• DocumentCode
    2585531
  • Title

    Towards a computational theory of model based vision and perception

  • Author

    Shvaytser, Haim

  • Author_Institution
    David Sarnoff Res. Center, Princeton, NJ, USA
  • fYear
    1990
  • fDate
    4-7 Dec 1990
  • Firstpage
    283
  • Lastpage
    286
  • Abstract
    When given partial data, a model based approach requires that pictures consistent with the model are chosen as plausible interpretations of the data. The author presents a computational theory that relates degrees of freedom in such models to the number of pixels that carry useful information. It is shown that in models with a finite number of degrees of freedom it is always possible to find a consistent interpretation from a finite number of pixels
  • Keywords
    computer vision; computerised pattern recognition; computerised picture processing; computational theory; degrees of freedom; model based vision; partial data; perception; pictures; pixels; plausible interpretations; Cleaning; Computational modeling; Computer vision; Filtering; Layout; Noise level; Psychology; Visual perception;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision, 1990. Proceedings, Third International Conference on
  • Conference_Location
    Osaka
  • Print_ISBN
    0-8186-2057-9
  • Type

    conf

  • DOI
    10.1109/ICCV.1990.139531
  • Filename
    139531