• DocumentCode
    2736527
  • Title

    Extraction of chained contour lines in images by a synchronous Boltzmann machine

  • Author

    Lacaille, Jérôme ; Azencott, Robert

  • Author_Institution
    Echole Normale Superieure, DIAM, Paris, France
  • fYear
    1991
  • fDate
    8-14 Jul 1991
  • Abstract
    Summary form only given, as follows. In gray-level images, local contour elements are strongly linked to the presence of high values (in norm) for the gradient of light intensity. But independent detection of high-contrast points does not in general extract smooth lines of chained contour elements, particularly in the presence of noise
  • Keywords
    computerised pattern recognition; computerised picture processing; neural nets; chained contour elements; chained contour lines; gray-level images; high-contrast points; light intensity; line detection; local contour elements; noise; smooth lines; synchronous Boltzmann machine; Hopfield neural networks; Image reconstruction; Neural networks; Productivity; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
  • Conference_Location
    Seattle, WA
  • Print_ISBN
    0-7803-0164-1
  • Type

    conf

  • DOI
    10.1109/IJCNN.1991.155534
  • Filename
    155534