Computational vision and regularization theory

Abstract

Descriptions of physical properties of visible surfaces, such as their distance and the presence of edges, must be recovered from the primary image data. Computational vision aims to understand how such descriptions can be obtained from inherently ambiguous and noisy data. A recent development in this field sees early vision as a set of ill-posed problems, which can be solved by the use of regularization methods. These lead to algorithms and parallel analog circuits that can solve ‘ill-posed problems’ and which are suggestive of neural equivalents in the brain.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

References

  1. 1

    Marr, D. Vision (Freeman, San Francisco, 1982).

    Google Scholar 

  2. 2

    Brady, J. M. Computing Surv. 14, 3–71 (1982).

    Article  Google Scholar 

  3. 3

    Ballard, D. H., Hinton, G. E. & Sejnowski, T. J. Nature 306, 21–26 (1983).

    CAS  Article  ADS  PubMed  PubMed Central  Google Scholar 

  4. 4

    Brown, C. M. Science 224, 1299–1305 (1984).

    CAS  Article  ADS  PubMed  PubMed Central  Google Scholar 

  5. 5

    Barrow, H. G. & Tennenbaum, J. M. Artif. Intell. 17, 75–117 (1981).

    Article  Google Scholar 

  6. 6

    Marr, D. & Ullman, S. Proc. R. Soc. B211, 151–180 (1981).

    CAS  ADS  Google Scholar 

  7. 7

    Poggio, T. & Koch, C. Proc. R. Soc. B (in the press).

  8. 8

    Poggio, T. & Torre, V. Artif. Intell. Lab. Memo No. 773 (MIT, Cambridge, 1984).

  9. 9

    Hadamard, J. Lectures on the Cauchy Problem in Linear Partial Differential Equations (Yale University Press, 1923).

    Google Scholar 

  10. 10

    Bertero, M., Del Mol, C. & Pike, E. R. J. inverse Prob. (in the press).

  11. 11

    Tikhonov, A. N. Sov. Math. Dokl. 4, 1035–1038 (1963).

    Google Scholar 

  12. 12

    Tikhonov, A. N. & Arsenin, V. Y. Solutions of Ill-posed Problems (Winston, Washington, DC, 1977).

    Google Scholar 

  13. 13

    Bertero, M. in Problem non ben posti ed inversi (Istituto di Analisi Globale, Firenze, 1982).

    Google Scholar 

  14. 14

    Nashed, M. Z. (ed.) Generalized Inverses and Applications (Academic, New York, 1976).

  15. 15

    Wahba, G. Tech. Rep. No. 595 (University of Wisconsin, 1980).

  16. 16

    Horn, B. K. P. Computer Graphics Image Processing 3, 111–299 (1974).

    Article  Google Scholar 

  17. 17

    Horn, B. K. P. Robot Vision (MIT Press & McGraw-Hill, Cambridge & New York, 1985).

    Google Scholar 

  18. 18

    Horn, B. K. P. & Schunck, B. G. Artif. Intell. 17, 185–203 (1981).

    Article  Google Scholar 

  19. 19

    Ikeuchi, K. & Horn, B. K. P. Artif. Intell. 17, 141–184 (1981).

    Article  Google Scholar 

  20. 20

    Grimson, W. E. L. From Images to Surfaces: A Computational Study of the Human Early Visual System (MIT, Cambridge, 1981).

    Google Scholar 

  21. 21

    Grimson, W. E. L. Phil. Trans. R. Soc. B298, 395–427 (1982).

    CAS  Article  Google Scholar 

  22. 22

    Terzopoulos, D. Computer Graphics Image Processing 24, 52–96 (1983).

    Article  Google Scholar 

  23. 23

    Hildreth, E. C. The Measurement of Visual Motion (MIT Press, Cambridge, 1984).

    Google Scholar 

  24. 24

    Hildreth, E. C. Proc. R. Soc. B221, 189–220 (1984).

    CAS  ADS  Google Scholar 

  25. 25

    Horn, B. K. P. & Brooks, M. J. Artif. Intell. Lab. Memo No. 813 (MIT, Cambridge, 1985).

  26. 26

    Poggio, T., Voorhees, H. & Yuille, A. Artif. Intell. Lab. Memo No. 833 (MIT, Cambridge, 1985).

  27. 27

    Torre, V. & Poggio, T. IEEE Trans. Pattern Analysis Machine Intelligence (in the press).

  28. 28

    Marr, D. & Poggio, T. Proc. R. Soc. B204, 301–328 (1979).

    CAS  ADS  Google Scholar 

  29. 29

    Marr, D. & Hildreth, E. C. Proc. R. Soc. B207, 187–217 (1980).

    CAS  ADS  Google Scholar 

  30. 30

    Morozov, V. A. Methods for Solving Incorrectly Posed Problems (Springer, New York, 1984).

    Google Scholar 

  31. 31

    Nishihara, H. K. Artif. Intell. Lab. Memo No. 780 (MIT, Cambridge, 1984).

  32. 32

    Hurlbert, A. Artif. Intell. Lab. Memo No. 814 (MIT, Cambridge, 1985).

  33. 33

    Land, E. H. Proc. natn. Acad. Sci. U.S.A. 80, 5163–5169 (1984).

    Article  ADS  Google Scholar 

  34. 34

    Yuille, A. Artif. Intell. Lab. Memo No. 724 (MIT, Cambridge, 1983); Advances in Artificial Intelligence (ed. O'Shea, T. M. M.) (Elsevier, Amsterdam, in the press).

    Google Scholar 

  35. 35

    Ullman, S. Computer Graphics Image Processing 9, 115–125 (1979).

