• DocumentCode
    1518861
  • Title

    Hough transform network

  • Author

    Basak, J. ; Pal, S.K.

  • Author_Institution
    Machine Intelligence Unit, Indian Stat. Inst., Calcutta, India
  • Volume
    35
  • Issue
    7
  • fYear
    1999
  • fDate
    4/1/1999 12:00:00 AM
  • Firstpage
    577
  • Lastpage
    578
  • Abstract
    A two-layered Hough transform network is proposed which accepts image co-ordinates as the input and learns the parametric forms of the lines in the image adaptively. It provides an efficient representation of visual information embedded in the connection weights. It not only reduces the large space requirements, as in the case of the classical Hough transform, but also represents the parameters with high precision
  • Keywords
    Hough transforms; image representation; neural nets; connection weights; embedded visual information representation; image co-ordinates as the input; two-layered Hough transform network;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19990283
  • Filename
    769493