More on Weak Feature: Self-correlate Histogram Distances

  • Sheng Wang
  • Qiang Wu
  • Xiangjian He
  • Wenjing Jia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7087)

Abstract

In object detection research, there is a discussion on weak feature and strong feature, feature descriptors, regardless of being considered as ’weak feature descriptors’ or ’strong feature descriptors’ does not necessarily imply detector performance unless combined with relevant classification algorithms. Since 2001, main stream object detection research projects have been following the Viola Jone’s weak feature (Haar-like feature) and AdaBoost classifier approach. Until 2005, when Dalal and Triggs have created the approach of a strong feature (Histogram of Oriented Gradient) and Support Vector Machine (SVM) framework for human detection.

This paper proposes an approach to improve the salience of a weak feature descriptor by using intra-feature correlation. Although the intensity histogram distance feature known as Histogram Distance of Haar Regions (HDHR) itself is considered as a weak feature and can only be used to construct a weak learner to learn an AdaBoost classifier. In our paper, we explore the pairwise correlations between each and every histograms constructed and a strong feature can then be formulated. With the newly constructed strong feature based on histogram distances, a SVM classifier can be trained and later used for classification tasks. Promising experimental results have been obtained.

Keywords

Weak feature Pairwise correlations Histogram distances SVM classifier 

References

  1. 1.
    Shechtman, E., Irani, M.: Matching Local Self-similarities across Images and Videos. In: Proc. CVPR, Minneapolis, pp. 1–8 (2007)Google Scholar
  2. 2.
    Walk, S., Majer, N., Schindler, K., Schiele, B.: New Features and Insights for Pedestrian Detection. In: Proc. CVPR, San Francisco, pp. 1030–1037 (2010)Google Scholar
  3. 3.
    Deselaers, T., Ferrari, V.: Global and Efficient Self-similarity for Object Classification and Detection. In: Proc. CVPR, San Francisco, pp. 1633–1640 (2010)Google Scholar
  4. 4.
    Perrotton, X., Sturzel, M., Roux, M.: Automatic Object Detection on Aerial Images Using Local Descriptors and Image Synthesis. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds.) ICVS 2008. LNCS, vol. 5008, pp. 302–311. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Zhang, H., Jia, W., He, X., Wu, Q.: Learning-Based License Plate Detection Using Global and Local Features. In: Proc. ICPR, Hong Kong, pp. 1102–1105 (2006)Google Scholar
  6. 6.
    Viola, P., Jones, M.: Rapid Object Detection Using A Boosted Cascade of Simple Features. In: Proc. CVPR, Kauai, pp. 511–518 (2001)Google Scholar
  7. 7.
    Porikli, F.: Integral Histogram: A Fast Way to Extract Histograms in Cartesian Spaces. In: Proc. CVPR, San Diego, pp. 829–836 (2005)Google Scholar
  8. 8.
    Kovesi, P.: University of Western, Australia, http://www.csse.uwa.edu.au/
  9. 9.
    Belongie, S., Malik, J.: Matching with Shape Contexts. In: Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries, Hilton Head, pp. 20–26 (2000)Google Scholar
  10. 10.
    Ludwig, O., Delgado, D., Goncalves, V., Nunes, U.: Trainable Classifier-Fusion Schemes: An Application to Pedestrian Detection. In: Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems, St. Louis, pp. 432–437 (2009)Google Scholar
  11. 11.
    Weyrauch, B., Huang, J., Heisele, B., Blanz, V.: Component-based Face Recognition with 3D Morphable Models. In: Proceedings of the First IEEE Workshop on Face Processing in Video, Washington, D.C, pp. 85–89 (2004)Google Scholar
  12. 12.
    Papageorgiou, C., Evgeniou, T., Poggio, T.: A Trainable Pedestrian Detection System. In: Proceedings of the IEEE International Conference on Intelligent Vehicles, Stuttgart, pp. 241–246 (1998)Google Scholar
  13. 13.
    Oren, M., Papageorgiou, C.P., Sinha, P., Osuna, E., Poggio, T.: Pedestrian Detection Using Wavelet Templates. In: Proc. CVPR, San Juan, pp. 193–199 (1997)Google Scholar
  14. 14.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: Proc. CVPR, San Diego, pp. 886–893 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Sheng Wang
    • 1
  • Qiang Wu
    • 1
  • Xiangjian He
    • 1
  • Wenjing Jia
    • 1
  1. 1.Research Centre for Innovation in IT Services and Applications (iNEXT)University of TechnologySydneyAustralia

Personalised recommendations