    Article  Google Scholar 

  36. 36

    Eigen, M. in The Neurosciences: 3rd Study Program (eds Schmitt, F. O. & Worden, F. G.) xix–xxvii (MIT Press, Cambridge, 1974).

    Google Scholar 

  37. 37

    Oster, G. F., Perelson, A. & Katchalsky, A. Nature 234, 393–399 (1971).

    Article  ADS  Google Scholar 

  38. 38

    Hopfield, J. J. Proc. natn. Acad. Sci. U.S.A. 81, 3088–3092 (1984).

    CAS  Article  ADS  Google Scholar 

  39. 39

    Koch, C., Marroquin, J. & Yuille, A. Artif. Intell. Lab. Memo No. 751 (MIT, Cambridge, 1985).

  40. 40

    Schmitt, F. O., Dev, P. & Smith, B. H. Science 193, 114–120 (1976).

    CAS  Article  ADS  PubMed  PubMed Central  Google Scholar 

  41. 41

    Graubard, K. & Calvin, W. H. in The Neurosciences: 4th Study Program (eds Schmitt, F. O. & Worden, F. G.) 317–332 (MIT Press, Cambridge, 1979).

    Google Scholar 

  42. 42

    Shepherd, G. M. & Brayton, R. K. Brain Res. 175, 377–382 (1979).

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  43. 43

    Bennett, M. V. L. in Handbook of Physiology, 221–250 (American Physiological Society, Bethesda, 1977).

    Google Scholar 

  44. 44

    Marder, E. Trends Neurosci. 7, 48–53 (1984).

    Article  Google Scholar 

  45. 45

    Schmitt, F. D. Neuroscience 13, 991–1002 (1984).

    CAS  Article  ADS  PubMed  PubMed Central  Google Scholar 

  46. 46

    Koch, C., Poggio, T. & Torre, V. Phil. Trans. R. Soc. B298, 227–268 (1982).

    CAS  Article  Google Scholar 

  47. 47

    Cole, K. S. Membranes, Ions and Impulses (University of California Press, Berkeley, 1968).

    Google Scholar 

  48. 48

    Jack, J. J., Noble, D. & Tsien, R. W. Electric Current Flow in Excitable Cells (Clarendon, Oxford, 1975).

    Google Scholar 

  49. 49

    Koch, C. & Poggio, T. Proc. R. Soc. B218, 455–477 (1983).

    CAS  ADS  Google Scholar 

  50. 50

    Marroquin, J. Artif. Intell. Lab. Memo No. 792 (MIT, Cambridge, 1984).

  51. 51

    Geman, S. & Geman, D. IEEE Trans. Pattern Analysis Machine Intelligence 6, 721–741 (1984).

    CAS  Article  Google Scholar 

  52. 52

    Blake, A. Pattern Recognition Lett. 1, 393–399 (1983).

    Article  Google Scholar 

  53. 53

    Hinton, G. E. & Sejnowski, T. J. Proc. IEEE 1983 Conf. Computer Vision and Pattern Recognition (Washington, DC, 1983).

    Google Scholar 

  54. 54

    Kirkpatrick, S., Gelatt, C. D. Jr & Vecchi, M. P. Science 220, 671–680 (1983).

    MathSciNet  CAS  Article  ADS  Google Scholar 

  55. 55

    Metropolis, N., Rosenbluth, A., Rosenbluth, M., Teller, A. & Teller, E. J. chem. Phys. 21(6), 1087–1092 (1953).

    CAS  Article  ADS  Google Scholar 

  56. 56

    Marroquin, J. Artif. Intell. Lab. Memo No. 839 (MIT, Cambridge, 1985).

  57. 57

    Poggio, T. & Hurlbert, A. Artif. Intell. Lab. Working Pap. No. 264 (MIT, Cambridge, 1984).

  58. 58

    Kohonen, T. Self-Organization and Associative Memory (Springer, Berlin, 1984).

    Google Scholar 

  59. 59

    Terzopoulos, D. IEEE Trans. Pattern Analysis Machine Intelligence (in the press).

  60. 60

    Hillis, W. D. The Connection Machine (MIT Press, Cambridge, 1985).

    Google Scholar 

  61. 61

    Fahle, M. & Poggio, T. Proc. R. Soc. B213, 451–477 (1981).

    CAS  ADS  Google Scholar 

  62. 62

    Wallach, H. & O'Connell, D. N. J. exp. Psychol. 45, 205–217 (1953).

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  63. 63

    Movshon, J. A., Adelson, E. H., Gizzi, M. S. & Newsome, W. T. in Pattern Recognition Mechanisms (eds Chagas, C., Gattar, R. & Gross, C. G.) 95–107 (Vatican, Rome, 1984); Expl Brain Res. (in the press).

    Google Scholar 

  64. 64

    Barlow, H. B. J. Phsiol., Lond. 119, 69–88 (1953).

    CAS  Article  Google Scholar 

  65. 65

    Kuffler, S. W. J. Neurophysiol. 16, 37–68 (1953).

    CAS  Article  Google Scholar 

  66. 66

    Terzopoulos, D. thesis, Massachusetts Inst. Technol. (1948).

  67. 67

    Terzopoulos, D. Artif. Intell. Lab. Memo. No. 800 (MIT, Cambridge, 1985).

Download references

Author information

Affiliations

Authors

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Poggio, T., Torre, V. & Koch, C. Computational vision and regularization theory. Nature 317, 314–319 (1985). https://doi.org/10.1038/317314a0

Download citation

Further reading

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Search

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing