A Multiscale Geometric Model of Human Vision

  • Bart M. Ter Haar Romeny
  • Luc Florack

Abstract

A crucial factor in human perception is that we are able to move around in the three-dimensional world we live in. This induces continuous changes in the structure of the visual world as it is projected onto the retina. Much attention has been paid to the analysis of the “pictorial mode” of perception, the analysis of the retinal images as such. Gibson4.1 was one of the pioneers in this field, studying the behavior and perception of aircraft pilots during landing manoeuvers. He coined the term “ecological optics” for the study of the natural inflow of information, in which the deformation of structure, due to relative movements of objects and observer (or his eyes), is studied.

Keywords

Receptive Field Gaussian Kernel Image Structure Scale Space Lateral Geniculate Nucleus 
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. 4.1
    Gibson J.J. The Perception of the Visual World. Boston: Houghton Mifflin; 1952.Google Scholar
  2. 4.2
    Kay D.C. Tensor Calculus (Schaum’s Outline Series). New York: McGraw-Hill; 1988.Google Scholar
  3. 4.3
    Gurevich B. Foundations of the Theory of Algebraic Invariants. Groningen: Noordhof; 1979.Google Scholar
  4. 4.4
    Anderson J.A., Rosenfeld E., eds. Neurocomputing: Foundations of Research. Cambridge: MIT; 1989.Google Scholar
  5. 4.5
    Spivak M. A Comprehensive Introduction to Differential Geometry (Vols. I-V). Berkeley: Publish or Perish; 1970.Google Scholar
  6. 4.6
    Young R.A. The Gaussian derivative theory of spatial vision: Analysis of cortical cell receptive field line-weighting profiles. In: General Motors Research Publication GMR-4920; 1985.Google Scholar
  7. 4.7
    Young R.A. The Gaussian derivative model for machine vision: Visual cortex simulation. J. Opt. Soc. Am. 1985; A2(13): 39, 102.Google Scholar
  8. 4.8
    Young R.A. Simulation of human retinal function with the Gaussian derivative model. Proc. IEEE Conf. Comput. Vision Patt. Recogn. 1986; 564–569.Google Scholar
  9. 4.9
    Kanatani K. Group-Theoretical Methods in Image Understanding (Springer Series in Information Sciences, Vol. 20 ). Berlin: Springer; 1990.Google Scholar
  10. 4.10
    Weyl H. The Classical Groups, their Invariants and Representations. Princeton: Princeton University Press; 1946.MATHGoogle Scholar
  11. 4.11
    Joins A.K. Fundamentals of Digital Image Processing. Englewood Cliffs: Prentice Hall; 1989.Google Scholar
  12. 4.12
    Höhne K.-H., Fuchs H., Pizer S.M., eds. 3D Imaging in Medicine (NATO ASI Series F60 ). Berlin: Springer; 1990.Google Scholar
  13. 4.13
    Lee D. Coping with discontinuities in computer vision: Their detection, classification, and measurement. Proc. IEEE Int. Conf. Comput. Vision (Cat. 88 CH 2664–1 ) 1988; 546–555.Google Scholar
  14. 4.14
    Witkin A.P. Scale space filtering. Proc. Int. Joint Conf. Artificial Intel!. (Karlsruhe) 1983; 1019–1021.Google Scholar
  15. 4.15
    Koenderink J.J. The structure of images. Biol. Cybern. 1984; 50: 363–370.MathSciNetMATHCrossRefGoogle Scholar
  16. 4.16
    Babaud J., Witkin A., Duda R. Uniqueness of the Gaussian kernel for scale space filtering. IEEE Trans. Patt. Anal. Mach. Intel!. 1986; PAMI-8: 26–33.CrossRefGoogle Scholar
  17. 4.17
    Korn A. Toward a symbolic representation of intensity changes in images. IEEE Trans. Patt. Anal. Mach. Intel!. 1988; PAMI-10: 610–625.CrossRefGoogle Scholar
  18. 4.18
    Koenderink J.J. Geometrical structures determined by the functional order in nervous nets. Biol. Cybern. 1984; 50: 43–50.MathSciNetMATHCrossRefGoogle Scholar
  19. 4.19
    Koenderink J.J., van Doom A.J. Representation of local geometry in the visual system. Biol. Cybern. 1987; 55: 367–375.MATHCrossRefGoogle Scholar
  20. 4.20
    Torre V., Poggio T.A. On edge detection. IEEE Trans. Patt. Anal. Mach. Intel!. 1986; PAMI-8: 147–163.CrossRefGoogle Scholar
