Using Curvature Information in the Decomposition and Representation of Planar Curves

  • Gregory Dudek
  • John Tsotsos
Part of the NATO ASI Series book series (volume 83)


This paper describes a new symbolic representation for planar curves. This representation is based on a segmentation of the curve based on regions of uniform curvature. Rather than smooth noisy data before doing the decomposition, the technique defines a family of functions that extract the segments of the curve as part of the smoothing process. The representation decomposes the curve at multiple scales and the parts produced appear to correspond to a natural decomposition of the curve. It also allows for multiple descriptions of some parts of the curve. The final representation can be rendered compact, avoids several common disadvantages in noisy curve description, and should be useful for recognition.


Curvature Function Smoothing Process Curvature Information Target Curvature Deformable Part Model 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Asada, H. and Brady, M. 1986. The curvature primal sketch. Pattern Analysis and Machine Intelligence, 8(1): 2–14.CrossRefGoogle Scholar
  2. Attneave, F. 1954. Some informational aspects of visual perception. Psychological Review, (61): 183–193.CrossRefGoogle Scholar
  3. Besl, P. J. 1988. Surfaces in Range Image Understanding. Springer-Verlag, New York, N.Y.CrossRefMATHGoogle Scholar
  4. Bhanu, B. and Faugeras, O. D. 1984. Shape matching of two-dimensional objects. PAMI, PAMI-6(2).Google Scholar
  5. Blake, A. and Zisserman, A. 1987. Visual Reconstruction. MIT Press, Cambridge, Mass.Google Scholar
  6. Brooks, R. A. 1981. Symbolic reasoning among 3-d models and 2-d images. AI, 17: 285–348.Google Scholar
  7. Connell, J. H. and Brady, M. 1985. Generating and generalizing models of visual objects. AI memo 823, MIT AI lab.Google Scholar
  8. Dudek, G. 1989. Curvature-tuned smoothness for representation and recognition. RCBV-TR-89–30, Dept, of computer science, University of Toronto.Google Scholar
  9. Grimson, E. 1981. From images to surfaces: a computational study of the human early From images to surfaces: a computational study of the human eraly visual system. MIT press, Cambridge, Mass.Google Scholar
  10. Hoffman, D. D. and Richards, W. A. 1984. Parts of recognition. Cognition, (18): 65–96.CrossRefGoogle Scholar
  11. Kehtarnavaz, N. and deFigueiredo, R. J. P. 1988. A 3-d contour segmentation scheme based on curvature and torsion. Pattern Analysis and Machine Intelligence, 10(5).Google Scholar
  12. Leyton, M. 1987. Symmetry-curvature duality. Computer Vision, Graphics and Image Processing, (38): 327–341.CrossRefGoogle Scholar
  13. Lowe, D. G. 1985. Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Boston, Mass.CrossRefGoogle Scholar
  14. Lowe, D. G. 1988. Organization of smooth image curves at multiple scales. Proceedings of the 2nd ICCV, pages 558–567.Google Scholar
  15. Marimont, D. H. 1984. A representation for image curves. AAAI, pages 237–242.Google Scholar
  16. Milios, E. 1988. Recovering shape deformation by an extrended circular image representation. Proceedings of the 2nd ICCV, pages 20–29.Google Scholar
  17. Mokhtarian, F. 1988. Evolution properties of space curves. JCCV, pages 100–105.Google Scholar
  18. Nishihara, H. K. 1981. Intensity, visible-surface, and volumetric representations. AI, 17: 265–284.Google Scholar
  19. Pentland, A. 1988. Automatic extraction of deformable part models. Vision Sciences TR-104, MIT Media Lab.Google Scholar
  20. Poggio, T., Torre, V., and Koch, C. 1985. Computational vision and regularization theory. Nature, 317: 314–319.CrossRefGoogle Scholar
  21. Richards, W. and Hoffman, D. D. 1984. Codon constraints on closed 2d shapes. AI memo 769, MIT AI lab.Google Scholar
  22. Terzopoulos, D. 1983. The role of constraints and discontinuities in visible surface reconstruction. Technical Report, MIT AI lab.Google Scholar
  23. Terzopoulos, D. 1984. Multiresolution computation of visible-surface representations. PhD, Dept. EE and CS, Massachusetts Institute of Technology.Google Scholar
  24. Terzopoulos, D. 1986. Regularization of inverse visual problems involving discontinuities. Pattern Analysis and Machine Intelligence, 8(4): 413–424.CrossRefGoogle Scholar
  25. Torre, V. and Poggio, T. 1984. On edge detection. AI Memo 768, MIT AI Laboratory.Google Scholar
  26. Witkin, A. P. 1983. Scale-space filtering. ICJAI 1983, 2.Google Scholar
  27. Zucker, S. W., David, C., Dobbins, A., and Iverson, L. 1988. The organization of curve detection: Coarse tangent fields and fine spline coverings. Proceedings of the 2nd ICCV, pages 568–577.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Gregory Dudek
    • 1
  • John Tsotsos
    • 1
  1. 1.Dept of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations