DOCSLIB.ORG

Markov Random Fields and Images

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Markov Random Fields and Images Volume 11 (4) 1998, pp. 413 { 437 Markov Random Fields and Images Patrick Perez Irisa/Inria, Campus de Beaulieu, 35042 Rennes Cedex, France e-mail: [email protected] At the intersection of statistical physics and probability theory,Markov random elds and Gibbs distributions have emerged in the early eighties as p owerful to ols for mo deling images and coping with high-dimensional inverse problems from low- level vision. Since then, they have b een used in many studies from the image pro cessing and computer vision community. Abrief and simple intro duction to the basics of the domain is prop osed. 1. Introduction and general framework With a seminal pap er by Geman and Geman in 1984 [18], powerful to ols known for long by physicists [2] and statisticians [3] were brought in a com- prehensive and stimulating way to the knowledge of the image pro cessing and computer vision community. Since then, their theoretical richness, their prac- tical versatility, and a numb er of fruitful connections with other domains, have resulted in a profusion of studies. These studies deal either with the mo d- eling of images (for synthesis, recognition or compression purp oses) or with the resolution of various high-dimensional inverse problems from early vision (e.g., restoration, deblurring, classi cation, segmentation, data fusion, surface reconstruction, optical ow estimation, stereo matching, etc. See collections of examples in [11,30,40]). The implicit assumption b ehind probabilistic approaches to image analysis is that, for a given problem, there exists a probability distribution that can capture to some extent the variability and the interactions of the di erent sets of relevant image attributes. Consequently, one considers the variables of the n problem as random variables forming a set (or random vector) X = (X ) i i=1 1 with joint probability distribution P . X 1 P is actually a probability mass in the case of discrete variables, and a probability density X function when the X 's are continuously valued. In the latter case, all summations over i states or con gurations should b e replaced byintegrals. 413 The rst critical step toward probabilistic mo deling thus obviously relies on the choice of the multivariate distribution P . Since there is so far no really X generic theory for selecting a mo del, a tailor-made parameterized function P X is generally chosen among standard ones, based on intuition of the desirable 2 prop erties . The basic characteristic of chosen distributions is their decomp osition as a pro duct of factors dep ending on just a few variables (one or two in most cases). Also, a given distribution involves only a few typ es of factors. One has simply to sp ecify these local \interaction" factors (which might be complex, and might involvevariables of di erent nature) to de ne, up to some multiplicative constant, the joint distribution P (x ;::: ;x ): one ends X 1 n up with a global mo del. With such a setup, eachvariable only directly dep ends on a few other \neigh- b oring" variables. From a more global p oint of view, all variables are mutually dep endent, but only through the combination of successive lo cal interactions. This key notion can b e formalized considering the graph for which i and j are neighb ors if x and x app ear within a same lo cal comp onent of the chosen i j factorization. This graph turns out to b e a p owerful to ol to account for lo cal and global structural prop erties of the mo del, and to predict changes in these prop erties through various manipulations. From a probabilistic p oint of view, this graph neatly captures Markov-typ e conditional indep endencies among the random variables attached to its vertices. After the sp eci cation of the mo del, one deals with its actual use for mo d- eling a class of problems and for solving them. At that p oint, as we shall see, one of the two following things will have to b e done: (1) drawing samples from the joint distribution, or from some conditional distribution deduced from the jointlaw when part of the variables are observed and thus xed; (2) maximiz- ing some distribution (P itself, or some conditional or marginal distribution X deduced from it). The very high dimensionality of image problems under concern usually ex- cludes any direct metho d for p erforming b oth tasks. However the lo cal decom- p osition of P fortunately allows