Markov Random Fields in Image Segmentation introduces the fundamentals of Markovian modeling in image segmentation as well as providing a brief overview of recent advances in the field.

}, author = {Zoltan Kato and Josiane Zerubia} } @article {1211, title = {Detection of Object Motion Regions in Aerial Image Pairs with a Multilayer Markovian Model}, journal = {IEEE TRANSACTIONS ON IMAGE PROCESSING}, volume = {18}, year = {2009}, note = {UT: 000269715500013ScopusID: 70349442338doi: 10.1109/TIP.2009.2025808}, month = {2009}, pages = {2303 - 2315}, publisher = {IEEE}, type = {Journal article}, abstract = {We propose a new Bayesian method for detectingthe regions of object displacements in aerial image pairs. We use a robust but coarse 2-D image registration algorithm. Our main challenge is to eliminate the registration errors from the extracted change map. We introduce a three-layer Markov Random Field (L3MRF) model which integrates information from two different features, and ensures connected homogenous regions in the segmented images. Validation is given on real aerial photos.

}, isbn = {1057-7149}, doi = {10.1109/TIP.2009.2025808 }, author = {Csaba Benedek and Tamas Sziranyi and Zoltan Kato and Josiane Zerubia} } @article {1213, title = {A higher-order active contour model of a {\textquoteright}gas of circles{\textquoteright} and its application to tree crown extraction}, journal = {PATTERN RECOGNITION}, volume = {42}, year = {2009}, note = {UT: 000263431200011doi: 10.1016/j.patcog.2008.09.008}, month = {2009///}, pages = {699 - 709}, isbn = {0031-3203}, author = {Peter Horvath and Ian Jermyn and Zoltan Kato and Josiane Zerubia} } @conference {1275, title = {K{\"o}r alak{\'u} objektumok szegment{\'a}l{\'a}sa magasabb rend{\H u} akt{\'\i}v kont{\'u}r modellek seg{\'\i}ts{\'e}g{\'e}vel}, booktitle = {A K{\'e}pfeldolgoz{\'o}k {\'e}s Alakfelismer{\H o}k T{\'a}rsas{\'a}g{\'a}nak konferenci{\'a}ja - K{\'E}PAF 2007}, year = {2007}, month = {Jan 2007}, pages = {133 - 140}, publisher = {K{\'e}pfeldolgoz{\'o}k {\'e}s Alakfelismer{\H o}k T{\'a}rsas{\'a}ga}, organization = {K{\'e}pfeldolgoz{\'o}k {\'e}s Alakfelismer{\H o}k T{\'a}rsas{\'a}ga}, type = {Conference paper}, address = {Debrecen} } @booklet {1266, title = {A Three-layer MRF model for Object Motion Detection in Airborne Images}, year = {2007}, month = {2007///}, author = {Csaba Benedek and Tamas Sziranyi and Zoltan Kato and Josiane Zerubia} } @inbook {1233, title = {A higher-order active contour model for tree detection}, booktitle = {Proceedings of the18th International Conference on Pattern Recognition, ICPR 2006}, year = {2006}, note = {ScopusID: 34047219865doi: 10.1109/ICPR.2006.79}, month = {2006///}, pages = {130 - 133}, publisher = {IEEE}, organization = {IEEE}, abstract = {We present a model of a {\textquoteright}gas of circles{\textquoteright}, the ensemble of regions in the image domain consisting of an unknown number of circles with approximately fixed radius and short range repulsive interactions, and apply it to the extraction of tree crowns from aerial images. The method uses the recently introduced {\textquoteright}higher order active contours{\textquoteright} (HOACs), which incorporate long-range interactions between contour points, and thereby include prior geometric information without using a template shape. This makes them ideal when looking for multiple instances of an entity in an image. We study an existing HOAC model for networks, and show via a stability calculation that circles stable to perturbations are possible for constrained parameter sets. Combining this prior energy with a data term, we show results on aerial imagery that demonstrate the effectiveness of the method and the need for prior geometric knowledge. The model has many other potential applications. {\textcopyright} 2006 IEEE.

