Recognizing 3-D objects with linear support vector machines

  • Massimiliano Pontil
  • Stefano Rogai
  • Alessandro Verri
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1407)


In this paper we propose a method for 3-D object recognition based on linear Support Vector Machines (SVMs). Intuitively, given a set of points which belong to either of two classes, a linear SVM finds the hyperplane leaving the largest possible fraction of points of the same class on the same side, while maximizing the distance of either class from the hyperplane. The hyperplane is determined by a subset of the points of the two classes, named support vectors, and has a number of interesting theoretical properties. The proposed method does not require feature extraction and performs recognition on images regarded as points of a space of high dimension. We illustrate the potential of the recognition system on a database of 7200 images of 100 different objects. The remarkable recognition rates achieved in all the performed experiments indicate that SVMs are well-suited for aspect-based recognition, even in the presence of small amount of occlusions.


Support Vector Machine Object Space Linear Support Vector Machine Object Pair Margin Vector 
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.
    Bazaraa, M., Shetty, C.M.: Nonlinear programming. (John Wiley, New York, 1979).Google Scholar
  2. 2.
    Brunelli, R., Poggio, T.: Face Recognition: Features versus Templates. IEEE Trans. on PAMI, 15 (1993) 1042–1052Google Scholar
  3. 3.
    Cortes C., Vapnik, V.N.: Support Vector Network. Machine learning 20 (1995) 1–25Google Scholar
  4. 4.
    Edelman, S., Bulthoff, H., Weinshall, D.: Stimulus Familiarity Determines Recognition Strategy for Novel 3-D Objects. AI Memo No. 1138, MIT, Cambridge (1989)Google Scholar
  5. 5.
    Murase, N., Nayar, S.K.: Visual Learning and Recognition of 3-D Object from Appearance. Int. J. Comput. Vision 14 (1995) 5–24CrossRefGoogle Scholar
  6. 6.
    Osuna, E., Freund, R., Girosi, F.: Training Support Vector Machines: an Applications to Face Detection. Proc. Int. Conf. Computer Vision and Pattern Recognition, Puerto Rico, (1997)Google Scholar
  7. 7.
    Poggio, T., Edelman, S.: A Network that Learns to Recognize Three-Dimensional Objects. Nature 343 (1990) 263–266CrossRefGoogle Scholar
  8. 8.
    Pontil, M., Verri, A.: Properties of Support Vector Machines. Neural Computation 10 (1998) 977–966CrossRefGoogle Scholar
  9. 9.
    Pontil, M., Verri, A.: Support Vector Machines for 3-D Objects Recognition. IEEE Trans. on PAMI (to appear)Google Scholar
  10. 10.
    Tarr, M., Pinker, S.: Mental Rotation and Orientation-Dependence in Shape Recognition. Cognitive Psychology 21 (1989) 233–282CrossRefGoogle Scholar
  11. 11.
    Vapnik, V.N., Chervonenkis, A.J.: On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab Appl. 16 (1971) 264–280zbMATHCrossRefGoogle Scholar
  12. 12.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. (Springer-Verlag, New York, 1995).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Massimiliano Pontil
    • 1
  • Stefano Rogai
    • 2
  • Alessandro Verri
    • 2
  1. 1.Center for Biological and Computational LearningMITCambridgeUSA
  2. 2.INFM - DISIUniversità di GenovaGenova (I)

Personalised recommendations