to devise suitable deterministic or sto chastic X iterative algorithms, based on a common principle: at each step, just a few variables (often a single one) are considered, all the others b eing \frozen". Markovian prop erties then imply that the computations to be done remain lo cal, that is, they only involve neighb oring variables. This pap er is intended to give a brief (and de nitely incomplete) overview of how Markovian mo dels can b e de ned and manipulated in the prosp ect of mo deling and analyzing images. Starting from the formalization of Markov ran- dom elds (mrfs) on graphs through the sp eci cation of a Gibbs distribution (x2), the standard issues of interest are then grossly reviewed: sampling from a high-dimensional Gibbs distribution (x3); learning mo dels (at least param- eters) from observed images (x4); using the Bayesian machinery to cop e with 2 Sup erscript denotes a parameter vector. Unless necessary, it will b e dropp ed for nota- tional convenience. 414 inverse problems, based on learned mo dels (x5); estimating parameters with partial observations, esp ecially in the case of inverse problems (x6). Finally two mo deling issues (namely the intro duction of so-called auxiliary variables, and the de nition of hierarchical mo dels), which are receiving a great deal of attention from the community at the moment, are evoked (x7). 2. Gibbs distribution and graphical Markovproperties Let us now make more formal acquaintance with Gibbs distributions and their Markov prop erties. Let X ;i = 1;::: ;n, be random variables taking values i in some discrete or continuous state space , and form the random vector T n X =(X ;::: ;X ) with con guration set = . All sorts of state spaces 1 n are used in practice. More common examples are: = f0;::: ;255g for 8-bit quantized luminances; = f1;::: ;Mg for semantic \lab elings" involving M classes; = R for continuously-valued variables like luminance, depth, etc.; = fu ;::: ;u g fv ;::: ;v g in matching problems involving max max max max 2 displacementvectors or stereo disparities for instance; = R in vector eld- based problems like optical ow estimation or shap e-from-shading. As said in the intro duction, P exhibits a factorized form: X Y P (x) / f (x ); (1) X c c c2C where C consists of small index subsets c, the factor f dep ends only on the c Q variable subset x = fx ;i 2 cg, and f is summable over . If, in addi- c i c c tion, the pro duct is p ositive (8x 2 ; P (x) > 0), then it can be written in X exp onential form (letting V = ln f ): c c X 1 P (x)= expf V (x )g: (2) X c c Z c Well known from physicists, this is the Gibbs (or Boltzman) distribution with P interaction potential fV ;c 2Cg, energy U = V , and partition function (of c c c P 3 parameters) Z = expfU (x)g . Con gurations of lower energies are x2 the more likely, whereas high energies corresp ond to low probabilities. The interaction structure induced by the factorized form is conveniently captured by a graph that statisticians refer to as the independencegraph: the Q indep endence graph asso ciated with the factorization f is the simple c c2C undirected graph G =[S; E ] with vertex set S = f1;::: ;ng, and edge set E de ned as: fi; j g2 E ()9c2C :fi; j gc, i.e., i and j are neighb ors if x i and x app ear simultaneously within a same factor f . The neighborhood n(i) j c 4 . As a consequence of site i is then de ned as n(i) = fj 2 S : fi; j g2 Eg 3 Formal expression of the normalizing constant Z must not veil the fact that it is unknown and b eyond reach in general, due to the intractable summation over . 4 n = fn(i);i 2 Sg is called a neighborhood system, and the neighb orho o d of some subset a S is de ned as n(a)=fj 2Sa:n(j)\a6=g. 415 of the de nition, any subset c is either a singleton or comp osed of mutually neighb oring sites: C is a set of cliques for G . When variables are attached to the pixels of an image, the most common neighb orho o d systems are the regular ones where a site away from the b order of the lattice has four or eight neighb ors. In the rst case ( rst-order neighb or- ho o d system, like in Figure 1.a) subsets c have at most two elements, whereas, in the second-order neighb orho o d system cliques can exhibit up to 4 sites. How- ever, other graph structures are also used: in segmentation applications where the image plane is partitioned, G might b e the planar graph asso ciated to the partition (Figure 1.b); and hierarchical image mo dels often live on (quad)-trees (Figure 1.c). (a) (b) (c) Figure 1.