} } @booklet {1267, title = {A Higher-Order Active Contour Model of a {\textquoteleft}Gas of Circles{\textquoteright} and its Application to Tree Crown Extraction}, year = {2006}, month = {2006///} } @inbook {1255, title = {An Improved {\textquoteleft}Gas of Circles{\textquoteright} Higher-Order Active Contour Model and its Application to Tree Crown Extraction}, booktitle = {Proceedings of Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP)}, year = {2006}, note = {doi: 10.1007/11949619_14}, month = {2006///}, pages = {152 - 161}, publisher = {Springer Verlag}, organization = {Springer Verlag}, address = {Berlin; Heidelberg; New York} } @inbook {1210, title = {A multi-layer MRF model for object-motion detection in unregistered airborne image-pairs}, booktitle = {Proceedings - 14th International Conference on Image Processing, ICIP 2007}, year = {2006}, month = {2006///}, pages = {VI-141 - VI-144}, publisher = {IEEE}, organization = {IEEE}, address = {Piscataway}, url = {http://www.icip2007.org/Papers/AcceptedList.asp} } @inbook {1276, title = {Shape Moments for Region Based Active Contours}, booktitle = {Joint Hungarian-Austrian conference on image processing and pattern recognition. 5th conference of the Hungarian Association for Image Processing and Pattern Recognition (K{\'E}PAF), 29th workshop of the Austrian Association for Pattern Reco}, year = {2005}, month = {2005///}, pages = {187 - 194}, publisher = {OCG}, organization = {OCG}, address = {Vienna} } @article {1278, title = {Markov random fields in image processing application to remote sensing and astrophysics}, journal = {JOURNAL DE PHYSIQUE IV}, volume = {12}, year = {2002}, note = {UT: 000175261200006doi: 10.1051/jp42002005}, month = {2002///}, pages = {117 - 136}, isbn = {1155-4339} } @article {1207, title = {Image segmentation using Markov random field model in fully parallel cellular network architectures}, journal = {REAL-TIME IMAGING}, volume = {6}, year = {2000}, note = {UT: 000088331700003ScopusID: 0034204755}, month = {2000///}, pages = {195 - 211}, isbn = {1077-2014}, url = {http://www.sztaki.hu/~sziranyi/Papers/Sziranyi_MRF.pdf} } @article {1236, title = {Unsupervised parallel image classification using Markovian models}, journal = {PATTERN RECOGNITION}, volume = {32}, year = {1999}, note = {UT: 000079145300005ScopusID: 0033116536doi: 10.1016/S0031-3203(98)00104-6}, month = {1999///}, pages = {591 - 604}, abstract = {This paper deals with the problem of unsupervised classification of images modeled by Markov random fields (MRF). If the model parameters are known then we have various methods to solve the segmentation problem (simulated annealing (SA), iterated conditional modes (ICM), etc). However, when the parameters are unknown, the problem becomes more difficult. One has to estimate the hidden label field parameters only from the observed image. Herein, we are interested in parameter estimation methods related to monogrid and hierarchical MRF models. The basic idea is similar to the expectation-maximization (EM) algorithm: we recursively look at the maximum a posteriori (MAP) estimate of the label field given the estimated parameters, then we look at the maximum likelihood (ML) estimate of the parameters given a tentative labeling obtained at the previous step. The only parameter supposed to be known is the number of classes, all the other parameters are estimated. The proposed algorithms have been implemented on a Connection Machine CM200. Comparative experiments have been performed on both noisy synthetic data and real images. {\textcopyright} 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

}, isbn = {0031-3203} } @booklet {1205, title = {Image segmentation using Markov random field model in fully parallel cellular network architectures.}, year = {1997}, month = {1997///}, pages = { - 17} } @booklet {1280, title = {Markov Random Field Image Segmentation using Cellular Neural Network}, year = {1997}, month = {1997///} } @conference {1206, title = {MRF based image segmentation with fully parallel cellular nonlinear networks}, booktitle = {A K{\'e}pfeldolgoz{\'o}k {\'e}s Alakfelismer{\H o}k T{\'a}rsas{\'a}g{\'a}nak konferenci{\'a}ja - K{\'E}PAF 1997}, year = {1997}, month = {Oct 1997}, pages = {43 - 50}, publisher = {Pannon Agr{\'a}rtudom{\'a}nyi Egyetem Georgikon Mez{\H o}gazdas{\'a}gtudom{\'a}nyi Kar}, organization = {Pannon Agr{\'a}rtudom{\'a}nyi Egyetem Georgikon Mez{\H o}gazdas{\'a}gtudom{\'a}nyi Kar}, address = {Keszthely} } @article {1237, title = {Bayesian image classification using Markov random fields}, journal = {IMAGE AND VISION COMPUTING}, volume = {14}, year = {1996}, note = {UT: A1996UT58100004ScopusID: 0030148684doi: 10.1016/0262-8856(95)01072-6}, month = {1996///}, pages = {285 - 295}, 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 convexifies 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).

