Advertisement

Applying VC-dimension analysis to object recognition

  • Michael Lindenbaum
  • Shai Ben-David
Recognition I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)

Abstract

We analyze the amount of information needed to carry out various model-based recognition tasks, in the context of a probabilistic data collection model. We focus on objects that may be described as semi-algebraic subsets of a Euclidean space, and on a wide class of object transformations, including perspective and affine transformations of 2D objects, and perspective projections of 3D objects. Our approach borrows from computational learning theory. We draw close relations between recognition tasks and a certain learnability framework. We then apply basic techniques of learnability theory to derive upper bounds on the number of data features that (provably) suffice for drawing reliable conclusions. The bounds are based on a quantitative analysis of the complexity of the hypotheses class that one has to choose from. Our central tool is the VC-dimension, which is a well studied parameter measuring the combinatorial complexity of families of sets. It turns out that these bounds grow linearly with the task complexity, measured via the VC-dimension of the class of objects one deals with.

Keywords

Recognition Task Data Feature Concept Class True Object Object Instance 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [BEHW89]
    Blumer, A., A. Ehrenfeucht, D. Haussler and M.K. Warmuth, 1989, “Learnability and The Vapnik-Chervonenkis Dimension”, JACM, 36(4), pp. 929–965.Google Scholar
  2. [BL93]
    S. Ben-David and M. Lindenbaum, 1993, “Localization vs. Identification of Semi-Algebraic Sets”, Proceedings of the 6th ACM Conference on Computational Learning Theory, pp. 327–336.Google Scholar
  3. [C75]
    Collins, G.E., 1975, “Quantifier Elimination for Real Closed Fields by Cylindrical Algebraic Decomposition”, Proceedings of the 2nd GI Conf. On Automata Theory and Formal Languages, Springer Lec. Notes Comp. Sci. 33, pp. 515–532.Google Scholar
  4. [GJ93]
    Goldberg P. and M. Jerrum, 1993, “Bounding the Vapnik-Chervonenkis Dimension of Concept Classes Parametrized by Real Numbers”, Proceedings of the 6th ACM Conference on Computational Learning Theory, pp. 361–368.Google Scholar
  5. [GTM89]
    Gottschalk P.G., J.L. Turney, and T.N. Mudge, 1989, “Efficient Recognition of Partially Visible Objects Using a Logarithmic Complexity Matching Technique”, Int. J. of Rob. Res., 8(6), pp. 110–131.Google Scholar
  6. [GH91]
    Grimson, W.E.L., and D.P. Huttenlocher, 1991, “On the Verification of Hypothesized Matches in Model-Based Recognition”, IEEE Trans. on Pattern Analysis and Mach. Intel., PAMI-13(12), pp. 1201–1213.Google Scholar
  7. [GHJ92]
    Grimson, W.E.L., D.P. Huttenlocher, and D.W. Jacobs, 1992, “A study of affine Matching with Bounded sensor error”, Second Europ. Conf. Comp. Vision, pp. 291–306.Google Scholar
  8. [L92]
    M. Lindenbaum, “Bounds on Shape Recognition Performance”, 1993. Proceedings of the 7th ICIAP, Italy.Google Scholar
  9. [LB93]
    M. Lindenbaum and S. Ben-David, “Applying VC-dimension Analysis to Object Recognition”, 1993, CIS report No. 9330, Computer Science Department, Technion.Google Scholar
  10. [M93]
    Maybank, S.J., 1993, Probabilistic Analysis of the Application of the Cross Ratio to Model Based Vision”, Manuscript.Google Scholar
  11. [M64]
    Milnor, J., 1964, “On the Betti Numbers of Real Varieties”, Proc. Amer. Math. Soc. 15, pp. 275–280.Google Scholar
  12. [MH90]
    Mundy, J.L. and A.J. Heller, 1990, “The Evolution and Testing of Model-Based Object Recognition Systems”, Proc. 3rd ICCV, pp. 268–282.Google Scholar
  13. [VC71]
    Vapnik, V.N. and A.Y. Chervonenkis, 1971, “On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities”, Theory of Probability and its applications, 16(2), pp. 264–280.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Michael Lindenbaum
    • 1
  • Shai Ben-David
    • 1
  1. 1.Computer Science DepartmentTechnionHaifaIsrael

Personalised recommendations