Load more

Recommended publications
  • Methods of Monte Carlo Simulation II
    Methods of Monte Carlo Simulation II Ulm University Institute of Stochastics Lecture Notes Dr. Tim Brereton Summer Term 2014 Ulm, 2014 2 Contents 1 SomeSimpleStochasticProcesses 7 1.1 StochasticProcesses . 7 1.2 RandomWalks .......................... 7 1.2.1 BernoulliProcesses . 7 1.2.2 RandomWalks ...................... 10 1.2.3 ProbabilitiesofRandomWalks . 13 1.2.4 Distribution of Xn .................... 13 1.2.5 FirstPassageTime . 14 2 Estimators 17 2.1 Bias, Variance, the Central Limit Theorem and Mean Square Error................................ 19 2.2 Non-AsymptoticErrorBounds. 22 2.3 Big O and Little o Notation ................... 23 3 Markov Chains 25 3.1 SimulatingMarkovChains . 28 3.1.1 Drawing from a Discrete Uniform Distribution . 28 3.1.2 Drawing From A Discrete Distribution on a Small State Space ........................... 28 3.1.3 SimulatingaMarkovChain . 28 3.2 Communication .......................... 29 3.3 TheStrongMarkovProperty . 30 3.4 RecurrenceandTransience . 31 3.4.1 RecurrenceofRandomWalks . 33 3.5 InvariantDistributions . 34 3.6 LimitingDistribution. 36 3.7 Reversibility............................ 37 4 The Poisson Process 39 4.1 Point Processes on [0, )..................... 39 ∞ 3 4 CONTENTS 4.2 PoissonProcess .......................... 41 4.2.1 Order Statistics and the Distribution of Arrival Times 44 4.2.2 DistributionofArrivalTimes . 45 4.3 SimulatingPoissonProcesses. 46 4.3.1 Using the Infinitesimal Definition to Simulate Approx- imately .......................... 46 4.3.2 SimulatingtheArrivalTimes . 47 4.3.3 SimulatingtheInter-ArrivalTimes . 48 4.4 InhomogenousPoissonProcesses. 48 4.5 Simulating an Inhomogenous Poisson Process . 49 4.5.1 Acceptance-Rejection. 49 4.5.2 Infinitesimal Approach (Approximate) . 50 4.6 CompoundPoissonProcesses . 51 5 ContinuousTimeMarkovChains 53 5.1 TransitionFunction. 53 5.2 InfinitesimalGenerator . 54 5.3 ContinuousTimeMarkovChains .
    [Show full text]
  • Image Segmentation Combining Markov Random Fields and Dirichlet Processes
    ANR meeting Image segmentation combining Markov Random Fields and Dirichlet Processes Jessica SODJO IMS, Groupe Signal Image, Talence Encadrants : A. Giremus, J.-F. Giovannelli, F. Caron, N. Dobigeon Jessica SODJO ANR meeting 1 / 28 ANR meeting Plan 1 Introduction 2 Segmentation using DP models Mixed MRF / DP model Inference : Swendsen-Wang algorithm 3 Hierarchical segmentation with shared classes Principle HDP theory 4 Conclusion and perspective Jessica SODJO ANR meeting 2 / 28 ANR meeting Introduction Segmentation – partition of an image in K homogeneous regions called classes – label the pixels : pixel i $ zi 2 f1;:::; K g Bayesian approach – prior on the distribution of the pixels – all the pixels in a class have the same distribution characterized by a parameter vector Uk – Markov Random Fields (MRF) : exploit the similarity of pixels in the same neighbourhood Constraint : K must be fixed a priori Idea : use the BNP models to directly estimate K Jessica SODJO ANR meeting 3 / 28 ANR meeting Segmentation using DP models Plan 1 Introduction 2 Segmentation using DP models Mixed MRF / DP model Inference : Swendsen-Wang algorithm 3 Hierarchical segmentation with shared classes Principle HDP theory 4 Conclusion and perspective Jessica SODJO ANR meeting 4 / 28 ANR meeting Segmentation using DP models Notations – N is the number of pixels – Y is the observed image – Z = fz1;:::; zN g – Π = fA1;:::; AK g is a partition and m = fm1;:::; mK g with mk = jAk j A1 A2 m1 = 1 m2 = 5 A3 m3 = 6 mK = 4 AK FIGURE: Example of partition Jessica SODJO ANR
    [Show full text]
  • 12 : Conditional Random Fields 1 Hidden Markov Model
    10-708: Probabilistic Graphical Models 10-708, Spring 2014 12 : Conditional Random Fields Lecturer: Eric P. Xing Scribes: Qin Gao, Siheng Chen 1 Hidden Markov Model 1.1 General parametric form In hidden Markov model (HMM), we have three sets of parameters, j i transition probability matrix A : p(yt = 1jyt−1 = 1) = ai;j; initialprobabilities : p(y1) ∼ Multinomial(π1; π2; :::; πM ); i emission probabilities : p(xtjyt) ∼ Multinomial(bi;1; bi;2; :::; bi;K ): 1.2 Inference k k The inference can be done with forward algorithm which computes αt ≡ µt−1!t(k) = P (x1; :::; xt−1; xt; yt = 1) recursively by k k X i αt = p(xtjyt = 1) αt−1ai;k; (1) i k k and the backward algorithm which computes βt ≡ µt t+1(k) = P (xt+1; :::; xT jyt = 1) recursively by k X i i βt = ak;ip(xt+1jyt+1 = 1)βt+1: (2) i