Exploiting Object Characteristics Using Custom Features for Boosting-Based Classification

  • Arne Ehlers
  • Florian Baumann
  • Bodo Rosenhahn
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)


Typical feature pools used to train boosted object detectors contain various redundant and unspecific information which often yield less discriminative detectors. In this paper we introduce a feature mining algorithm taking domain specific knowledge into account. Our proposed feature pool contains rectangular shaped features generated from an image clustering algorithm applied on the mean image of the object training set. A combination of two such spatially separated rectangular regions yields a set of features which have a similar evaluation time like classical Haar-like features, but are much smarter (automatically) selected and more discriminative since image correlations can be more consequently exploited. Overall, training is faster and results in more selective detectors showing improved precision. Several experiments demonstrate the gain when using our proposed feature set in contrast to standard features.


  1. 1.
    Viola, P., Jones, M.J.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)CrossRefGoogle Scholar
  2. 2.
    Dollár, P., Tu, Z., Tao, H., Belongie, S.: Feature mining for image classification. In: CVPR. IEEE Computer Society (2007)Google Scholar
  3. 3.
    Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. In: Artificial Intelligence, vol. 97, pp. 245–271 (1997)Google Scholar
  4. 4.
    Koller, D., Sahami, M.: Toward optimal feature selection. In: ICML, pp. 284–292. Morgan Kaufmann (1996)Google Scholar
  5. 5.
    Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)zbMATHGoogle Scholar
  6. 6.
    Zhao, X., Chai, X., Niu, Z., Heng, C., Shan, S.: Context constrained facial landmark localization based on discontinuous haar-like feature. In: FG, pp. 673–678. IEEE (2011)Google Scholar
  7. 7.
    Sung, K.K., Poggio, T., Rowley, H.A., Baluja, S., Kanade, T.: MIT+CMU frontal face dataset a, b and c. MIT+CMU (1998)Google Scholar
  8. 8.
    Jain, V., Learned-Miller, E.: Fddb: A benchmark for face detection in unconstrained settings. Technical Report UM-CS-2010-009, University of Massachusetts, Amherst (2010)Google Scholar
  9. 9.
    Agarwal, S., Awan, A., Roth, D.: UIUC image database for car detection (2002)Google Scholar
  10. 10.
    Lienhart, R., Maydt, J.: An extended set of haar-like features for rapid object detection. IEEE ICIP 2002 (2002)Google Scholar
  11. 11.
    Stanciulescu, B., Breheret, A., Moutarde, F.: Introducing new adaboost features for real-time vehicle detection. In: COGIS (2007)Google Scholar
  12. 12.
    Moutarde, F., Stanciulescu, B., Breheret, A.: Real-time visual detection of vehicles and pedestrians with new efficient adaboost features. In: IEEE IROS (2008)Google Scholar
  13. 13.
    Pham, M.T., Gao, Y., Hoang, V.D.D., Cham, T.J.: Fast polygonal integration and its application in extending haar-like features to improve object detection. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010) (2010)Google Scholar
  14. 14.
    Smith, K., Carleton, A., Lepetit, V.: Fast ray features for learning irregular shapes. In: IEEE: ICCV, pp. 397–404 (2009)Google Scholar
  15. 15.
    Hartigan, J.A., Wong, M.A.: Algorithm as 136: A k-means clustering algorithm. Journal of the Royal Statistical Society 28(1), 100–108 (1979)zbMATHGoogle Scholar
  16. 16.
    Meyer, F.: Topographic distance and watershed lines. In: Signal Processing, vol. 38, pp. 113–125 (1994)Google Scholar
  17. 17.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: 9th Int. Conf. Computer Vision, vol. 1, pp. 10–17 (2003)Google Scholar
  18. 18.
    Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: Combining segmentation and recognition. In: IEEE Computer Vision and Pattern Recognition (2004)Google Scholar
  19. 19.
    Lantuéjoul, C.: La squelettisation et son application aux mesures topologiques des mosaiques poly- cristallines. PhD thesis, Ecole des Mines (1978)Google Scholar
  20. 20.
    Digabel, H., Lantuéjoul, C.: Iterative algorithms. In: Actes du Second Symposium Européen d’Analyse Quantitative des Microstructures en Sciences des Matériaux, pp. 85–99 (1977)Google Scholar
  21. 21.
    Schapire, R.E., Freund, Y., Bartlett, P., Lee, W.S.: Boosting the margin: A new explanation for the effectiveness of voting methods. In: Proceedings of the Fourteenth International Conference on Machine Learning (ICML), pp. 322–330 (1997)Google Scholar
  22. 22.
    The MPLab GENKI Database, u.S.: - (-)
  23. 23.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)CrossRefGoogle Scholar
  24. 24.
    Li, J., Wang, T., Zhang, Y.: Face detection using surf cascade. In: ICCV Workshops, pp. 2183–2190. IEEE (2011)Google Scholar
  25. 25.
    Jain, V., Learned-Miller, E.G.: Online domain adaptation of a pre-trained cascade of classifiers. In: CVPR, pp. 577–584. IEEE (2011)Google Scholar
  26. 26.
    Mikolajczyk, K., Schmid, C., Zisserman, A.: Human detection based on a probabilistic assembly of robust part detectors. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 69–82. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  27. 27.
    Subburaman, V.B., Marcel, S.: Fast Bounding Box Estimation based Face Detection. In: ECCV, Workshop on Face Detection: Where We Are, and What Next? (2010)Google Scholar
  28. 28.
    Bradski, G.: The opencv library. Dr. Dobb’s Journal of Software Tools (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Arne Ehlers
    • 1
  • Florian Baumann
    • 1
  • Bodo Rosenhahn
    • 1
  1. 1.Institut für Informationsverarbeitung (TNT)Leibniz Universität HannoverGermany

Personalised recommendations