• DocumentCode
    396857
  • Title

    Kullback-Leibler divergence and Markov random fields for speckled image restoration

  • Author

    Bratsolis, Emnianuel ; Sigelle, Marc

  • Author_Institution
    Dept. Traitement du Signal et des Images, Ecole Nat. Superieure des Telecommun., Paris, France
  • Volume
    1
  • fYear
    2003
  • fDate
    1-4 July 2003
  • Firstpage
    425
  • Abstract
    In this paper we describe an approximation of speckled image observation (attachment to data) laws by generalized Gaussian pdfs. We use Kullback-Leibler (KL) divergence (entropy) for this purpose. This leads to a mathematical model which can be useful for speckled image restoration and for related hyperparameter estimation.
  • Keywords
    Markov processes; entropy; image restoration; parameter estimation; Kullback-Leibler divergence; Markov random field; entropy; generalized Gaussian pdf; hyperparameter estimation; image observation; speckled image restoration; Bismuth; Context modeling; Entropy; Equations; Image restoration; Markov random fields; Mathematical model; Speckle; Stochastic processes;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Its Applications, 2003. Proceedings. Seventh International Symposium on
  • Print_ISBN
    0-7803-7946-2
  • Type

    conf

  • DOI
    10.1109/ISSPA.2003.1224731
  • Filename
    1224731