Another key quantity is the conditional probability of any hidden state given the entire sequence, which can be computed by the dot product of forward message and backward message by, i i i i X i;j γt = p(yt = 1jx1:T ) / αtβt = ξt ; (3) j where we define, i;j i j ξt = p(yt = 1; yt−1 = 1; x1:T ); i j / µt−1!t(yt = 1)µt t+1(yt+1 = 1)p(xt+1jyt+1)p(yt+1jyt); i j i = αtβt+1ai;jp(xt+1jyt+1 = 1): The implementation in Matlab can be vectorized by using, i Bt(i) = p(xtjyt = 1); j i A(i; j) = p(yt+1 = 1jyt = 1): 1 2 12 : Conditional Random Fields The relation of those quantities can be simply written in pseudocode as, T αt = (A αt−1): ∗ Bt; βt = A(βt+1: ∗ Bt+1); T ξt = (αt(βt+1: ∗ Bt+1) ): ∗ A; γt = αt: ∗ βt: 1.3 Learning 1.3.1 Supervised Learning The supervised learning is trivial if only we know the true state path.
    [Show full text]
  • Lecturenotes 4 MCMC I – Contents
    Lecturenotes 4 MCMC I – Contents 1. Statistical Physics and Potts Models 2. Sampling and Re-weighting 3. Importance Sampling and Markov Chain Monte Carlo 4. The Metropolis Algorithm 5. The Heatbath Algorithm (Gibbs Sampler) 6. Start and Equilibration 7. Energy Checks 8. Specific Heat 1 Statistical Physics and Potts Model MC simulations of systems described by the Gibbs canonical ensemble aim at calculating estimators of physical observables at a temperature T . In the following we choose units so that β = 1/T and consider the calculation of the expectation value of an observable O. Mathematically all systems on a computer are discrete, because a finite word length has to be used. Hence, K X (k) Ob = Ob(β) = hOi = Z−1 O(k) e−β E (1) k=1 K X (k) where Z = Z(β) = e−β E (2) k=1 is the partition function. The index k = 1,...,K labels all configurations (or microstates) of the system, and E(k) is the (internal) energy of configuration k. To distinguish the configuration index from other indices, it is put in parenthesis. 2 We introduce generalized Potts models in an external magnetic field on d- dimensional hypercubic lattices with periodic boundary conditions. Without being overly complicated, these models are general enough to illustrate the essential features we are interested in. In addition, various subcases of these models are by themselves of physical interest. Generalizations of the algorithmic concepts to other models are straightforward, although technical complications may arise. We define the energy function of the system by (k) (k) (k) −β E = −β E0 + HM (3) where (k) X (k) (k) (k) (k) 2 d N E = −2 J (q , q ) δ(q , q ) + (4) 0 ij i j i j q hiji N 1 for qi = qj (k) X (k) with δ(qi, qj) = and M = 2 δ(1, qi ) .
    [Show full text]
  • Mathematisches Forschungsinstitut Oberwolfach Scaling Limits in Models of Statistical Mechanics
    Mathematisches Forschungsinstitut Oberwolfach Report No. 41/2018 DOI: 10.4171/OWR/2018/41 Scaling Limits in Models of Statistical Mechanics Organised by Dmitry Ioffe, Haifa Gady Kozma, Rehovot Fabio Toninelli, Lyon 9 September – 15 September 2018 Abstract. This conference (part of a long running series) aims to cover the interplay between probability and mathematical statistical mechanics. Specific topics addressed during the 22 talks include: Universality and critical phenomena, disordered models, Gaussian free field (GFF), random planar graphs and unimodular planar maps, reinforced random walks and non-linear σ-models, non-equilibrium dynamics. Less stress is given to topics which have running series of Oberwolfach conferences devoted to them specifically, such as random matrices or integrable models and KPZ universality class. There were 50 participants, including 9 postdocs and graduate students, working in diverse intertwining areas of probability, statistical mechanics and mathematical physics. Subject classification: MSC: 60,82; IMU: 10,13. Introduction by the Organisers This workshop was a sequel to a MFO conference, by the same organizers, which took place in 2015. More broadly, it is a sequel to MFO conferences in 2006, 2009 and 2012, organised by Ken Alexander, Marek Biskup, Remco van der Hofstad and Vladas Sidoravicius. The main focus of the conference remained on probabilistic and analytic methods of non-integrable statistical mechanics. With respect to the previous editions, greater emphasis was put on statistical mechanics models on groups and general graphs, as a lot has happened in this arena recently. The list of 50 participants reflects our attempts to maintain an optimal balance between diverse fields, leading experts and promising young researchers.
