Visual Algorithms

  • T. Poggio
Part of the Springer Series in Information Sciences book series (SSINF, volume 11)


One can distinguish (or at least I did so with David Marr:see Marr and Poggio, 1976; Marr, 1982) at least three levels at which a visual processor must be understood. At the top level is the computational theory of the device in which the problem to be solved is characterized, and the natural constraints are made explicit. At the bottom is the level of the detailed neuronal ”hardware” — neural circuits, synapses and so forth — that perform the computation. In the middle is a study of the algorithms used to compute the solution. This second level is the hardest to define precisely since it represents a bridge between the computational level and the hardware level. Thus, while the circuitry is determined by the available mechanisms and the computation by the nature of the problem, the algorithm itself is determined by the computation and by the available hardware.


Receptive Field Optical Flow Associative Memory Finite State Machine Polynomial 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. Barlow, H.B. Critical limiting factors in the design of the eye and visual cortex. Proc. R. Soc. Lond. B 212, 1 –34 (1981)ADSCrossRefGoogle Scholar
  2. Barlow, H.B., Levick, W.R. The mechanism of directionally selective units in rabbit’s retina. J. Physiol. 178, 477–504 (1965)Google Scholar
  3. Geiger, G., Poggio, T. The Orientation of Flies towards Visual Patterns: On the Search for the Underlying Functional Interactions. Biol. Cyber., 19, 39–54, (1975).CrossRefGoogle Scholar
  4. Grimson, W.E.L.: From images to surfaces. M.I.T. Press (1981)Google Scholar
  5. Koch, C., Poggio, T. and Torre, V., Retinal Ganglion Cells: A Functional Interpretation of Dendritic Morphology, Phil. Trans. R. Soc.B, 298, 227–264, (1982)ADSCrossRefGoogle Scholar
  6. Kohonen, T.: Associative memory. A system-theoretical approach. Berlin, Heidelberg, New York: Springer (1977)Google Scholar
  7. Kolmogorov, A.N.: On the representation of continuous functions of several variables by superpositions of continuous functions of one variable and addition (in russian). Dokl. Akad. Nauk SSSR 114, 679–681 (1957); Am. Math. Soc. Transl. 28, 55–59 (1963)MathSciNetGoogle Scholar
  8. Logan Jr., B. F. Information in the Zero-crossings of Bandpass Signals, The Bell System Technical Journal, Vol. 56, 487–510 (1977)MathSciNetADSMATHGoogle Scholar
  9. Marr, D.: Vision. W.H. Freeman, San Francisco (1982)Google Scholar
  10. Marr, D., Hildreth, E. 1980 Theory of Edge Detection Proc. Roy. Soc. Lond. B 207, 187–217 (1980)ADSCrossRefGoogle Scholar
  11. Marr, D. C ., Poggio, T. From Understanding Computation to Understanding Neural Circuitry. In: MECHANISMS IN VISUAL PERCEPTION, E. Poppel, R. Held and J. E. Dowling, eds. Neuro sciences Res. Prog. Bull., 15, No. 3, pp. 470-488, 1977 Also available as A. I. Memo 857, Massachusetts Institute of Technology Artificial Intelligence, May 1976.Google Scholar
  12. Marr, D., Poggio, T. A Theory of Human Stereo Vision. A. I. Memo 451, November 1977, Massachusetts Institute of Technology, Artificial Intelligence Laboratory. Also avalable in a shorter version as A Computational Theory of Human Stereo Vision. Proc. R. Soc. Lond. B, 204, 301–328, (1979.)ADSCrossRefGoogle Scholar
  13. Marr, D., Ullman, S.: Directional selectivity and its use in early visual processing. Proc. R. Soc. Lond. B 211, 151–180, (1981)ADSCrossRefGoogle Scholar
  14. Minsky, M., Papert, S.: Perceptrons. An introduction to computational geometry. Cambridge. Mass., London: MIT Press (1969)Google Scholar
  15. Nishihara, H.K.: Intensity, Visible-Surface, and Volumetric Representations. Artif. Intell. 17, 265–284 (1981)CrossRefGoogle Scholar
  16. Nishihara, H.K., Larson, N.G. Proc. DARPA image Understanding Workshop 114–120 Science Application Inc., Arlington, VA (1981)Google Scholar
  17. Palm, G.: On representation and approximation of nonlinear systems. Biol. Cybernetics 31, 119–124 (1978)MathSciNetMATHCrossRefGoogle Scholar
  18. Palm, G.: On representation and approximation of nonlinear systems. Part II. Biol. Cybernetics 34, 49–52 (1979)MathSciNetMATHCrossRefGoogle Scholar
