@string{cnna="Proceedings of International Workshop on Cellular Neural Networks and their Applications"}
@InProceedings{Sziranyi-etal96,
  author =	 {Sziranyi, Tamas and Zerubia, Josiane and Geldreich,
                  David and Kato, Zoltan},
  title =	 {Cellular Neural Network in {M}arkov Random Field
                  Image Segmentation},
  booktitle =	 cnna,
  pages =	 {139--144},
  year =	 1996,
  month =        jun,
  organization = {IEEE},
  address =	 {Seville, Spain},
  abstract =	 {Statistical approaches to early vision processes
                  need a huge amount of computing power. These
                  algorithms can usually be implemented on parallel
                  computing structures. CNN is a fast parallel
                  processor array for image processing. However, CNN
                  is basically a deterministic analog circuit. We use
                  the CNN-UM architecture for statistical image
                  segmentation. With a single random in-put signal, we
                  were able to implement a (pseudo) random field
                  generator using one layer (one memory/cell) of the
                  CNN. The whole algorithm needs 8 memories/cell. We
                  can introduce this pseudo-stochastic segmentation
                  process in the CNN structure. Considering the simple
                  structure of the analog VLSI design, we use simple
                  arithmetic functions (addition, multiplication) and
                  very simple nonlinear output functions (step,
                  jigsaw). With this architecture, a real VLSI CNN
                  chip can execute a pseudo-stochastic relaxation
                  algorithm of about 100 iterations in about 1
                  msec. In the Markov random field (MRF) theory, one
                  important problem is parameter estimation. The
                  random segmentation process must be preceded by the
                  estimation of the gray-level distribution of the
                  different classes on small image segments. This
                  process is basically supervised. Usually the
                  histograms of noisy images can be modelled as simple
                  Gaussian distributions. This approach cannot be held
                  in a CNN structure, since there should be as many
                  additional layers as the number of classes. We
                  should follow another way. We have developed a
                  pixel-level distribution model.}
}