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 1993

Articles in journal or book chapters

1. Zoltan Kato, Josiane Zerubia, and Mark Berthod. Bayesian Image Classification Using Markov Random Fields. In Ali Mohammad-Djafari and Guy Demoment, editors, Maximum Entropy and Bayesian Methods, pages 375-382. Kluwer Academic Publisher, 1993.
   Abstract: In this paper, we present two relaxation techniques: Deterministic Pseudo-Annealing (DPA) and Modified Metropolis Dynamics (MMD) in order to do image classification using a Markov Random Field modelization. For the first algorithm (DPA), the a posteriori probability of a tentative labeling is generalized to continuous labeling. The merit function thus defined has the same maxima under constraints yielding probability vectors. Changing these constraints convexify the merit function. The algorithm solve this unambigous maximization problem and then tracks down the solution while the original constraints are restored yielding a good even if suboptimal solution to the original labeling assignment problem. As for the second method (MMD), it 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 of course also a suboptimal technique which gives faster results than stochastic relaxation. These two methods have been implemented on a Connection Machine CM2 and simulation results are shown with a SPOT image and two synthetic noisy images. These results are compared to those obtained with the Metropolis algorithm, the Gibbs sampler and ICM (Iterated Conditional Mode).
   @INCOLLECTION{Kato-etal93,
   AUTHOR = {Zoltan Kato and Josiane Zerubia and Mark Berthod},
   BOOKTITLE = {Maximum Entropy and Bayesian Methods},
   PUBLISHER = {Kluwer Academic Publisher},
   TITLE = {Bayesian Image Classification Using Markov Random Fields},
   YEAR = {1993},
   EDITOR = {Ali Mohammad-Djafari and Guy Demoment},
   PAGES = {375--382},
   }
   


2. Attila Kuba and A. Volcic. The structure of the class of non-uniquely reconstructible sets. Acta Scientiarum Mathematicarum, 58(1-4):359-384, 1993. [WWW]
   Abstract: Consider the class of all measurable plane sets having given horizontal and vertical projections. According to this class the plane can be divided into three subsets: the essentially common subset of all elements of the class, the essentially common subset of the complements of all elements of the class, and the remaining subset of the plane. The three sets together are called the structure of the class. In this paper a method is given by which the structure of an arbitrary class can be determined from the projections. The method is similar to the procedure applied in the case of binary matrices. First, the structure of the normalized class (having rearranged non-increasing projections from the original ones) is constructed. Then, by a measure preserving mapping the structure of the original class is derived from the structure of the normalized class. The structure can be used in the reconstruction of non-unique sets from their projections, e.g. it gives information about the shape and the position of the possible solutions and an upper bound of the measure of the difference between two solutions.
   @ARTICLE{KubaVolcic199358,
   AUTHOR = {Attila Kuba and A. Volcic},
   JOURNAL = {Acta Scientiarum Mathematicarum},
   TITLE = {The structure of the class of non-uniquely reconstructible sets},
   YEAR = {1993},
   NUMBER = {1-4},
   PAGES = {359-384},
   VOLUME = {58},
   URL = {http://www.math.u-szeged.hu/publikac/acta/acta.htm},
   }
   

Conference articles

1. Zoltan Kato, Mark Berthod, and Josiane Zerubia. A Hierarchical Markov Random Field Model for Image Classification. In Proceedings of the International Workshop on Image and Multidimensional Digital Signal Processing, Cannes, France, September 1993. IEEE. [PS]
   Abstract: In this paper, we propose a hierarchical Markov Random Field (MRF) model. This model is based on a classical multiscale model, which consists of a label pyramid and a whole observation field. The parameters of the coarse grid can be derived by simple computation from the finest grid. In the label pyramid, we have introduced a new local interaction between two neighbor grids. This model gives a relaxation algorithm with a new annealingscheme: The Multi-Temperature Annealing (MTA) scheme, which consists of associating higher temperatures to higher levels, thus beeing less sensitive to local minima at coarser grids. The model was tested on different synthetic and real images. The algorithm was implemented on a Connection MachineCM200.
   @INPROCEEDINGS{Kato-etal93d,
   AUTHOR = {Zoltan Kato and Mark Berthod and Josiane Zerubia},
   BOOKTITLE = {Proceedings of the International Workshop on Image and Multidimensional Digital Signal Processing},
   TITLE = {A Hierarchical Markov Random Field Model for Image Classification},
   YEAR = {1993},
   ADDRESS = {Cannes, France},
   MONTH = {September},
   ORGANIZATION = {IEEE},
   PS = {../papers/imdsp.ps},
   }
   


2. Zoltan Kato, Mark Berthod, and Josiane Zerubia. Multiscale Markov Random Field Models for Parallel Image Classification. In Proceedings of the International Conference on Computer Vision, Berlin, Germany, pages 253-257, May 1993. IEEE. [PS]
   Abstract: In this paper, we are interested in multiscale Markov Random Field (MRF) models. It is well known that multigrid methods can improve significantly the convergence rate and the quality of the final results of iterative relaxation techniques. Herein, we propose a new hierarchical model, which consists of a label pyramid and a whole observation field. The parameters of the coarse grid can be derived by simple computation from the finest grid. In the label pyramid, we have introduced a new local interaction between two neighbor grids. This model gives a relaxation algorithm which can be run in parallel on the entire pyramid. On the other hand, the new model allows to propagate local interactions more efficiently giving estimates closer to the global optimum for deterministic as well as for stochastic relaxation schemes. It can also be seen as a way to incorporate cliques with far apart sites for a reasonable price.
   @INPROCEEDINGS{Kato-etal93a,
   AUTHOR = {Zoltan Kato and Mark Berthod and Josiane Zerubia},
   BOOKTITLE = {Proceedings of the International Conference on Computer Vision},
   TITLE = {Multiscale Markov Random Field Models for Parallel Image Classification},
   YEAR = {1993},
   ADDRESS = {Berlin, Germany},
   MONTH = {May},
   ORGANIZATION = {IEEE},
   PAGES = {253-257},
   PS = {../papers/iccv93.ps},
   }
   


3. Zoltan Kato, Mark Berthod, and Josiane Zerubia. Parallel Image Classification using Multiscale Markov Random Fields. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing, volume 5, Minneapolis, USA, pages 137-140, April 1993. IEEE. [PS]
   Abstract: In this paper, we are interested in massively parallel multiscale relaxation algorithms applied to image classification. First, we present a classical multiscale model applied to supervised image classification.The model consists of a label pyramid and a whole observation field. The potential functions of the coarse grid are derived by simple computations. Then, we propose another scheme introducing a local interaction between two neighbor grids in the label pyramid. This is a way to incorporate cliques with far apart sites for a reasonable price. Finally we present the results on noisy synthetic data and on a SPOT image obtained by different relaxation methods using these models.
   @INPROCEEDINGS{Kato-etal93c,
   AUTHOR = {Zoltan Kato and Mark Berthod and Josiane Zerubia},
   BOOKTITLE = {Proceedings of the International Conference on Acoustics, Speech and Signal Processing},
   TITLE = {Parallel Image Classification using Multiscale Markov Random Fields},
   YEAR = {1993},
   ADDRESS = {Minneapolis, USA},
   MONTH = {April},
   ORGANIZATION = {IEEE},
   PAGES = {137-140},
   VOLUME = {5},
   PS = {../papers/icassp93.ps},
   }
   

  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