Institute of Informatics>>> Department of Image Processing and Computer Graphics>>>

Magyarul

Selected Publications of the Department of Image Processing and Computer Graphics of the year 1996

Articles in journal or book chapters

1. Mark Berthod, Zoltan Kato, Shan Yu, and Josiane Zerubia. Bayesian Image Classification Using Markov Random Fields. Image and Vision Computing, 14:285-295, 1996. [PDF] Keyword(s): Bayesian image classification, Markov random fields, Optimisation.
   Abstract: In this paper, we present three optimisation techniques, Deterministic Pseudo-Annealing (DPA), Game Strategy Approach (GSA), and Modified Metropolis Dynamics (MMD), in order to carry out image classification using a Markov random field model. For the first approach (DPA), the a posteriori probability of a tentative labelling is generalised to a continuous labelling. The merit function thus defined has the same maxima under constraints yielding probability vectors. Changing these constraints convexities the merit function. The algorithm solves this unambiguous maximisation problem, and then tracks down the solution while the original constraints are restored yielding a good, even if suboptimal, solution to the original labelling assignment problem. In the second method (GSA), the maximisation problem of the a posteriori probability of the labelling is solved by an optimisation algorithm based on game theory. A non-cooperative n-person game with pure strategies is designed such that the set of Nash equilibrium points of the game is identical to the set of local maxima of the a posteriori probability of the labelling. The algorithm converges to a Nash equilibrium. The third method (MMD) is a modified version of the Metropolis algorithm: at each iteration the new state is chosen randomly, but the decision to accept it is purely deterministic. This is also a suboptimal technique but it is much faster than stochastic relaxation. These three methods have been implemented on a Connection Machine CM2. Experimental results are compared to those obtained by the Metropolis algorithm, the Gibbs sampler and ICM (Iterated Conditional Mode).
   @ARTICLE{Berthod-etal96,
   AUTHOR = {Mark Berthod and Zoltan Kato and Shan Yu and Josiane Zerubia},
   JOURNAL = {Image and Vision Computing},
   TITLE = {Bayesian Image Classification Using Markov Random Fields},
   YEAR = {1996},
   PAGES = {285--295},
   VOLUME = {14},
   KEYWORDS = {Bayesian image classification, Markov random fields, Optimisation},
   }
   


2. Zoltan Kato, Mark Berthod, and Josiane Zerubia. A Hierarchical Markov Random Field Model and Multi-Temperature Annealing for Parallel Image Classification. Computer Vision, Graphics and Image Processing: Graphical Models and Image Processing, 58(1):18-37, January 1996. [PDF] [PS]
   Abstract: In this paper, we are interested in massively parallel multiscale relaxation algorithms applied to image classification. It is well known that multigrid methods can improve significantly the convergence rate and the quality of the final results of iterative relaxation techniques. First, we present a classical multiscale model which consists of a label pyramid and a whole observation field. The potential functions of coarser grids are derived by simple computations. The optimization problem is first solved at the higher scale by a parallel relaxation algorithm, then the next lower scale is initialized by a projection of the result. Second, we propose a hierarchical Markov Random Field model based on this classical model. We introduce new interactions between neighbor levels in the pyramid. It can also be seen as a way to incorporate cliques with far apart sites for a reasonable price. This model results in a relaxation algorithm with a new annealing scheme: The Multi-Temperature Annealing (MTA) scheme, which consists of associating higher temperatures to higher levels, in order to be less sensitive to local minima at coarser grids. The convergence to the global optimum is proved by a generalisation of the annealing theorem of Geman and Geman.
   @ARTICLE{Kato-etal96,
   AUTHOR = {Zoltan Kato and Mark Berthod and Josiane Zerubia},
   JOURNAL = {Computer Vision, Graphics and Image Processing: Graphical Models and Image Processing},
   TITLE = {A Hierarchical Markov Random Field Model and Multi-Temperature Annealing for Parallel Image Classification},
   YEAR = {1996},
   MONTH = {January},
   NUMBER = {1},
   PAGES = {18--37},
   VOLUME = {58},
   PS = {../papers/cvgip.ps},
   }
   

Conference articles

1. Tamas Sziranyi, Josiane Zerubia, David Geldreich, and Zoltan Kato. Cellular Neural Network in Markov Random Field Image Segmentation. In Proceedings of the International Workshop on Cellular Neural Networks and their Applications, Seville, Spain, pages 139-144, June 1996. IEEE.
   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.
   @INPROCEEDINGS{Sziranyi-etal96,
   AUTHOR = {Tamas Sziranyi and Josiane Zerubia and David Geldreich and Zoltan Kato},
   BOOKTITLE = {Proceedings of the International Workshop on Cellular Neural Networks and their Applications},
   TITLE = {Cellular Neural Network in Markov Random Field Image Segmentation},
   YEAR = {1996},
   ADDRESS = {Seville, Spain},
   MONTH = {June},
   ORGANIZATION = {IEEE},
   PAGES = {139--144},
   }
   

  This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

 This document was translated from BibTEX by bibtex2html