    [Show full text]
  • MCMC Learning (Slides)
    Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions MCMC Learning Varun Kanade Elchanan Mossel UC Berkeley UC Berkeley August 30, 2013 Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions Outline Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions Uniform Distribution Learning • Unknown target function f : {−1; 1gn ! {−1; 1g from some class C • Uniform distribution over {−1; 1gn • Random Examples: Monotone Decision Trees [OS06] • Random Walk: DNF expressions [BMOS03] • Membership Query: DNF, TOP [J95] • Main Tool: Discrete Fourier Analysis X Y f (x) = f^(S)χS (x); χS (x) = xi S⊆[n] i2S • Can utilize sophisticated results: hypercontractivity, invariance, etc. • Connections to cryptography, hardness, de-randomization etc. • Unfortunately, too much of an idealization. In practice, variables are correlated. Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions Markov Random Fields • Graph G = ([n]; E). Each node takes some value in finite set A. n • Distribution over A : (for φC non-negative, Z normalization constant) 1 Y Pr((σ ) ) = φ ((σ ) ) v v2[n] Z C v v2C clique C Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions Markov Random Fields • MRFs widely used in vision, computational biology, biostatistics etc. • Extensive Algorithmic Theory for sampling from MRFs, recovering parameters and structures • Learning Question: Given f : An ! {−1; 1g. (How) Can we learn with respect to MRF distribution? • Can we utilize the structure of the MRF to aid in learning? Uniform Distribution Learning Markov Random Fields Harmonic Analysis Experiments and Questions Learning Model • Let M be a MRF with distribution π and f : An ! {−1; 1g the target function • Learning algorithm gets i.i.d.
    [Show full text]
  • Random and Out-Of-Equilibrium Potts Models Christophe Chatelain
    Random and Out-of-Equilibrium Potts models Christophe Chatelain To cite this version: Christophe Chatelain. Random and Out-of-Equilibrium Potts models. Statistical Mechanics [cond- mat.stat-mech]. Université de Lorraine, 2012. tel-00959733 HAL Id: tel-00959733 https://tel.archives-ouvertes.fr/tel-00959733 Submitted on 15 Mar 2014 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Habilitation `aDiriger des Recherches Mod`eles de Potts d´esordonn´eset hors de l’´equilibre Christophe Chatelain Soutenance publique pr´evue le 17 d´ecembre 2012 Membres du jury : Rapporteurs : Werner Krauth Ecole´ Normale Sup´erieure, Paris Marco Picco Universit´ePierre et Marie Curie, Paris 6 Heiko Rieger Universit´ede Saarbr¨ucken, Allemagne Examinateurs : Dominique Mouhanna Universit´ePierre et Marie Curie, Paris 6 Wolfhard Janke Universit´ede Leipzig, Allemagne Bertrand Berche Universit´ede Lorraine Institut Jean Lamour Facult´edes Sciences - 54500 Vandœuvre-l`es-Nancy Table of contents 1. Random and Out-of-Equililibrium Potts models 4 1.1.Introduction................................. 4 1.2.RandomPottsmodels .......................... 6 1.2.1.ThepurePottsmodel ......................... 6 1.2.1.1. Fortuin-Kasteleyn representation . 7 1.2.1.2. From loop and vertex models to the Coulomb gas .
