An Empirical-Statistical Agenda for Recognition

  • David Forsyth
Chapter
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1681)

Abstract

This piece first describes what I see as the significant weaknesses in current un- derstanding of object recognition. We lack good schemes for: using unreliable information — like radiometric measurements — effectively; integrating poten- tially contradictory cues; revising hypotheses in the presence of new information; determining potential representations from data; and suppressing individual dif- ferences to obtain abstract classes. The problems are difficult, but none are unapproachable, given a change of emphasis in our research.

Keywords

Feature Selection Probabilistic Model Object Recognition Markov Chain Monte Carlo Method Grid Edge 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Y. Amit, D. Geman, and K. Wilder. Joint induction of shape features and tree classifiers. IEEE T. Pattern Analysis and Machine Intelligence, 19(11):1300–1305, 1997.CrossRefGoogle Scholar
  2. [2]
    T.O. Binford. Visual perception by computer. In Proc. IEEE Conference on Systems and Control, 1971.Google Scholar
  3. [3]
    G. Buchsbaum. A spatial processor model for object colour perception. J. Franklin Inst., 310:1–26, 1980.CrossRefGoogle Scholar
  4. [4]
    G. Finlayson. Colour in perspective. IEEE T. Pattern Analysis and Machine Intelligence, 18:1034–1038, 1996.CrossRefGoogle Scholar
  5. [5]
    D.A. Forsyth. A novel algorithm for colour constancy. Int. J. Computer Vision, 5:5–36, 1990.CrossRefGoogle Scholar
  6. [6]
    D.A. Forsyth Sampling, Resampling and Colour Constancy. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 1991.Google Scholar
  7. [7]
    P.J. Green. Reversible jump markov chain monte carlo computation and bayesian model determination. Biometrika, 82(4):711–732, 1995.MATHCrossRefMathSciNetGoogle Scholar
  8. [8]
    H. Helson. Some factors and implications of colour constancy. J. Opt. Soc. America, 48:555–567, 1934.Google Scholar
  9. [9]
    C-Y. Huang, O.T. Camps, and T. Kanungo. Object recognition using appearance-based parts and relations. In IEEE Conf. on Computer Vision and Pattern Recog-nition, pages 877–83, 1997.Google Scholar
  10. [10]
    Mark Jerrum and Alistair Sinclair. The markov chain monte carlo method: an approach to approximate counting and integration. In D.S. Hochbaum, editor, Approximation Algorithms for NP-hard Problems. PWS Publishing, Boston, 1996.Google Scholar
  11. [11]
    D.B. Judd. Hue, saturation and lightness of surface colors with chromatic illumination. J. Opt. Soc. America, 30:2–32, 1940.CrossRefGoogle Scholar
  12. [12]
    G.J. Klinker, S.A. Shafer, and T. Kanade. A physical approach to color image understanding. Int. J. Computer Vision, 4(1):7–38, 199.Google Scholar
  13. [13]
    E.H. Land and J.J. McCann. Lightness and retinex theory. J. Opt. Soc. Am., 61(1):1–11, 1971.Google Scholar
  14. [14]
    H.C. Lee. Method for computing the scene-illuminant chromaticity from specular highlights. J. Opt. Soc. Am.-A, 3:1694–1699, 1986.Google Scholar
  15. [15]
    L.T. Maloney and B.A. Wandell. A computational model of color constancy. J. Opt. Soc. Am, 1:29–33, 1986.Google Scholar
  16. [16]
    D.H. Marimont and B.A. Wandell. Linear models of surface and illuminant spectra. J. Opt. Soc. Am.-A, 9:1905–1913, 1992.Google Scholar
  17. [17]
    D. J. Murdoch and P. J. Green. Exact sampling from a continuous state space. To appear in the Scandinavian Journal of Statistics, 1998.Google Scholar
  18. [18]
    R.M. Neal. Probabilistic inference using markov chain monte carlo methods. Computer science tech report crg-tr-93-1, University of Toronto, 1993.Google Scholar
  19. [19]
    James G. Propp and David B. Wilson. Exact sampling with coupled markov chains and applications to statistical mechanics. Random Structures and Algorithms, 9:223–252, 1996.MATHCrossRefMathSciNetGoogle Scholar
  20. [20]
    E. Rosch and C.B. Mervis. Family resemblances: Studies in the internal structure of categories. Cognitive Psychology, 7:573–605, 1975.CrossRefGoogle Scholar
  21. [21]
    E. Rosch, C.B. Mervis, W.E. Gray, D.M. Johnson, and P. Boyes-Braim. Basic objects in natural categories. Cognitive Psychology, 8:382–439, 1976.CrossRefGoogle Scholar
  22. [22]
    A. Zisserman, D.A. Forsyth, J.L. Mundy, C.A. Rothwell, and J.S. Liu. 3d object recognition using invariance. Articial Intelligence, 78:239–288, 1995.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • David Forsyth
    • 1
  1. 1.Computer Science DivisionBerkeleyUSA

Personalised recommendations