Equivalent contraction kernels to build dual irregular pyramids

  • Walter G. Kropatsch
Part of the Advances in Computing Science book series (ACS)


A raw digital image consists of a 2D spatial arragement of pixels each of which results from measuring the light at a specific location of the image plane. Currently most of the artificial sensors (e.g. CCD cameras) have the rigid structure of an orthogonal grid, whereas most natural vision systems are based on non-regular arrangements of sensors [1]. Although arrays are certainly easier to manage technically, topological relations seem to play an even more important role for vision tasks in natural systems than precise geometrical positions.


Span Tree Base Graph Span Forest Pyramid Level Region Adjacency Graph 
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. [1]
    Peter K. Ahnelt and Dietmar Pum. The foveal photoreceptors. a model for the comparison of physiologic and algorithmic image compressions. In Peter Mandl, editor, Modelling and New Methods in Image Processing and in Geographical Information Systems, OCG-Schriftenreihe, Osterr. Arbeitsgemeinschaft für Mustererkennung, pages 223–232. Oldenbourg, 1991. Band 61.Google Scholar
  2. [2]
    M. Bister, J. Cornelis, and Azriel Rosenfeld. A critical view of pyramid segmentation algorithms Pattern Recognition Letters, Vol. 11 (No. 9):pp. 605–617, September 1990.MATHCrossRefGoogle Scholar
  3. [3]
    P. J. Burt and E. H. Adelson. The Laplacian pyramid as a compact image code. IEEE Transactions on Communications, Vol. COM-31(No. 4 ):pp. 532–540, April 1983.Google Scholar
  4. [4]
    Jean-Michel Jolion and Annick Montanvert. The adaptive pyramid, a framework for 2D image analysis. Computer Vision, Graphics, and Image Processing: Image Understanding, 55 (3):pp. 339–348, May 1992.MATHCrossRefGoogle Scholar
  5. [5]
    Walter G. Kropatsch. Building Irregular Pyramids by Dual Graph Contraction. IEE-Proc. Vision, Image and Signal Processing, Vol. 142 (No. 6):pp. 366–374, December 1995.Google Scholar
  6. [6]
    Walter G. Kropatsch. Equivalent Contraction Kernels and The Do-main of Dual Irregular Pyramids. Technical Report PRIP-TR-42, In-stitute f. Automation 183/2, Dept. for Pattern Recognition and Image Processing, TU Wien, Austria, 1995. Also available through
  7. [7]
    Walter G. Kropatsch and Souheil BenYacoub. A revision of pyramid segmentation. In Walter G. Kropatsch, editor, 13th International Conference on Pattern Recognition, volume II, pages 477–481. IEEE Comp.Soc., 1996.Google Scholar
  8. [8]
    Herwig Macho and Walter G. Kropatsch. Finding Connected Components with Dual Irregular Pyramids. In Franc Solina and Walter G. Kropatsch, editors, Visual Modules, Proc. of 19th ÖAGM and 1st SDVR Workshop, pages 313–321. OCGSchriftenreihe, Osterr. Arbeitsgemeinschaft für Mustererkennung, R. Oldenburg, 1995. Band 81.Google Scholar
  9. [9]
    David Marr. Visual information processing: The structure and creation of visual representations. Philosophical Transactions of the Royal Society London, Ser. B(290):pp. 199–218, 1980.Google Scholar
  10. [10]
    Christophe Mathieu, Isabelle E. Magnin, and C. Baldy-Porcher. Optimal stochastic pyramid: segmentation of MRI data. Proc. Med. Imaging VI: Image Processing, SPIE Vol. 1652:pp. 14–22, Feb. 1992.CrossRefGoogle Scholar
  11. [11]
    Peter Meer. Stochastic image pyramids. Computer Vision, Graphics, and Image Processing, Vol. 45 (No. 3):pp. 269–294, March 1989.CrossRefGoogle Scholar
  12. [12]
    Theo Pavlidis. Structural Pattern Recognition. Springer, New York, 1977.Google Scholar

Copyright information

© Springer-Verlag/Wien 1997

Authors and Affiliations

  • Walter G. Kropatsch

There are no affiliations available

Personalised recommendations