• DocumentCode
    2733638
  • Title

    Image restoration using Lagrange programming neural networks

  • Author

    Zhu, Xinen ; Zhang, Shaoting ; Constantinides, A.G.

  • Author_Institution
    Dept. of Electr. Eng., Imperial Coll., London
  • fYear
    1991
  • fDate
    8-14 Jul 1991
  • Abstract
    Summary form only given, as follows. An approach involving the use of Lagrange programming neural networks to restore degraded images is proposed. Three kinds of neurons take part in the restoration process: parameter neurons, variable neurons, and Lagrange neurons. The parameter neurons adapt to various input parameters, while the variable and Lagrange neurons construct a canonical computational circuit to fulfill fundamental solution-finding computation. Maximum entropy restoration is completed with ease by taking advantage of the features of robust stability and functional flexibility of the neural network. High-quality images were obtained in experiments
  • Keywords
    computerised picture processing; neural nets; Lagrange neurons; Lagrange programming neural networks; degraded images; functional flexibility; image restoration; input parameters; maximum entropy restoration; parameter neurons; robust stability; solution-finding computation; variable neurons; Circuits; Degradation; Educational institutions; Entropy; Image restoration; Lagrangian functions; Neural networks; Neurons; Robust stability;
  • 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.1991.155516
  • Filename
    155516