Advertisement

Canonical frames for planar object recognition

  • Charles A. Rothwell
  • Andrew Zisserman
  • David A. Forsyth
  • Joseph L. Mundy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)

Abstract

We present a canonical frame construction for determining projectively invariant indexing functions for non-algebraic smooth plane curves. These invariants are semi-local rather than global, which promotes tolerance to occlusion.

Two applications are demonstrated. Firstly, we report preliminary work on building a model based recognition system for planar objects. We demonstrate that the invariant measures, derived from the canonical frame, provide sufficient discrimination between objects to be useful for recognition. Recognition is of partially occluded objects in cluttered scenes. Secondly, jigsaw puzzles are assembled and rendered from a single strongly perspective view of the separate pieces. Both applications require no camera calibration or pose information, and models are generated and verified directly from images.

Keywords

Invariant Measure Distinguished Point Hash Table Algebraic Curf Planar Object 
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.

References

  1. 1.
    Asada, H. and Brady, M. “The Curvature Primal Sketch,” PAMI-8, No. 1, p.2–14, January 1986.Google Scholar
  2. 2.
    Ayache, N. and Faugeras, O.D. “HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects,” PAMI-8, No. 1, p.44–54, January 1986.Google Scholar
  3. 3.
    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 First DARPA-ESPRIT Workshop on Invariance, p.387–425, March 1991.Google Scholar
  4. 4.
    Beardsley, P.A. “Correction of radial distortion,” OUEL internal report 1896/91, 1991.Google Scholar
  5. 5.
    Blake, A. and Marinos, C. “Shape from Texture: Estimation, Isotropy and Moments,” Artificial Intelligence, Vol. 45, p.232–380, 1990.Google Scholar
  6. 6.
    Blake, A. and Sinclair,D. On the projective normalisation of planar shape, TR OUEL, in preparation, 1992.Google Scholar
  7. 7.
    Brady, M. and Yuille, A. “An Extremum Principle for Shape from Contour,” PAMI-6, No. 3, p.288–301, May 1984.Google Scholar
  8. 8.
    Canny J.F. “A Computational Approach to Edge Detection,” PAMI-6, No. 6. p.679–698, 1986.Google Scholar
  9. 9.
    Carlsson, S. “Projectively Invariant Decomposition of Planar Shapes,” Geometric Invariance in Computer Vision, Mundy, J.L. and Zisserman, A., editors, MIT Press, 1992.Google Scholar
  10. 10.
    Clemens, D.T. and Jacobs, D.W. “Model Group Indexing for Recognition,” Proceedings CVPR, p.4-9, 1991, and PAMI-13, No. 10, p. 1007–1017, October 1991.Google Scholar
  11. 11.
    Duda, R.O. and Hart P.E. Pattern Classification and Scene Analysis, Wiley, 1973.Google Scholar
  12. 12.
    Forsyth, D.A., Mundy, J.L., Zisserman, A.P. and Brown, C.M. “Projectively Invariant Representations Using Implicit Algebraic Curves,” Proceedings ECCV1, Springer-Verlag, p.427–436, 1990.Google Scholar
  13. 13.
    Freeman, H. and Gardner, I. “Apictorial Jigsaw Puzzles: The Computer Solution of a Problem in Pattern Recognition,” IEEE Transaction in Electronic Computers, Vol. 13, No. 2, p. 118–127, April 1964.Google Scholar
  14. 14.
    Huttenlocher, D.P. and Ullman, S. “Object Recognition Using Alignment,” Proceedings ICCV1, p. 102–111, 1987. or15. Huttenlocher D.P. “Fast Affine Point Matching: An Output-Sensitive Method,” Proceedings CVPR, p.263–268, 1991.Google Scholar
  15. 16.
    Kanatani, K. and Chou, T-C. “Shape From Texture: General Principle,” Artificial Intelligence, Vol. 38, No. 1, p.1–48, February 1989.Google Scholar
  16. 17.
    Kapur, D. and Mundy, J.L. “Fitting Affine Invariant Conics to Curves,” Geometric Invariance in Computer Vision, Mundy, J.L. and Zisserman, A., editors, MIT Press, to appear 1992.Google Scholar
  17. 18.
    Lamdan, Y., Schwartz, J.T. and Wolfson, H.J. “Object Recognition by Affine Invariant Matching,” Proceedings CVPR, p.335–344, 1988.Google Scholar
  18. 19.
    Lane, E.P. A Treatise on Projective Differential Geometry, University of Chicago press, 1941.Google Scholar
  19. 20.
    Marinos, C. and Blake, A. “Shape from Texture: the Homogeneity Hypothesis,” Proceedings ICCV3, p.350–354, 1990.Google Scholar
  20. 21.
    Mohr, R. and Morin, L. “Relative Positioning from Geometric Invariants,” Proceedings CVPR, p.139–144, 1991.Google Scholar
  21. 22.
    Mundy, J.L. and Heller, A.J. “The Evolution and Testing of a Model-Based Object Recognition System,” Proceedings ICCV3, p.268–282, 1990.Google Scholar
  22. 23.
    Rothwell, C.A., Zisserman, A. Forsyth, D.A. and Mundy, J.L. “Fast Recognition using Algebraic Invariants,” Geometric Invariance in Computer Vision, Mundy, J.L. and Zisserman, A., editors, MIT Press, 1992.Google Scholar
  23. 24.
    Semple, J.G. and Kneebone, G.T. Algebraic Projective Geometry, Oxford University Press, 1952.Google Scholar
  24. 25.
    Slama, C.C., editor, Manual of Photogrammetry, 4th edition, American Society of Photogrammetry, Falls Church VA, 1980.Google Scholar
  25. 26.
    Springer, C.E. Geometry and Analysis of Projective Spaces, Freeman, 1964.Google Scholar
  26. 27.
    Van Gool, L. Kempenaers, P. and Oosterlinck, A. “Recognition and Semi-Differential Invariants,” Proceedings CVPR, p.454–460, 1991.Google Scholar
  27. 28.
    Wayner, P.C. “Efficiently Using Invariant Theory for Model-based Matching,” Proceedings CVPR, p.473–478, 1991.Google Scholar
  28. 29.
    Weiss, I. “Projective Invariants of Shapes,” Proceeding DARPA Image Understanding Workshop, p.1125–1134, April 1988.Google Scholar
  29. 30.
    Witkin, A.P., “Recovering Surface Shape and Orientation from Texture” Artificial Intelligence, 17, p.17–45, 1981.Google Scholar
  30. 31.
    Wolfson, H., Schonberg, E., Kalvin, A. and Lamdan, Y. “Solving Jigsaw Puzzles by Computer,” Annals of Operational Research, Vol. 12, p.51–64, 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Charles A. Rothwell
    • 1
  • Andrew Zisserman
    • 1
  • David A. Forsyth
    • 2
  • Joseph L. Mundy
    • 3
  1. 1.Robotics Research Group, Department of Engineering ScienceOxford UniversityEngland
  2. 2.Department of Computer ScienceUniversity of IowaIowaUSA
  3. 3.The General Electric Corporate Research and Development LaboratorySchenectadyUSA

Personalised recommendations