate clutter images during training. Secondly, the redundant HFs are heuristically pre-eliminated from the feature pool to obtain a small set of independent features. Thirdly, classifiers that have fewer parameters to be optimized are used to build the object detector. As a result, they are faster to train than their traditional counterparts. Apart from faster training, an additional advantage of the proposed detector is that its output is invariant to global illumination changes. Our results indicate that if the object class does not exhibit substantial intra-class variation, then the proposed method can be used to build accurate and real-time object detectors whose training time is in the order of seconds. The quick training and testing speed of the proposed system makes it ideal for use in content-based image retrieval applications.

Keywords

Training Image Training Time Face Detection Global Illumination Fast Training 
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.
  2. 2.
    Baker, S., Nayar, S.K.: Pattern rejection. In: CVPR 1996, pp. 544–549 (1996)Google Scholar
  3. 3.
    Huang, J., Mumford, D.: Statistics of natural images and models. In: CVPR 1999, pp. 541–547 (1999)Google Scholar
  4. 4.
    Li, S.Z., Zhu, L., Zhang, Z., Blake, A., Zhang, H., 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
  5. 5.
    McCane, B., Novins, K.: On training cascade face detectors. In: IVCNZ 2003, pp. 239–244 (2003)Google Scholar
  6. 6.
    Papageorgiou, C.P., Oren, M., Poggio, T.: A general framework for object detection. In: ICCV 1998, pp. 555–562 (1998)Google Scholar
  7. 7.
    Pham, M.-T., Cham, T.-J.: Fast training and selection of Haar features using statistics in boosting-based face detection. In: ICCV 2007, pp. 1–7 (2007)Google Scholar
  8. 8.
    Roth, D., Yang, M., Ahuja, N.: A SNoW-based face detector. In: NIPS 2000, pp. 855–861 (2000)Google Scholar
  9. 9.
    Rowley, H.A., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE TPAMI 20(1), 23–38 (1998)Google Scholar
  10. 10.
    Schapire, R.E.: A brief introduction to boosting. In: IJCAI 1999, pp. 1401–1406 (1999)Google Scholar
  11. 11.
    Schneiderman, H., Kanade, T.: A statistical method for 3D object detection applied to faces and cars. In: CVPR 2000, pp. 746–751 (2000)Google Scholar
  12. 12.
    Stojmenovic, M.: Pre-eliminating features for fast training in real time object detection in images with a novel variant of AdaBoost. In: CIS 2006, pp. 1–6 (2006)Google Scholar
  13. 13.
    Viola, P., Jones, M.J.: Robust real-time face detection. IJCV 57(2), 137–154 (2004)CrossRefGoogle Scholar
  14. 14.
    Wu, J., Brubaker, S.C., Mullin, M.D., Rehg, J.M.: Fast asymmetric learning for cascade face detection. IEEE TPAMI 30(3), 369–382 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sri-Kaushik Pavani
    • 1
    • 2
  • David Delgado-Gomez
    • 1
    • 2
  • Alejandro F. Frangi
    • 1
    • 2
    • 3
  1. 1.Research Group for Computational Imaging & Simulation Technologies in BiomedicineUniversitat Pompeu FabraBarcelonaSpain
  2. 2.Networking Research Center on Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN)Spain
  3. 3.Catalan Institution for Research and Advanced Studies (ICREA)Spain

Personalised recommendations