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.

1 aKato, Zoltan1 aZerubia, Josiane uhttps://www.inf.u-szeged.hu/en/publication/markov-random-fields-in-image-segmentation01149nas a2200181 4500008004100000020001400041245009500055210006900150260001500219300001600234490000700250520049500257100001900752700002000771700001700791700002100808856013800829 2009 eng d a1057-714900aDetection of Object Motion Regions in Aerial Image Pairs with a Multilayer Markovian Model0 aDetection of Object Motion Regions in Aerial Image Pairs with a bIEEEc2009 a2303 - 23150 v183 aWe 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.

1 aBenedek, Csaba1 aSziranyi, Tamas1 aKato, Zoltan1 aZerubia, Josiane uhttps://www.inf.u-szeged.hu/en/publication/detection-of-object-motion-regions-in-aerial-image-pairs-with-a-multilayer-markovian-model00655nas a2200169 4500008004100000020001400041245010700055210006900162260001200231300001400243490000700257100001900264700001600283700001700299700002100316856014800337 2009 eng d a0031-320300aA higher-order active contour model of a 'gas of circles' and its application to tree crown extraction0 ahigherorder active contour model of a gas of circles and its app c2009/// a699 - 7090 v421 aHorvath, Peter1 aJermyn, Ian1 aKato, Zoltan1 aZerubia, Josiane uhttps://www.inf.u-szeged.hu/en/publication/a-higher-order-active-contour-model-of-a-gas-of-circles-and-its-application-to-tree-crown-extraction00446nas a2200097 4500008004100000245009900041210007600140260007300216300001400289856004500303 2007 eng d00aKör alakú objektumok szegmentálása magasabb rendű aktív kontúr modellek segítségével0 aKör alakú objektumok szegmentálása magasabb rendű aktív kontúr m aDebrecenbKépfeldolgozók és Alakfelismerők TársaságacJan 2007 a133 - 140 uhttps://www.inf.u-szeged.hu/en/node/127500526nas a2200133 4500008004100000245007500041210006900116260001200185100001900197700002000216700001700236700002100253856011800274 2007 eng d00aA Three-layer MRF model for Object Motion Detection in Airborne Images0 aThreelayer MRF model for Object Motion Detection in Airborne Ima c2007///1 aBenedek, Csaba1 aSziranyi, Tamas1 aKato, Zoltan1 aZerubia, Josiane uhttps://www.inf.u-szeged.hu/en/publication/a-three-layer-mrf-model-for-object-motion-detection-in-airborne-images01332nas a2200109 4500008004100000245005900041210005600100260001800156300001400174520098900188856004501177 2006 eng d00aA higher-order active contour model for tree detection0 ahigherorder active contour model for tree detection bIEEEc2006/// a130 - 1333 aWe present a model of a 'gas of circles', 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 'higher order active contours' (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. © 2006 IEEE.

uhttps://www.inf.u-szeged.hu/en/node/123300360nas a2200085 4500008004100000245010700041210006900148260001200217856004500229 2006 eng d00aA Higher-Order Active Contour Model of a `Gas of Circles' and its Application to Tree Crown Extraction0 aHigherOrder Active Contour Model of a Gas of Circles and its App c2006/// uhttps://www.inf.u-szeged.hu/en/node/126700438nas a2200097 4500008004100000245011200041210006900153260005900222300001400281856004500295 2006 eng d00aAn Improved `Gas of Circles' Higher-Order Active Contour Model and its Application to Tree Crown Extraction0 aImproved Gas of Circles HigherOrder Active Contour Model and its aBerlin; Heidelberg; New YorkbSpringer Verlagc2006/// a152 - 161 uhttps://www.inf.u-szeged.hu/en/node/125500403nas a2200097 4500008004100000245009300041210006900134260003000203300002000233856005200253 2006 eng d00aA multi-layer MRF model for object-motion detection in unregistered airborne image-pairs0 amultilayer MRF model for objectmotion detection in unregistered aPiscatawaybIEEEc2006/// aVI-141 - VI-144 uhttp://www.icip2007.org/Papers/AcceptedList.asp00325nas a2200097 4500008004100000245005100041210005100092260002500143300001400168856004500182 2005 eng d00aShape Moments for Region Based Active Contours0 aShape Moments for Region Based Active Contours aViennabOCGc2005/// a187 - 194 uhttps://www.inf.u-szeged.hu/en/node/127600416nas a2200121 4500008004100000020001400041245009200055210006900147260001200216300001400228490000700242856004500249 2002 eng d a1155-433900aMarkov random fields in image processing application to remote sensing and astrophysics0 aMarkov random fields in image processing application to remote s c2002/// a117 - 1360 v12 uhttps://www.inf.u-szeged.hu/en/node/127800441nas a2200121 4500008004100000020001400041245010400055210006900159260001200228300001400240490000600254856005900260 2000 eng d a1077-201400aImage segmentation using Markov random field model in fully parallel cellular network architectures0 aImage segmentation using Markov random field model in fully para c2000/// a195 - 2110 v6 uhttp://www.sztaki.hu/~sziranyi/Papers/Sziranyi_MRF.pdf01647nas a2200133 4500008004100000020001400041245007000055210006900125260001200194300001400206490000700220520124100227856004501468 1999 eng d a0031-320300aUnsupervised parallel image classification using Markovian models0 aUnsupervised parallel image classification using Markovian model c1999/// a591 - 6040 v323 aThis 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. © 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

