The role of key-points in finding contours

  • O. Henricsson
  • F. Heitger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)


This paper describes a method for aggregating local edge evidences into coherent pieces of contour. An independent representation of corner and junction features provides suitable stop-conditions for the aggregation process and allows to divide contours into meaningful substrings, right from the beginning. The active role of corner and junction points makes the Contours converge onto them and greatly reduces the problems associated with purely edge-based methods. A second stage is concerned with completing established contours across regions that are less well-defined by contrast. The algorithm suggested uses the attributes of established structures (e.g. direction of termination) as well as local orientation and edge evidences to constrain possible completions in a rigorous way.


edge detection key-point detection edge linking contour completion 


  1. 1.
    E. H. Adelson and J. R. Bergen. Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A, 2(2):pp. 284–299, 1985.Google Scholar
  2. 2.
    H. Asada and M. Brady. The Curvature Primal Sketch. IEEE Trans. Pattern Anal. Machine Intell, PAMI-8(1):pp. 2–14, 1986.Google Scholar
  3. 3.
    J. F. Canny. A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Machine Intell, PAMI-8(6):pp. 679–698, 1986.Google Scholar
  4. 4.
    W. T. Freeman. Steerable filters and local analysis of image structure. PhD thesis, MIT, Media Laboratory, Cambridge MA, 1992.Google Scholar
  5. 5.
    G. H. Granlund. In Search of a General Picture Processing Operator. Computer Graphics and Image Processing, 8:pp. 155–173, 1978.Google Scholar
  6. 6.
    G. Guy and G. Medioni. Perceptual Grouping Using Global Saliency-Enhancing Operators. In ICPR'92, pages 99–103, 1992.Google Scholar
  7. 7.
    F. Heitger, G. Gerig, L. Rosenthaler, and O. Kübler. Extraction of boundary keypoints and completion of simple figures. In SCIA '89, pages 1090–1097, 1989.Google Scholar
  8. 8.
    F. Heitger, L. Rosenthaler, R. von der Heydt, E. Peterhans, and O. Kübler. Simulation of neural contour mechanisms: From simple to end-stopped cells. Vision Research, 32:pp. 963–981, 1992.Google Scholar
  9. 9.
    F. Heitger and R. von der Heydt. A Computational Model of Neural Contour Processing: Figure-Ground Segregation and Illusory Contours. In ICCV'93, pages 32–40, Berlin, Germany, 1993.Google Scholar
  10. 10.
    H. Knutsson and G. Granlund. Texture analysis using two-dimensional quadrature filters. In IEEE Computer Society Workshop on Computer Architecture for Pattern Analysis and Image Database Management, pages 206–213, 1983.Google Scholar
  11. 11.
    D. G. Lowe. Perceptual organization and visual recognition. Kluwer Academic Publishers, Boston, MA, 1985.Google Scholar
  12. 12.
    J. Matas and J. Kittler. Junction detection using probabilistic relaxation. Image and Vision Computing, 11(4):pp. 197–202, 1993.Google Scholar
  13. 13.
    G. Medioni and Y. Yasumoto. Corner Detection and Curve Representation Using Cubic B-Splines. Comput. Vision, Graphics and Image Process., 39:pp. 267–278, 1987.Google Scholar
  14. 14.
    R. Mohan and R. Nevatia. Perceptual Organization for Scene Segmentation and Dsecription. IEEE Trans. Pattern Anal. Machine Intell., PAMI-14(6):pp. 616–635, 1992.Google Scholar
  15. 15.
    M. C. Morrone and D. C. Burr. Feature detection in human vision: a phasedependent energy model. Proc. R. Soc. Lond., B 235:pp. 221–245, 1988.Google Scholar
  16. 16.
    M. C. Morrone and R. A. Owens. Feature detection from local energy. Pattern Recognition Letters, 6:pp. 303–313, 1987.Google Scholar
  17. 17.
    P. Perona and J. Malik. Detecting and localizing edges composed of steps, peaks and roofs. Technical Report UCB/CSD 90/590, Computer Science Division, University of California at Berkley, 1990.Google Scholar
  18. 18.
    L. Rosenthaler, F. Heitger, O. Kübler, and R. von der Heydt. Detection of General Edges and Keypoints. In G. Sandini, editor, Lecture Notes in Computer Science, pages 78–86. Springer Verlag, Berlin, 1992.Google Scholar
  19. 19.
    A. Sha'ashua and S. Ullman. Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network. In ICCV'88, pages 321–327, 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • O. Henricsson
    • 1
  • F. Heitger
    • 1
  1. 1.Communication Technology LaboratorySwiss Federal Institute of Technology ETHZürichSwitzerland

Personalised recommendations