Learning to Recognize 3D Objects with SNoW

  • Ming-Hsuan Yang
  • Dan Roth
  • Narendra Ahuja
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1842)

Abstract

This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or incrementally learned feature space and is specifically tailored for learning in the presence of a very large number of features. We use pixel-based and edge-based representations in large scale object recognition experiments in which the performance of SNoW is compared with that of Support Vector Machines (SVMs) and nearest neighbor using the 100 objects in the Columbia Image Object Database (COIL-100). Experimental results show that the SNoW-based method outperforms the SVM-based system in terms of recognition rate and the computational cost involved in learning. Most importantly, SNoW’s performance degrades more gracefully when the training data contains fewer views. The empirical results also provide insight into practical and theoretical considerations on view-based methods for 3D object recognition.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    A. Blum. Learning boolean functions in an infinite attribute space. Machine Learning, 9(4):373–386, Oct. 1992.Google Scholar
  2. 2.
    J. F. Canny. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679–698, 1986.CrossRefGoogle Scholar
  3. 3.
    A. Carleson, C. Cumby, J. Rosen, and D. Roth. The SNoW learning architecture. Technical Report UIUCDCS-R-99-2101, UIUC Computer Science Department, May 1999.Google Scholar
  4. 4.
    C. Cortes and V. Vapnik. Support vector networks. Machine Learning, 20, 1995.Google Scholar
  5. 5.
    A. R. Golding and D. Roth. A winnow based approach to context-sensitive spelling correction. Machine Learning, 34:107–130, 1999. Special Issue on Machine Learning and Natural Language.MATHCrossRefGoogle Scholar
  6. 6.
    M. Kearns and U. Vazirani. Introduction to computational Learning Theory. MIT Press, 1994.Google Scholar
  7. 7.
    J. Kivinen and M. K. Warmuth. Exponentiated gradient versus gradient descent for linear predictors. In Proceedings of the Annual ACM Symp. on the Theory of Computing, 1995.Google Scholar
  8. 8.
    N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285–318, 1988.Google Scholar
  9. 9.
    N. Littlestone. Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow. In Proc. 4th Annu. Workshop on Comput. Learning Theory, pages 147–156, San Mateo, CA, 1991. Morgan Kaufmann.Google Scholar
  10. 10.
    M. Munoz, V. Punyakanok, D. Roth, and D. Zimak. A learning approach to shallow parsing. In EMNLP-VLC’99, the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, June 1999.Google Scholar
  11. 11.
    H. Murase and S. K. Nayar. Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision, 14:5–24, 1995.CrossRefGoogle Scholar
  12. 12.
    S. K. Nayar, S. A. Nene, and H. Murase. Real-time 100 object recognition system. In Proceedings of IEEE International Conference on Robotics and Automation, 1996.Google Scholar
  13. 13.
    T. Poggio and S. Edelman. A network that learns to recognize 3d objects. Nature, 343:263–266, 1990.CrossRefGoogle Scholar
  14. 14.
    M. Pontil and A. Verri. Support vector machines for 3d object recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(6):637–646, 1998.CrossRefGoogle Scholar
  15. 15.
    D. Roobaert and M. V. Hulle. View-based 3d object recognition with support vector machines. In IEEE International Workshop on Neural Networks for Signal Processing, 1999.Google Scholar
  16. 16.
    D. Roth. Learning to resolve natural language ambiguities: A unified approach. In Proceedings of the Fifteenth National Conference on Artificial Intelligence, pages 806–813, 1998.Google Scholar
  17. 17.
    B. Schölkopf. Support Vector Learning. PhD thesis, Informatik der Technischen Universitat Berlin, 1997.Google Scholar
  18. 18.
    M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71–86, 1991.CrossRefGoogle Scholar
  19. 19.
    L. G. Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134–1142, Nov. 1984.Google Scholar
  20. 20.
    V. Vapnik. The Nature of Statistical Learning Theory. Springer, 1995.Google Scholar
  21. 21.
    M.-H. Yang, D. Roth, and N. Ahuja. A SNoW-based face detector. In NIPS-12; The 1999 Conference on Advances in Neural Information Processing Systems, pages 855–861. MIT Press, 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Ming-Hsuan Yang
    • 1
  • Dan Roth
    • 1
  • Narendra Ahuja
    • 1
  1. 1.Department of Computer Science and Beckman InstituteUniversity of Illinois at Urbana-ChampaignUrbana

Personalised recommendations