Hierarchical object description using invariants

  • Charles A. Rothwell
Part of the Lecture Notes in Computer Science book series (LNCS, volume 825)


Invariant indexing functions have recently been shown to be effective for producing efficient recognition algorithms. However, the most useful shape descriptors for recognition are local or semi-local rather than global. In this paper we introduce an approach that ties together local invariant descriptions into larger object descriptions. The method works well for planar objects and has been used within two different recognition systems.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Åström, K. “Affine Invariants of Planar Sets,” TR, Department of Mathematics, Lund Institute of Technology, Sweden, 1993.Google Scholar
  2. 2.
    Bolles, R. and Cain, R. “Recognising and Locating Partially Visible Objects: The Local-Feature-Focus Method,” IJRR, Vol. 1, No. 3, p. 57–82, 1982.Google Scholar
  3. 3.
    Brady, M. “Criteria for Representation of Shape,” in Human and Machine Vision, Beck, Hope and Rosenfeld editors, Academic Press, 1983.Google Scholar
  4. 4.
    Carlsson, S. “Projectively Invariant Decomposition of Planar Shapes,” in [21], p. 267–273, 1992.Google Scholar
  5. 5.
    Ettinger, G.J. “Large Hierarchical Object Recognition Using Libraries of Parameterized Model Sub-Parts,” Proceedings CVPR88, p. 32–41, 1988.Google Scholar
  6. 6.
    Forsyth, D.A., Mundy, J.L., Zisserman, A.P., Coelho, C., Heller, A. and Rothwell, C.A. “Invariant Descriptors for 3-D Object Recognition and Pose,” IEEE Trans. PAMI, Vol. 13, No. 10, p. 971–991, October 1991.Google Scholar
  7. 7.
    Barrett, E.B., Payton, P.M. and Brill, M.H. “Contributions to the Theory of Projective Invariants for Curves in Two and Three Dimensions,” Proceedings 1st DARPA-ESPRIT Workshop on Invariance, p. 387–425, March 1991.Google Scholar
  8. 8.
    Binford, T.O. “Inferring Surfaces from Images,” Artificial Intelligence, Vol. 17, p. 205–244, 1981.Google Scholar
  9. 9.
    Binford, T.O. and Levitt, T.S. “Quasi-Invariants: Theory and Explanation,” Proceeding Darpa IUW, p. 819–829, 1993.Google Scholar
  10. 10.
    Canny, J.F. “A Computational Approach to Edge Detection,” IEEE Trans. PAMI, Vol. 8, No. 6, p. 679–698, 1986.Google Scholar
  11. 11.
    Grimson, W.E.L. Object Recognition by Computer, The Role of Geometric Constraints, MIT Press, 1990.Google Scholar
  12. 12.
    Jacobs, D.W. “Space Efficient 3D Model Indexing,” Proceedings CVPR92, p. 439–444, 1992.Google Scholar
  13. 13.
    Keren, D., Subrahmonia, J. and Cooper, D.B. “Robust Object Recognition Based on Implicit Algebraic Curves and Surfaces,” Proceedings CVPR92, p. 791–794, 1992.Google Scholar
  14. 14.
    Lamdan, Y., Schwartz, J.T. and Wolfson, H.J. “Object Recognition by Affine Invariant Matching,” Proceedings CVPR88, p. 335–344, 1988.Google Scholar
  15. 15.
    Lowe, D.G. Perceptual Organization and Visual Recognition, Kluwer Academic Publishers, 1985.Google Scholar
  16. 16.
    Liu, J., Mundy, J.L., Forsyth, D.A., Zisserman, A. and Rothwell, C.A. “Efficient Recognition of Rotationally Symmetric Surfaces and Straight Homogeneous Generalized Cylinders,” Proceedings CVPR93, p. 123–128, 1993.Google Scholar
  17. 17.
    Marr, D. Vision, Freeman, 1982.Google Scholar
  18. 18.
    Maybank, S.J. “The Projective Geometry of Ambiguous Surfaces,” Proc. R. Soc. Lond., Series A, Vol. 332, p. 1–47, 1990.Google Scholar
  19. 19.
    Mohr, R. and Morin, L. “Relative Positioning from Geometric Invariants,” Proceedings CVPR91, p. 139–144, 1991.Google Scholar
  20. 20.
    Moons, T., Pauwels, E., Van Gool, L. and Oosterlinck, A. “Viewpoint Invariant Characterization of Objects Composed of Different Rigid Parts: a Mathematical Framework,” in Geometry and Topology of Submanifolds, Vol. 5., Verstraelen, P. and Dillen, F. editors, World Scientific, 1993.Google Scholar
  21. 21.
    Mundy, J.L. and Zisserman, A.P. Geometric Invariance in Computer Vision, MIT Press, 1992.Google Scholar
  22. 22.
    Nielsen, L. “Automated Guidance of Vehicles using Vision and Projective Invariant Marking,” Automatica, Vol. 24, p. 135–148, 1988.Google Scholar
  23. 23.
    Rothwell, C.A., Zisserman, A., Forsyth, D.A. and Mundy, J.L. “Canonical Frames for Planar Object Recognition,” Proceedings ECCV2, p. 757–772, 1992.Google Scholar
  24. 24.
    Rothwell, C.A., Forsyth, D.A., Zisserman, A. and Mundy, J.L. “Extracting Projective Information from Single Views of 3D Point Sets,” Proceedings ICCV4, p. 573–582, 1993.Google Scholar
  25. 25.
    Rothwell, C.A. Object Recognition through Invariant Indexing, To appear OUP, 1994.Google Scholar
  26. 26.
    Sinclair, D.A. and Blake, A. “Isoperimetric Normalisation of Planar Curves,” TR, Department of Engineering Science, Oxford University, Oxford, 1993.Google Scholar
  27. 27.
    Taubin, G. and Cooper, D.B. “Object Recognition Based on Moment (or Algebraic) Invariants,” IBM TR-RC17387, IBM T.J. Watson Research Centre, P.O. Box 704, Yorktown Heights, NY 10598, 1991.Google Scholar
  28. 28.
    Taubin, G. “An Improved Algorithm for Algebraic Curve and Surface Fitting,” Proceedings ICCV4, p. 658–665, 1993.Google Scholar
  29. 29.
    Van Gool, L. Kempenaers, P. and Oosterlinck, A. “Recognition and Semi-Differential Invariants,” Proceedings CVPR91, p. 454–460, 1991.Google Scholar
  30. 30.
    Wayner, P.C. “Efficiently Using Invariant Theory for Model-Based Matching,” Proceedings CVPR91, p. 473–478, 1991.Google Scholar
  31. 31.
    Weiss, I. “Projective Invariants of Shapes,” Proceedings DARPA Image Understanding Workshop, p. 1125–1134, April 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Charles A. Rothwell
    • 1
  1. 1.GE CRDSchenectadyUSA

Personalised recommendations