International Journal of Computer Vision

, Volume 1, Issue 4, pp 303–320 | Cite as

A ‘complexity level’ analysis of immediate vision

  • John K. Tsotsos


This paper demonstrates how serious consideration of the deep complexity issues inherent in the design of a visual system can constrain the development of a theory of vision. We first show how the seemingly intractable problem of visual perception can be converted into a much simpler problem by the application of several physical and biological constraints. For this transformation, two guiding principles are used that are claimed to be critical in the development of any theory of perception. The first is that analysis at the ‘complexity level’ is necessary to ensure that the basic space and performance constraints observed in human vision are satisfied by a proposed system architecture. Second, the ‘maximum power/minimum cost principle’ ranks the many architectures that satisfy the complexity level and allows the choice of the best one. The best architecture chosen using this principle is completely compatible with the known architecture of the human visual system, and in addition, leads to several predictions. The analysis provides an argument for the computational necessity of attentive visual processes by exposing the computational limits of bottom-up early vision schemes. Further, this argues strongly for the validity of the computational approach to modeling the human visual system. Finally, a new explanation for the pop-out phenomenon so readily observed in visual search experiments, is proposed.


Visual Search Visual Perception Visual Process Basic Space Human Visual System 
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. Ballard, D. [1986]. “Cortical connections and parallel processing: Structure and function”, Behavioral and Brain Sciences, vol. 9(1), pp. 67–90.Google Scholar
  2. Ballard, D., Hinton, G., and Sejnowski, T. [1983]. “Parallel visual computation”, Nature, vol. 306(5938), pp. 21–26.Google Scholar
  3. Barrow, H., and Tenenbaum, J.M. [1978]. “Recovering intrinsic scene characteristics from images”. In Computer Vision Systems, A., Hanson and E., Riseman (eds.). Academic Press: New York, pp. 3–26.Google Scholar
  4. Corbeil, J.-C. [1986]. The Stoddart Visual Dictionary. Stoddart Publishing: Toronto.Google Scholar
  5. Cowey, A., [1979]. “Cortical maps and visual perception”, Quart. J. Exper. Psychology, vol. 31, pp. 1–17.Google Scholar
  6. Daniel, P., and Whitteridge, D. [1961]. “The representation of the visual field on the cerebral cortex in monkeys”, Journal of Physiology, vol. 159, pp. 203–221.Google Scholar
  7. Feldman, J. (special issue editor), [1985]. “Connectionist models and their applications”, Cognitive Science, vol. 9(1), pp. 1–169.Google Scholar
  8. Feldman, J., and Ballard, D. [1982]. “Connectionist models and their properties”, Cognitive Science, vol. 6, pp. 205–254.Google Scholar
  9. Hinton, G. [1981]. “Shape representation in parallel systems”, Proc. Seventh Int. Joint Conf. Artif. Intel., vancouver. pp. 1088–1096.Google Scholar
  10. Hubel, D., and Wiesel, T. [1977]. “Functional architecture of macaque visual cortex”, Proc. Roy. Soc. (London), vol. B-198, pp. 1–59.Google Scholar
  11. Kirousis, L., and Papadimitriou, C. [1985]. “The complexity of recognizing polyhedral scenes”, 26th Annual Symposium on Foundations of Computer Science, Portland, Ore.Google Scholar
  12. Mackworth, A., and Freuder, E. [1985]. “The complexity of some polynomial network consistency algorithms for constraint satisfaction problems”, Artificial Intelligence, vol. 25, pp. 65–74.Google Scholar
  13. Marr, D. [1982]. Vision, W.H. Freeman: San Francisco.Google Scholar
  14. Moran, J., and Desimone, R. [1985]. “Selective attention gates visual processing in the extrastriate cortex”, Science, vol. 229, pp. 782–784.Google Scholar
  15. Nakayama, K., and Silverman, G. [1986]. “Serial and parallel processing of visual feature conjunctions”, Nature, vol. 320(6059), pp. 264–265.Google Scholar
  16. Neisser, U. [1967]. Cognitive Psychology. Appleton-Century-Crofts: New York.Google Scholar
  17. Poggio, T. [1982]. “Visual algorithms”, MIT AI Memo 683, Cambridge, Mass., May.Google Scholar
  18. Richards, W. [1982]. “How to play twenty questions with nature and win”, MIT AI Memo 660, Cambridge, Mass.Google Scholar
  19. Rumelhart, D., and McClelland, J. [1986a]. “PDP models and general issues in cognitive science”. In Parallel Distributed Processing, D., Rumelhart and J., McClelland (eds.). MIT Press: Cambridge, Mass., pp. 110–146.Google Scholar
  20. Rumelhart, D., McClelland, J. (eds.) [1986b]. Parallel Distributed Processing. MIT Press: Cambridge, Mass.Google Scholar
  21. Stensaas, S., Eddington, D., and Dobelle, W. [1974]. “The topography and variability of the primary visual cortex in man”, Journal of Neurosurgery, vol. 40, pp. 747–755.Google Scholar
  22. Treisman, A. [1985]. “Preattentive processing in vision”, Computer Vision, Graphics and Image Processing, vol. 31, pp. 156–177.Google Scholar
  23. Tsotsos, J. [1980]. A Framework For Visual Motion Understanding, PhD thesis; also, CSRI-TR-114, Dept. of Computer Science, Univ. of Toronto.Google Scholar
  24. Tsotsos, J. [1985]. “Knowledge organzation and its role in the interpretation of time-varying data: The Alven system”, Computational Intelligence, vol. 1(1), pp. 16–32.Google Scholar
  25. Tsotsos, J. [1986]. “Connectionist computing and neural machinery: examining the test of ‘timing”, Behavioral and Brain Sciences, vol. 9(1), pp. 106–107 (commentary on [Ballard 1986]).Google Scholar
  26. Tsotsos, J. [1987a]. “Representational axes and temporal cooperative processes”. In Vision, Brain and Cooperative Computation, M., Arbib and A., Hansen (Eds.). MIT Press/Bradford Books: Cambridge, Mass., pp. 361–418.Google Scholar
  27. Tsotsos, J. [1987b]. “Image understanding”. In The Encyclopedia of Artificial Intelligence, S., Shapiro (Ed.). John Wiley & Sons: New York, pp. 389–409.Google Scholar
  28. Ullman, S. [1983]. “Visual routines”, MIT AI Memo 723, Cambridge, Mass.Google Scholar
  29. Uhr, L. [1972]. “Layered ‘recognition cone’ networks that preprocess, classify and describe”, Ieee Trans. on Computers, pp. 758–768.Google Scholar
  30. van Essen, D., and Maunsell, J. [1983]. “Hierarchical organization and functional streams in the visual cortex”, Trends in Neuroscience, September, pp. 370–375.Google Scholar
  31. van, Essen, D., and Zeki, S. [1978]. “The topographic organization of rhesus monkey prestriate cortex”, Journal of Physiology, vol. 277, pp. 193–226.Google Scholar
  32. Zucker, S. [1985]. “Does connectionism suffice?” Behavioral and Brain Sciences, vol. 8(2), pp. 301–302 (commentary on [Feldman 1985a]).Google Scholar

Copyright information

© Kluwer Academic Publishers 1987

Authors and Affiliations

  • John K. Tsotsos
    • 1
  1. 1.Department of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations