Limitations of non model-based recognition schemes

  • Yael Moses
  • Shimon Ullman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


Approaches to visual object recognition can be divided into model-based and non model-based schemes. In this paper we establish some limitations on non model-based recognition schemes. We show that a consistent non model-based recognition scheme for general objects cannot discriminate between objects. The same result holds even if the recognition function is imperfect, and is allowed to mis-identify each object from a substantial fraction of the viewing directions. We then consider recognition schemes restricted to classes of objects. We define the notion of the discrimination power of a consistent recognition function for a class of objects. The function's discrimination power determines the set of objects that can be discriminated by the recognition function. We show how the properties of a class of objects determine an upper bound on the discrimination power of any consistent recognition function for that class.


  1. 1.
    Bolles, R.C. and Cain, R.A. 1982. Recognizing and locating partially visible objects: The local-features-focus method. Int. J. Robotics Research, 1(3), 57–82.Google Scholar
  2. 2.
    Brooks, R.A. 1981. Symbolic reasoning around 3-D models and 2-D images, Artificial Intelligence J., 17, 285–348.Google Scholar
  3. 3.
    Burns, J. B., Weiss, R. and Riseman, E.M. 1990. View variation of point set and line segment features. Proc. Image Understanding Workshop, Sep., 650–659.Google Scholar
  4. 4.
    Cannon, S.R., Jones, G.W., Campbell, R. and Morgan, N.W. 1986. A computer vision system for identification of individuals. Proc. IECON 86 0, WI., 1, 347–351.Google Scholar
  5. 5.
    Clemens, D.J. and Jacobs, D.W. 1990. Model-group indexing for recognition. Proc. Image Understanding Workshop, Sep., 604–613.Google Scholar
  6. 6.
    Forsyth, D., Mundy, L., Zisserman, A., Coelho, C., Heller A. and Rothwell, C. 1991. Invariant Descriptors for 3-D object Recognition and pose. IEEE Trans. on PAMI. 13(10), 971–991.Google Scholar
  7. 7.
    Grimson, W.E.L. and Lozano-Pérez, T. 1984. Model-based recognition and localization from sparse data. Int. J. Robotics Research, 3(3), 3–35.Google Scholar
  8. 8.
    Grimson, W.E.L. and Lozano-Pérez, T. 1987. Localizing overlapping parts by searching the interpretation tree. IEEE Trans. on PAMI. 9(4), 469–482.Google Scholar
  9. 9.
    Horn B. K.P. 1977. Understanding image intensities, Artificial Intelligence J., 8(2), 201–231Google Scholar
  10. 10.
    Huttenlocher, D.P. and Ullman, S. 1987. Object recognition using alignment. Proceeding of ICCV Conf., London, 102–111.Google Scholar
  11. 11.
    Kanade, T. 1977. Computer recognition of human faces. Birkhauser Verlag. Basel and Stuttgart.Google Scholar
  12. 12.
    Lowe, D.G. 1985. Three dimensional object recognition from single two-dimensional images. Robotics research Technical Report 202, Couraant Inst. of Math. Sciences, N. Y. University.Google Scholar
  13. 13.
    Moses, Y, and Ullman S. 1991. Limitations of non model-based recognition schemes. AI MEMO No 1301, The Artificial Intelligence Lab., M.I.T.Google Scholar
  14. 14.
    Phong, B.T. 1975. Illumination for computer generated pictures. Communication of the ACM, 18(6), 311–317.Google Scholar
  15. 15.
    Poggio T., and Edelman S. 1990. A network that learns to recognize three dimensional objects. Nature, 343, 263–266.PubMedGoogle Scholar
  16. 16.
    Ullman S. 1977. Transformability and object identity. Perception and Psychophysics, 22(4), 414–415.Google Scholar
  17. 17.
    Ullman S. 1989. Alignment pictorial description: an approach to object recognition. Cognition, 32(3), 193–254.PubMedGoogle Scholar
  18. 18.
    Wong, K.H., Law, H.H.M. and Tsang P.W.M, 1989. A system for recognizing human faces, Proc. ICASSP, 1638–1642.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Yael Moses
    • 1
  • Shimon Ullman
    • 1
  1. 1.Dept. of Applied Mathematics and Computer ScienceThe Weizmann Institute of ScienceRehovotIsrael

Personalised recommendations