  21. 4.21
    Poggio T., Torre V., Koch C. Computational vision and regularization. Nature 1985; 317: 314–319.CrossRefGoogle Scholar
  22. 4.22
    Koenderink J.J. Image structure. In: Viergever M.A., Todd-Pokropek A., eds. Mathematics and Computer Science in Medical Imaging (NATO ASI Series F39 ). Berlin: Springer; 1988: 67–104.Google Scholar
  23. 4.23
    Hubel D.H. Eye, Brain, and Vision (Scientific American Library Series 22 ). San Francisco: Freeman; 1988.Google Scholar
  24. 4.24
    Koenderink J.J. Simultaneous order in nervous nets from a functional standpoint. Biol. Cybern. 1984; 50: 35–41.MathSciNetMATHCrossRefGoogle Scholar
  25. 4.25
    Hubel D.H., Wiesel T.N. Brain mechanisms of vision. Sci. Am. 1979; 241 (3): 130–146.Google Scholar
  26. 4.26
    Koenderink J.J., van Doom A.J. Receptive field families. Biol. Cybern. 1990; 63: 291–298.MATHCrossRefGoogle Scholar
  27. 4.27
    Lipschutz M.M. Differential Geometry (Schaum’s Outline Series). New York: McGraw-Hill; 1969.Google Scholar
  28. 4.28
    Marr D., Hildrecht E.C. Theory of edge detection. Proc. R. Soc. London 1980; 200: 269–294.CrossRefGoogle Scholar
  29. 4.29
    Clark J.J. Authenticating edges produced by zero-crossing algorithms. IEEE Trans. Path. Anal. Mach. Intel!. 1989; PAMI-11: 43–57.CrossRefGoogle Scholar
  30. 4.30
    Lindeberg T. Scale space for discrete signals. IEEE Trans. Patt. Anal. Mach. Intel!. 1990; PAMI-12: 234–245.Google Scholar
  31. 4.31
    Canny J. A computational approach to edge detection. IEEE Trans. Patt. Anal. Mach. Intel!. 1987; PAMI-8: 679–698.CrossRefGoogle Scholar
  32. 4.32
    De Micheli E., Caprile B., Ottonello P., Torre V. Localization and noise in edge detection. IEEE Trans. Patt. Anal. Mach. Intel!. 1989; PAMI-10: 1106–1117.CrossRefGoogle Scholar
  33. 4.33
    Koenderink J.J., van Doom A.J. The structure of two-dimensional scalar fields with applications to vision. Biol. Cybern. 1979; 33: 151–158.MATHCrossRefGoogle Scholar
  34. 4.34
    Koenderink J.J., van Doom A.J. A description of the structure of visual images in terms of an ordered hierarchy of light and dark blobs. In: Jaffe S.C., ed. Proc. 2nd IEEE Int. Conf. Vis. Psychophys. Med. Imag. (Cat. 81 CH 1676–6 ) New York: IEEE; 1981: 173–176.Google Scholar
  35. 4.35
    Rangarajan R., Shah M., Van Brackle D. Optimal corner detector. Proc. IEEE Int. Conf. Comput. Vision (Cat. 88 CH 2664–1) 1988; 90–95.Google Scholar
  36. 4.36
    Noble J.A. Finding corners. Image Vis. Comput. 1988; 6: 121–128.CrossRefGoogle Scholar
  37. 4.37
    Koenderink J.J. Solid Shape. Cambridge: MIT; 1990.Google Scholar
  38. 4.38
    Lifshitz L.M., Pizer S.M. A multiresolution hierarchical approach to image segmentation based on intensity extrema. IEEE Trans. Patt. Anal. Mach. Intel!. 1990; PAMI-12: 529–541.CrossRefGoogle Scholar
  39. 4.39
    De Graaf C.N., Vincken K.L., Viergever M.A. et al. A hyperstack for the segmentation of 3D images. In: Orthendahl D.A., Llacer J., eds. Proceedings of the 11th International Conference on Image Processing in Medical Imaging. New York: Plenum; 1989: 115–122.Google Scholar
  40. 4.40
    Bergholm F. Edge focusing. IEEE Trans. Patt. Anal. Mach. Intel!. 1987; PAMI-9: 726–741.CrossRefGoogle Scholar
  41. 4.41
    Bovik A.C., Clark M., Geisler W.S. Multichannel texture analysis using localized spatial filters. IEEE Trans. Patt. Anal. Mach. Intel!. 1990; PAMI-12: 55–73.CrossRefGoogle Scholar
  42. 4.42
    Mallat S.G. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. Patt. Anal. Mach. Intel!. 1989; PAMI-11: 674–694.CrossRefGoogle Scholar
  43. 4.43
    Perona P., Malik J. Scale space and edge detection using anisotropic diffusion. IEEE Trans. Patt. Anal. Mach. Intel!. 1990; PAMI-12: 629–639.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1993

Authors and Affiliations

  • Bart M. Ter Haar Romeny
  • Luc Florack

There are no affiliations available

Personalised recommendations