uhttps://www.inf.u-szeged.hu/en/node/123600380nas a2200097 4500008004100000245010500041210006900146260001200215300001000227856004500237 1997 eng d00aImage segmentation using Markov random field model in fully parallel cellular network architectures.0 aImage segmentation using Markov random field model in fully para c1997/// a - 17 uhttps://www.inf.u-szeged.hu/en/node/120500326nas a2200085 4500008004100000245007300041210006900114260001200183856004500195 1997 eng d00aMarkov Random Field Image Segmentation using Cellular Neural Network0 aMarkov Random Field Image Segmentation using Cellular Neural Net c1997/// uhttps://www.inf.u-szeged.hu/en/node/128000442nas a2200097 4500008004100000245008100041210006900122260009600191300001200287856004500299 1997 eng d00aMRF based image segmentation with fully parallel cellular nonlinear networks0 aMRF based image segmentation with fully parallel cellular nonlin aKeszthelybPannon Agrártudományi Egyetem Georgikon Mezőgazdaságtudományi KarcOct 1997 a43 - 50 uhttps://www.inf.u-szeged.hu/en/node/120602054nas a2200133 4500008004100000020001400041245006100055210006100116260001200177300001400189490000700203520166500210856004501875 1996 eng d a0262-885600aBayesian image classification using Markov random fields0 aBayesian image classification using Markov random fields c1996/// a285 - 2950 v143 aIn 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).

uhttps://www.inf.u-szeged.hu/en/node/123700379nas a2200097 4500008004100000245007000041210006900111260004200180300001400222856004500236 1996 eng d00aCellular Neural Network in Markov Random Field Image Segmentation0 aCellular Neural Network in Markov Random Field Image Segmentatio aNew YorkbWiley - IEEE Pressc1996/// a139 - 144 uhttps://www.inf.u-szeged.hu/en/node/120801810nas a2200133 4500008004100000020001400041245011000055210006900165260001200234300001200246490000700258520136600265856004501631 1996 eng d a1077-316900aA Hierarchical Markov Random Field Model and Multitemperature Annealing for Parallel Image Classification0 aHierarchical Markov Random Field Model and Multitemperature Anne c1996/// a18 - 370 v583 aIn 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). © 1996 Academic Press, Inc.

