Orientation Invariant Features for Multiclass Object Recognition

  • Michael Villamizar
  • Alberto Sanfeliu
  • Juan Andrade-Cetto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4225)


We present a framework for object recognition based on simple scale and orientation invariant local features that when combined with a hierarchical multiclass boosting mechanism produce robust classifiers for a limited number of object classes in cluttered backgrounds. The system extracts the most relevant features from a set of training samples and builds a hierarchical structure of them. By focusing on those features common to all trained objects, and also searching for those features particular to a reduced number of classes, and eventually, to each object class. To allow for efficient rotation invariance, we propose the use of non-Gaussian steerable filters, together with an Orientation Integral Image for a speedy computation of local orientation.


Feature Selection Object Recognition Object Class Integral Image Sift Descriptor 
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.


  1. 1.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. 15th IEEE Conf. Comput. Vision Pattern Recog., Kauai, pp. 511–518 (2001)Google Scholar
  3. 3.
    Li, L.: Multiclass boosting with repartitioning. In: Proc. 23rd Int. Conf. Machine Learning, Pittsburgh (to appear, 2006)Google Scholar
  4. 4.
    Eibl, G., Pfeiffer, K.P.: Multiclass boosting for weak classifiers. J. Mach. Learn. Res. 6, 189–210 (2005)MathSciNetGoogle Scholar
  5. 5.
    Torralba, A., Murphy, K., Freeman, W.: Sharing features: efficient boosting procedures for multiclass object detection. In: Proc. 18th IEEE Conf. Comput. Vision Pattern Recog., Washington, pp. 762–769 (2004)Google Scholar
  6. 6.
    Villamizar, M., Sanfeliu, A., Andrade-Cetto, J.: Computation of rotation local invariant features using the integral image for real time object detection. In: Proc. 18th IAPR Int. Conf. Pattern Recog., Hong Kong, IEEE Comp. Soc., (to appear, 2006)Google Scholar
  7. 7.
    Papageorgiou, C.P., Oren, M., Poggio, T.: A general framework for object detection. In: Proc. IEEE Int. Conf. Comput. Vision, Bombay, p. 555 (1998)Google Scholar
  8. 8.
    Yokono, J., Poggio, T.: Oriented filters for object recognition: An empirical study. In: Proc. 6th IEEE Int. Conf. Automatic Face Gesture Recog., Seoul, pp. 755–760 (2004)Google Scholar
  9. 9.
    Yokono, J., Poggio, T.: Rotation invariant object recognition from one training example. Technical Report 2004-010, MIT AI Lab (2004)Google Scholar
  10. 10.
    Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. IEEE Trans. Pattern Anal. Machine Intell. 13, 891–906 (1991)CrossRefGoogle Scholar
  11. 11.
    Schaffalitzky, F., Zisserman, A.: Multi-view matching for unordered image sets, or How do I organize my holiday snaps? In: Proc. 7th European Conf. Comput. Vision, Copenhagen, pp. 414–431. Springer, Heidelberg (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Michael Villamizar
    • 1
  • Alberto Sanfeliu
    • 1
  • Juan Andrade-Cetto
    • 2
  1. 1.Institut de Robòtica i Informàtica IndustrialUPC-CSICBarcelonaSpain
  2. 2.Computer Vision CenterUniversitat Autònoma de BarcelonaBellaterraSpain

Personalised recommendations