• DocumentCode
    276645
  • Title

    Interpreting line drawings with higher order neural networks

  • Author

    Salem, Gaby J. ; Young, Tzay Y.

  • Author_Institution
    IBM Corp., Boca Raton, FL, USA
  • Volume
    i
  • fYear
    1991
  • fDate
    8-14 Jul 1991
  • Firstpage
    713
  • Abstract
    A neural network solution to line labeling is presented. Line labeling constraints in trihedral scenes are designed into a Hopfield-type network. The labeling constraints require a higher-order of interaction than that of Hopfield and Tank´s (1985) quadratic energy model. The analog model is modified to include an additional layer of neurons. A brief introduction to the line labeling problem is provided. The design of the energy function and the updating equation is described. Experimental results are analyzed
  • Keywords
    computer vision; neural nets; Hopfield-type network; analog model; constraints; higher order neural networks; line drawing interpretation; line labeling; quadratic energy model; trihedral scenes; updating equation; Application software; Artificial intelligence; Artificial neural networks; Computer vision; Engineering drawings; Equations; Labeling; Layout; Neural networks; Neurons;
  • 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.1991.155268
  • Filename
    155268