Advertisement

Towards a Primal Sketch of Real World Scenes in Early Vision

  • Axel F. Korn
Conference paper
Part of the Springer Study Edition book series (volume 41)

Abstract

The problem of symbolic representation of intensity variations in gray-value pictures of real scenes is studied. The goal is to relate the responses of a filter bank of different gradient filters to the structure of the picture which is determined by the physics of the image generation process. A simple criterion is proposed for the selection of a suitable center frequency of the involved band-pass filters. The gradient vectors of the image function give the direction of maximal intensity changes with high resolution (8 bit) which can be used for an invariant shape description by corner points of a contour. The picture is segmented by closed contour lines into regions which form a topographic representation in the picture domain.

Keywords

Edge Detection Filter Bank Corner Point Contour Point Real World Scene 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Marr, D.: Vision. W.H. Freeman and Comp., San Francisco, CA, 1982Google Scholar
  2. 2.
    Korn, A.: Combination of Different Spatial Frequency Filters for Modeling Edges and Surfaces in Gray-Value Pictures. Proc.2nd Int. Technical Symposium on Optical and Electro-Optical Applied Science and Engineering, Cannes, Dec. 2–6, 1985, SPIE, Vol. 595, 22–30Google Scholar
  3. 3.
    Nagel, H.-H.: Principles of (Low-Level) Computer Vision. In “Fundamentals in Computer Understanding: Speech, Vision, and Natural Language”, J.P. Haton (Ed.), Cambridge University Press, Cambridge/UK 113–139 (1987)Google Scholar
  4. 4.
    Canny, J.F.: Finding Edges and Lines in Images. Artif. Intell. Lab., Mass. Inst. Technol., Cambridge, MA, Tech. Rep. AI-TR-720, June 1983.Google Scholar
  5. 5.
    Koenderink, J.J. and Doorn, A.J. van: Invariant features of contrast detection: an explanation in terms of self-similar detector arrays. J. Opt. Am. 72, 83–87 (1984)CrossRefGoogle Scholar
  6. 6.
    Wilson, H.R. and Bergen, J.R.: A four channel model for threshold spatial vision. Vision Research, 19, 19–32 (1979)CrossRefGoogle Scholar
  7. 7.
    Campbell, F.W. and Robson, J.G.: Applications of Fourier analysis to the visibility of gratings, J. Physiol. (London) 197, 551–566 (1968)Google Scholar
  8. 8.
    Frisby, J. P., Seeing, Illusion, Brain and Mind. Oxford University Press, Oxford, 1979Google Scholar
  9. 9.
    Torre, v., and Poggio T.A., On Edge Detection. IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-8 (1986) 147–163Google Scholar
  10. 10.
    Asada, H., and Brady, M.: The curvature primal sketch. IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-8, 2–14 (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1989

Authors and Affiliations

  • Axel F. Korn
    • 1
  1. 1.Fraunhofer-Institut für Informations- und Datenverarbeitung (IITB)Karlsruhe 1W. Germany

Personalised recommendations