Components for Object Detection and Identification

  • Bernd Heisele
  • Ivaylo Riskov
  • Christian Morgenstern
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4170)


We present a component-based system for object detection and identification. From a set of training images of a given object we extract a large number of components which are clustered based on the similarity of their image features and their locations within the object image. The cluster centers build an initial set of component templates from which we select a subset for the final recognizer. The localization of the components is performed by normalized cross-correlation. Two types of components are used, gray value components and components consisting of the magnitudes of the gray value gradient.

In experiments we investigate how the component size, the number of the components, and the feature type affects the recognition performance. The system is compared to several state-of-the-art classifiers on three different data sets for object identification and detection.


Training Image Object Detection Search Region Equal Error Rate Gradient Component 
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.
    Bileschi, S., Wolf, L.: A unified system for object detection, texture recognition, and context analysis based on the standard model feature set. In: British Machine Vision Conference (BMVC) (2005)Google Scholar
  2. 2.
    Bileschi, S.M., Heisele, B.: Advances in Component-Based Face Detection. In: Lee, S.-W., Verri, A. (eds.) SVM 2002. LNCS, vol. 2388, pp. 135–143. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Crandall, D., Felzenszwalb, P., Huttenlocher, D.: Spatial priors for part-based recognition using statistical model. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10–17 (2005)Google Scholar
  4. 4.
    Dorko, G., Schmid, C.: Selection of scale invariant neighborhoods for object class recognition. In: International Conference on Computer Vision (ICCV), pp. 634–640 (2003)Google Scholar
  5. 5.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 264–271 (2003)Google Scholar
  6. 6.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Tecnical report, Dept. of Statistics, Stanford University (1998)Google Scholar
  7. 7.
    Heisele, B., Serre, T., Mukherjee, S., Poggio, T.: Hierarchical classification and feature reduction for fast face detection with support vector machines. Pattern Recognition 36(9), 2007–2017 (2003)MATHCrossRefGoogle Scholar
  8. 8.
    Heisele, B., Serre, T., Pontil, M., Vetter, T., Poggio, T.: Categorization by learning and combining object parts. In: Neural Information Processing Systems (NIPS), Vancouver (2001)Google Scholar
  9. 9.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit model. In: ECCV 2004 Workshop on Statistical Learning in Computer Vision (2004)Google Scholar
  10. 10.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  11. 11.
    Mohan, A., Papageorgiou, C., Poggio, T.: Example-based object detection in images by components. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 349–361 (2001)CrossRefGoogle Scholar
  12. 12.
    Morgenstern, C., Heisele, B.: Component-based recognition of objects in an office environment. A.I. Memo 232, Center for Biological and Computational Learning. MIT, Cambridge (2003)Google Scholar
  13. 13.
    Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., Poggio, T.: Pedestrian detection using wavelet templates. In: IEEE Conference on Computer Vision and Pattern Recognition, San Juan, pp. 193–199 (1997)Google Scholar
  14. 14.
    Osuna, E.: Support Vector Machines: Training and Applications. Ph.D thesis. MIT, Department of Electrical Engineering and Computer Science, Cambridge, MA (1998)Google Scholar
  15. 15.
    Poggio, T., Edelman, S.: A network that learns to recognize 3-D objects. Nature 343, 163–266 (1990)CrossRefGoogle Scholar
  16. 16.
    Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2(11), 1019–1025 (1999)CrossRefGoogle Scholar
  17. 17.
    Riesenhuber, M., Poggio, T.: The individual is nothing, the class everything: Psychophysics and modeling of recognition in object classes. A.I. Memo 1682, Center for Biological and Computational Learning. MIT, Cambridge (2000)Google Scholar
  18. 18.
    Rowley, H.A., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(1), 23–38 (1998)CrossRefGoogle Scholar
  19. 19.
    Schapire, R., Freund, Y., Bartlett, P., Lee, W.S.: Boosting the margin: A new explanation of effectiveness of voting methods. The Annals of Statistics 26(5), 1651–1686 (1998)MATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Serre, T., Riesenhuber, M., Louie, J., Poggio, T.A.: On the Role of Object-Specific Features for Real World Object Recognition in Biological Vision. In: Bülthoff, H.H., Lee, S.-W., Poggio, T.A., Wallraven, C. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 387–397. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  21. 21.
    Serre, T., Wolf, L., Poggio, T.: A new biologically motivated framework for robust object recognition. A.I. Memo 2004-26, Center for Biological and Computational Learning. MIT, Cambridge (2004)Google Scholar
  22. 22.
    Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression database. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI) 25(12), 1615–1618 (2003)CrossRefGoogle Scholar
  23. 23.
    Sung, K.-K.: Learning and Example Selection for Object and Pattern Recognition. Ph.D thesis. MIT, Artificial Intelligence Laboratory and Center for Biological and Computational Learning, Cambridge, MA (1996)Google Scholar
  24. 24.
    Ullman, S., Vidal-Naquet, M., Sali, E.: Visual features of intermdediate complexity and their use in classification. Nature Neuroscience 5(7), 682–687 (2002)Google Scholar
  25. 25.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 511–518 (2001)Google Scholar
  26. 26.
    Weber, M., Welling, W., Perona, P.: Towards automatic dscovery of object categories. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (June 2000)Google Scholar
  27. 27.
    Weisberg, S.: Applied Linear Regression. Wiley, New York (1980)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bernd Heisele
    • 1
    • 2
  • Ivaylo Riskov
    • 1
  • Christian Morgenstern
    • 1
  1. 1.Center for Biological and Computational Learning, M.I.T.CambridgeUSA
  2. 2.Honda Research Institute USBostonUSA

Personalised recommendations