uhttps://www.inf.u-szeged.hu/en/node/123800962nas a2200133 4500008004100000020001400041245005300055210005200108260001200160300001600172490000600188520058900194856004500783 1995 eng d a1057-714900aDPA: a deterministic approach to the MAP problem0 aDPA a deterministic approach to the MAP problem c1995/// a1312 - 13140 v43 aDeterministic 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. uhttps://www.inf.u-szeged.hu/en/node/123900983nas a2200109 4500008004100000245004500041210004500086260003000131300001600161520065100177856004500828 1995 eng d00aUnsupervised adaptive image segmentation0 aUnsupervised adaptive image segmentation aPiscatawaybIEEEc1995/// a2399 - 24023 aThis 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. uhttps://www.inf.u-szeged.hu/en/node/124001618nas a2200109 4500008004100000245008400041210006900125260003000194300001400224520122500238856004501463 1995 eng d00aUnsupervised parallel image classification using a hierarchical Markovian model0 aUnsupervised parallel image classification using a hierarchical aPiscatawaybIEEEc1995/// a169 - 1743 aThis 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). uhttps://www.inf.u-szeged.hu/en/node/124100418nas a2200097 4500008004100000245011900041210006900160260003200229300001400261856004500275 1994 eng d00aMulti-Temperature Annealing: A New Approach for the Energy-Minimization of Hierarchical Markov Random Field Models0 aMultiTemperature Annealing A New Approach for the EnergyMinimiza aLos AlamitosbIEEEc1994/// a520 - 522 uhttps://www.inf.u-szeged.hu/en/node/126100351nas a2200085 4500008004100000245009700041210007000138260001200208856004500220 1994 eng d00aSegmentation hiérarchique d'images sur CM200 (Hierarchical Image Segmentation on the CM200)0 aSegmentation hiérarchique dimages sur CM200 Hierarchical Image S c1994/// uhttps://www.inf.u-szeged.hu/en/node/128100383nas a2200085 4500008004100000245014300041210007000184260001200254856003100266 1994 eng d00aSegmentation multirésolution d'images sur SUN version 1 du 26.05.1994 (Multiresolution Image Segmentation on SUN version 1 of 26.05.1994)0 aSegmentation multirésolution dimages sur SUN version 1 du 260519 c1994/// uhttp://www.app.asso.fr/en/00387nas a2200097 4500008004100000245006100041210006100102260006700163300001400230856004500244 1993 eng d00aBayesian Image Classification Using Markov Random Fields0 aBayesian Image Classification Using Markov Random Fields aDordrecht; Boston; LondonbKluwer Academic Publishersc1993/// a375 - 382 uhttps://www.inf.u-szeged.hu/en/node/125000283nas a2200085 4500008004100000245005000041210004900091260001200140856004500152 1993 eng d00aExtraction d'information dans les images SPOT0 aExtraction dinformation dans les images SPOT c1993/// uhttps://www.inf.u-szeged.hu/en/node/127100359nas a2200085 4500008004100000245011100041210006900152260001200221856004000233 1993 eng d00aA Hierarchical Markov Random Field Model and Multi-Temperature Annealing for Parallel Image Classification0 aHierarchical Markov Random Field Model and MultiTemperature Anne c1993/// uhttp://hal.inria.fr/inria-00074736/00347nas a2200085 4500008004100000245007000041210006800111260003700179856004500216 1993 eng d00aA Hierarchical Markov Random Field Model for Image Classification0 aHierarchical Markov Random Field Model for Image Classification bIEEE Computer Soc. Pr.cSep 1993 uhttps://www.inf.u-szeged.hu/en/node/126201316nas a2200109 4500008004100000245007600041210006900117260003200186300001400218520092900232856004501161 1993 eng d00aMultiscale Markov random field models for parallel image classification0 aMultiscale Markov random field models for parallel image classif aLos AlamitosbIEEEc1993/// a253 - 2573 aIn 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. uhttps://www.inf.u-szeged.hu/en/node/124201074nas a2200109 4500008004100000245007200041210006900113260002800182300001400210520069500224856004500919 1993 eng d00aParallel image classification using multiscale Markov random fields0 aParallel image classification using multiscale Markov random fie aNew YorkbIEEEc1993/// a137 - 1403 aIn 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. uhttps://www.inf.u-szeged.hu/en/node/124300349nas a2200085 4500008004100000245008400041210006900125260001200194856005700206 1992 eng d00aImage Classification Using Markov Random Fields with Two New Relaxation Methods0 aImage Classification Using Markov Random Fields with Two New Rel c1992/// uhttp://hal.inria.fr/docs/00/07/49/54/PDF/RR-1606.pdf00376nas a2200097 4500008004100000245007200041210006900113260003700182300001400219856004500233 1992 eng d00aSatellite Image Classification Using a Modified Metropolis Dynamics0 aSatellite Image Classification Using a Modified Metropolis Dynam bIEEE Computer Soc. Pr.cMar 1992 a573 - 576 uhttps://www.inf.u-szeged.hu/en/node/1263