Distinctive Features Should Be Learned

  • Justus H. Piater
  • Roderic A. Grupen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1811)

Abstract

Most existing machine vision systems perform recognition based on a fixed set of hand-crafted features, geometric models, or eigen-subspace decomposition. Drawing from psychology, neuroscience and intuition, we show that certain aspects of human performance in visual discrimination cannot be explained by any of these techniques. We argue that many practical recognition tasks for artificial vision systems operating under uncontrolled conditions critically depend on incremental learning. Loosely motivated by visuocortical processing, we present feature representations and learning methods that perform biologically plausible functions. The paper concludes with experimental results generated by our method.

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 Trans. Pattern Anal. Mach. Intell., 19(11):1300–1305, 1997.CrossRefGoogle Scholar
  2. 2.
    I. Biederman. Recognition-by-components: A theory of human image understanding. Psychological Review, 94:115–147, 1987.CrossRefGoogle Scholar
  3. 3.
    W. T. Freeman and E. H. Adelson. The design and use of steerable filters. IEEE Trans. Pattern Anal. Mach. Intell., 13(9):891–906, 1991.CrossRefGoogle Scholar
  4. 4.
    I. Gauthier and M. J. Tarr. Becoming a “Greeble” expert: Exploring mechanisms for face recognition. Vision Research, 37(12):1673–1682, 1997.CrossRefGoogle Scholar
  5. 5.
    E. J. Gibson and E. S. Spelke. The development of perception. In J. H. Flavell and E. M. Markman, editors, Handbook of Child Psychology Vol. III: Cognitive Development, chapter 1, pages 2–76. Wiley, 4th edition, 1983.Google Scholar
  6. 6.
    D. Marr. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. Freeman, San Francisco, 1982.Google Scholar
  7. 7.
    S. A. Nene, S. K. Nayar, and H. Murase. Columbia object image library (COIL-20). Technical Report CUCS-005-96, Columbia University, New York, NY, Feb. 1996.Google Scholar
  8. 8.
    J. H. Piater and R. A. Grupen. Toward learning visual discrimination strategies. In Proc. Computer Vision and Pattern Recognition (CVPR’ 99), volume 1, pages 410–415, Ft. Collins, CO, June 1999. IEEE Computer Society.Google Scholar
  9. 9.
    A. D. Pick. Improvement of visual and tactual form discrimination. J. Exp. Psychol., 69:331–339, 1965.CrossRefGoogle Scholar
  10. 10.
    R. P. N. Rao and D. H. Ballard. An active vision architecture based on iconic representations. Artificial Intelligence, 78:461–505, 1995.CrossRefGoogle Scholar
  11. 11.
    P. G. Schyns, R. L. Goldstone, and J.-P. Thibaut. The development of features in object concepts. Behavioral and Brain Sciences, 21(1):1–54, 1998.CrossRefGoogle Scholar
  12. 12.
    P. G. Schyns and L. Rodet. Categorization creates functional features. J. Exp. Psychol.: Learning, Memory, and Cognition, 23(3):681–696, 1997.CrossRefGoogle Scholar
  13. 13.
    J. R. Silver and H. A. Rollins. The effects of visual and verbal feature-emphasis on form discrimination in preschool children. J. Exp. Child Psychol., 16:205–216, 1973.CrossRefGoogle Scholar
  14. 14.
    J. W. Tanaka and M. Taylor. Object categories and expertise: Is the basic level in the eye of the beholder? Cognitive Psychology, 23:457–482, 1991.CrossRefGoogle Scholar
  15. 15.
    J.-P. Thibaut. The development of features in children and adults: The case of visual stimuli. In Proc. 17th Annual Meeting of the Cognitive Science Society, pages 194–199. Lawrence Erlbaum, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Justus H. Piater
    • 1
  • Roderic A. Grupen
    • 1
  1. 1.University of MassachusettsAmherstUSA

Personalised recommendations