}, isbn = {0262-8856} } @inbook {1208, title = {Cellular Neural Network in Markov Random Field Image Segmentation}, booktitle = {1996 FOURTH IEEE INTERNATIONAL WORKSHOP ON CELLULAR NEURAL NETWORKS AND THEIR APPLICATIONS, PROCEEDINGS (CNNA-96)}, year = {1996}, note = {UT: A1996BH11L00025ScopusID: 0030409916Besorol{\'a}s: Konferenciak{\"o}zlem{\'e}ny}, month = {1996///}, pages = {139 - 144}, publisher = {Wiley - IEEE Press}, organization = {Wiley - IEEE Press}, address = {New York} } @article {1238, title = {A Hierarchical Markov Random Field Model and Multitemperature Annealing for Parallel Image Classification}, journal = {GRAPHICAL MODELS AND IMAGE PROCESSING}, volume = {58}, year = {1996}, note = {UT: A1996TZ03400002ScopusID: 0029732459doi: 10.1006/gmip.1996.0002}, month = {1996///}, pages = {18 - 37}, 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 multitemperature 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 generalization of the annealing theorem of S. Geman and D. Geman (IEEE Trans. Pattern Anal. Mach. Intell. 6, 1984, 721-741). {\textcopyright} 1996 Academic Press, Inc.

}, isbn = {1077-3169} } @article {1239, title = {DPA: a deterministic approach to the MAP problem}, journal = {IEEE TRANSACTIONS ON IMAGE PROCESSING}, volume = {4}, year = {1995}, note = {UT: A1995RT35400011ScopusID: 0029375669doi: 10.1109/83.413175}, month = {1995///}, pages = {1312 - 1314}, abstract = {Deterministic pseudo-annealing (DPA) is a new deterministic optimization method for finding the maximum a posteriori (MAP) labeling in a Markov random field, in which the probability of a tentative labeling is extended to a merit function on continuous labelings. This function is made convex by changing its definition domain. This unambiguous maximization problem is solved, and the solution is followed down to the original domain, yielding a good, if suboptimal, solution to the original labeling assignment problem. The performance of DPA is analyzed on randomly weighted graphs.}, isbn = {1057-7149} } @inbook {1240, title = {Unsupervised adaptive image segmentation}, booktitle = {ICASSP-95}, year = {1995}, note = {ScopusID: 0028996751doi: 10.1109/ICASSP.1995.479976}, month = {1995///}, pages = {2399 - 2402}, publisher = {IEEE}, organization = {IEEE}, address = {Piscataway}, abstract = {This paper deals with the problem of unsupervised Bayesian segmentation of images modeled by Markov Random Fields (MRF). If the model parameters are known then we have various methods to solve the segmentation problem (Simulated Annealing, ICM, etc...). However, when they are not known, the problem becomes more difficult. One has to estimate the hidden label field parameters from the available image only. Our approach consists of a recent iterative method of estimation, called Iterative Conditional Estimation (ICE), applied to a monogrid Markovian image segmentation model. The method has been tested on synthetic and real satellite images.} } @inbook {1241, title = {Unsupervised parallel image classification using a hierarchical Markovian model}, booktitle = {Proceedings of the 5th International Conference on Computer Vision}, year = {1995}, note = {ScopusID: 0029214757doi: 10.1109/ICCV.1995.466790}, month = {1995///}, pages = {169 - 174}, publisher = {IEEE}, organization = {IEEE}, address = {Piscataway}, abstract = {This paper deals with the problem of unsupervised classification of images modeled by Markov Random Fields (MRF). If the model parameters are known then we have various methods to solve the segmentation problem (simulated annealing, ICM, etc...). However, when they are not known, the problem becomes more difficult. One has to estimate the hidden label field parameters from the only observable image. Our approach consists of extending a recent iterative method of estimation, called Iterative Conditional Estimation (ICE) to