  19. Palm, G., Poggio, T. The Volterra Representation and the Wiener Expansion: Validity and Pitfalls. SIAM J. Appl Math, 33, 195–216, (1977)MathSciNetMATHGoogle Scholar
  20. Palm, G., Poggio, T. Stochastic Identification Methods for Nonlinear Systems: An Extension of the Wiener Theory. SIAM J. Appl. Math., 34, 524–534, (1978)MathSciNetMATHCrossRefGoogle Scholar
  21. Poggio, T. On Optimal Nonlinear Associative Recall. Biol. Cyber., 19, 201–209, (1975a)MathSciNetMATHCrossRefGoogle Scholar
  22. Poggio, T. On Optimal Discrete Estimation. PROCEEDINGS OF THE FIRST SYMPOSIUM ON TESTING AND IDENTIFICATION OF NONLINEAR SYSTEMS, March 17–20, 1975, California Institute of Technology, Pasadena, California. G. I). McCann and P. Z. Marmarelis, eds., pp. 30–37 (1975b)Google Scholar
  23. Poggio, T., Marr’s Computational Approach to Vision, Trends in NeuroSciences — October, Vol. 4, No. 10, pp. 258–262, (1981)CrossRefGoogle Scholar
  24. Poggio, T., Trigger Features or Fourier Analysis in Early Vision: A New Point of View, In: The Recognition of Pattern and Form, ed. D. Albrecht, Springer, (1982)Google Scholar
  25. Poggio, T. and Koch, C. Nonlinear Interactions in a Dendritic Tree: Localization, Timing and Role in Information Processing, A. I. Memo No.657, September 1981, Massachusetts Institute of Technology Artificial Intelligence Laboratory (1981)Google Scholar
  26. Poggio, T., Koch, C. and Torre, V., Microelectronics in Nerve Cells: Dendritic Morphology and Information Processing, A. I. Memo No.650, October 1981, Massachusetts Institute of Technology Artificial Intelligence Laboratory (1981b)Google Scholar
  27. Poggio, T., Nishihara, H.K. and Nielsen, K.R.K. Zero-crossings and Spatiotemporal Interpolation in Vision: Aliasing and electrical coupling between sensors, A.I. Memo No. 675, May 1982, Massachusetts Institute of Technology Artificial Intelligence Laboratory (1982)Google Scholar
  28. Poggio, T., Reichardt, W. Visual Control of Orientation Behaviour in the Fly. Part II. Towards the Underlying Neural Interactions. Quart. Rev. Biophys., 9, 3, 377–438, (1976)CrossRefGoogle Scholar
  29. Poggio, T., Reichardt, W. On the Representation of Multi-Input Systems: Computational Properties of Polynomial Algorithms. Biol Cyber., 37, 167–186, (1980)MathSciNetMATHCrossRefGoogle Scholar
  30. Poggio, T., Reichardt, W. Characterization of Nonlinear Interactions in the Fly’s Visual System, pp. 64–84, Appendix 4: A Polynomial Representation of Algorithms, pp. 197–202. In: THEORETICAL APPROACHES IN NEUROBIOLOGY, W. Reichardt and T. Poggio, eds., MIT Press, Cambridge, Mass., (1981)Google Scholar
  31. Poggio, T., Reichardt, W., Hausen, K. A Neuronal Circuitry for Relative Movement Discrimination by the Visual System of the Fly. Naturwissenschaften, 68, 443–466, (1981a)ADSCrossRefGoogle Scholar
  32. Poggio, T. and Rosser, B., The Computational Problem of Motor Control, In: Machine Intelligence 10, eds Hayes, Michie, Pao (1982)Google Scholar
  33. Poggio, T., Torre, V. A new approach to synaptic interaction. In: Lecture Notes in Biomathematics 21. Theoretical Approaches to Complex Systems, Proceedings, Tubingen, June 11–12, 1977. Eds. R. Heim and G. Palm Springer-Verlag, Berlin Heidelberg New York, pp. 89–115 (1977)Google Scholar
  34. Poggio, T., Torre, V. A theory of synaptic interactions. In: Theoretical approaches in neurobiology. Eds. W.Reichardt and T.Poggio. M.I.T. Press (1981)Google Scholar
  35. Reichardt, W., Poggio, T. Figure-Ground Discrimination by Relative Movement in the Visual System of the Fly. Part 1: Experimental Results. Biol. Cyber., 35, 81–100, (1979)CrossRefGoogle Scholar
  36. Resnikoff, H.L., On the Psychophysical function, J. Math Biol. 2, 295–276, (1975)MathSciNetCrossRefGoogle Scholar
  37. Torre, V., Poggio, T. A Synaptic Mechanism Possibly Underlying Directional Selectivity to Motion. Proc. R. Soc. Lond. B, 202, 409–216, (1978)ADSCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1983

Authors and Affiliations

  • T. Poggio
    • 1
  1. 1.Artificial Intelligence Laboratory and Department of PsychologyM.I.T.CambridgeUSA

Personalised recommendations