a hierarchical markovian model. The idea resembles the Estimation-Maximization (EM) algorithm as we recursively look at the Maximum a Posteriori (MAP) estimate of the label field given the estimated parameters then we look at the Maximum Likelihood (ML) estimate of the parameters given a tentative labeling obtained at the previous step. We propose unsupervised image classification algorithms using a hierarchical model. The only parameter supposed to be known is the number of regions, all the other parameters are estimated. The presented algorithms have been implemented on a Connection Machine CM200. Comparative tests have been done on noisy synthetic and real images (remote sensing).} } @inbook {1261, title = {Multi-Temperature Annealing: A New Approach for the Energy-Minimization of Hierarchical Markov Random Field Models}, booktitle = {Proceedings of the 12th IAPR International Conference on Pattern Recognition}, year = {1994}, note = {doi: 10.1109/ICPR.1994.576342}, month = {1994///}, pages = {520 - 522}, publisher = {IEEE}, organization = {IEEE}, address = {Los Alamitos} } @booklet {1281, title = {Segmentation hi{\'e}rarchique d{\textquoteright}images sur CM200 (Hierarchical Image Segmentation on the CM200)}, year = {1994}, month = {1994///} } @booklet {1279, title = {Segmentation multir{\'e}solution d{\textquoteright}images sur SUN version 1 du 26.05.1994 (Multiresolution Image Segmentation on SUN version 1 of 26.05.1994)}, year = {1994}, month = {1994///}, url = {http://www.app.asso.fr/en/} } @inbook {1250, title = {Bayesian Image Classification Using Markov Random Fields}, booktitle = {Maximum Entropy and Bayesian Methods}, year = {1993}, month = {1993///}, pages = {375 - 382}, publisher = {Kluwer Academic Publishers}, organization = {Kluwer Academic Publishers}, address = {Dordrecht; Boston; London} } @booklet {1271, title = {Extraction d{\textquoteright}information dans les images SPOT}, year = {1993}, month = {1993///} } @booklet {1272, title = {A Hierarchical Markov Random Field Model and Multi-Temperature Annealing for Parallel Image Classification}, year = {1993}, month = {1993///}, url = {http://hal.inria.fr/inria-00074736/} } @conference {1262, title = {A Hierarchical Markov Random Field Model for Image Classification}, booktitle = {International Workshop on Image and Multidimensional Digital Signal Processing (IMDSP)}, year = {1993}, note = {Art. No.: imdsp.ps}, month = {Sep 1993}, publisher = {IEEE Computer Soc. Pr.}, organization = {IEEE Computer Soc. Pr.} } @inbook {1242, title = {Multiscale Markov random field models for parallel image classification}, booktitle = {Fourth International Conference on Computer Vision, ICCV 1993, Berlin, Germany, 11-14 May, 1993, Proceedings}, year = {1993}, note = {ScopusID: 0027224261}, month = {1993///}, pages = {253 - 257}, publisher = {IEEE}, organization = {IEEE}, address = {Los Alamitos}, 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.} } @inbook {1243, title = {Parallel image classification using multiscale Markov random fields}, booktitle = {ICASSP-93}, year = {1993}, note = {ScopusID: 0027266514doi: 10.1109/ICASSP.1993.319766}, month = {1993///}, pages = {137 - 140}, publisher = {IEEE}, organization = {IEEE}, address = {New York}, 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.} } @booklet {1273, title = {Image Classification Using Markov Random Fields with Two New Relaxation Methods}, year = {1992}, month = {1992///}, url = {http://hal.inria.fr/docs/00/07/49/54/PDF/RR-1606.pdf} } @conference {1263, title = {Satellite Image Classification Using a Modified Metropolis Dynamics}, booktitle = {International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year = {1992}, note = {doi: 10.1109/ICASSP.1992.226148}, month = {Mar 1992}, pages = {573 - 576}, publisher = {IEEE Computer Soc. Pr.}, organization = {IEEE Computer Soc. Pr.} }