    [Show full text]
  • Markov Random Fields: – Geman, Geman, “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images”, IEEE PAMI 6, No
    MarkovMarkov RandomRandom FieldsFields withwith ApplicationsApplications toto MM--repsreps ModelsModels Conglin Lu Medical Image Display and Analysis Group University of North Carolina, Chapel Hill MarkovMarkov RandomRandom FieldsFields withwith ApplicationsApplications toto MM--repsreps ModelsModels Outline: Background; Definition and properties of MRF; Computation; MRF m-reps models. MarkovMarkov RandomRandom FieldsFields Model a large collection of random variables with complex dependency relationships among them. MarkovMarkov RandomRandom FieldsFields • A model based approach; • Has been applied to a variety of problems: - Speech recognition - Natural language processing - Coding - Image analysis - Neural networks - Artificial intelligence • Usually used within the Bayesian framework. TheThe BayesianBayesian ParadigmParadigm X = space of the unknown variables, e.g. labels; Y = space of data (observations), e.g. intensity values; Given an observation y∈Y, want to make inference about x∈X. TheThe BayesianBayesian ParadigmParadigm Prior PX : probability distribution on X; Likelihood PY|X : conditional distribution of Y given X; Statistical inference is based on the posterior distribution PX|Y ∝ PX •PY|X . TheThe PriorPrior DistributionDistribution • Describes our assumption or knowledge about the model; • X is usually a high dimensional space. PX describes the joint distribution of a large number of random variables; • How do we define PX? MarkovMarkov RandomRandom FieldsFields withwith ApplicationsApplications toto MM--repsreps ModelsModels Outline: 9 Background; Definition and properties of MRF; Computation; MRF m-reps models. AssumptionsAssumptions •X = {Xs}s∈S, where each Xs is a random variable; S is an index set and is finite; • There is a common state space R:Xs∈R for all s ∈ S; | R | is finite; • Let Ω = {ω=(x , ..., x ): x ∈ , 1≤i≤N} be s1 sN si R the set of all possible configurations.
    [Show full text]
  • Anomaly Detection Based on Wavelet Domain GARCH Random Field Modeling Amir Noiboar and Israel Cohen, Senior Member, IEEE
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, VOL. 45, NO. 5, MAY 2007 1361 Anomaly Detection Based on Wavelet Domain GARCH Random Field Modeling Amir Noiboar and Israel Cohen, Senior Member, IEEE Abstract—One-dimensional Generalized Autoregressive Con- Markov noise. It is also claimed that objects in imagery create a ditional Heteroscedasticity (GARCH) model is widely used for response over several scales in a multiresolution representation modeling financial time series. Extending the GARCH model to of an image, and therefore, the wavelet transform can serve as multiple dimensions yields a novel clutter model which is capable of taking into account important characteristics of a wavelet-based a means for computing a feature set for input to a detector. In multiscale feature space, namely heavy-tailed distributions and [17], a multiscale wavelet representation is utilized to capture innovations clustering as well as spatial and scale correlations. We periodical patterns of various period lengths, which often ap- show that the multidimensional GARCH model generalizes the pear in natural clutter images. In [12], the orientation and scale casual Gauss Markov random field (GMRF) model, and we de- selectivity of the wavelet transform are related to the biological velop a multiscale matched subspace detector (MSD) for detecting anomalies in GARCH clutter. Experimental results demonstrate mechanisms of the human visual system and are utilized to that by using a multiscale MSD under GARCH clutter modeling, enhance mammographic features. rather than GMRF clutter modeling, a reduced false-alarm rate Statistical models for clutter and anomalies are usually can be achieved without compromising the detection rate. related to the Gaussian distribution due to its mathematical Index Terms—Anomaly detection, Gaussian Markov tractability.
    [Show full text]
  • Theory of Continuum Percolation I. General Formalism
    Theory of continuum percolation I. General formalism Alon Drory Dipartimento di Fisica, Universit´a La Sapienza Piazzale Aldo Moro 2, Roma 00187, Italy Abstract The theoretical basis of continuum percolation has changed greatly since its beginning as little more than an analogy with lattice systems. Nevertheless, there is yet no comprehensive theory of this field. A ba- sis for such a theory is provided here with the introduction of the Potts fluid, a system of interacting s-state spins which are free to move in the continuum. In the s → 1 limit, the Potts magnetization, suscepti- bility and correlation functions are directly related to the percolation probability, the mean cluster size and the pair-connectedness, respec- tively. Through the Hamiltonian formulation of the Potts fluid, the standard methods of statistical mechanics can therefore be used in the continuum percolation problem. arXiv:cond-mat/9606195v1 26 Jun 1996 1 1 Introduction The theoretical basis of continuum percolation [1] changed drastically during the 1970’s. In their seminal 1970 paper, Scher and Zallen [2] considered continuum percolation as an extension of lattice models. Noting that the critical volume φc is approximately universal, i. e., essentially independent of the lattice structure, they suggested it might be carried over into continuum systems. Such a view of the continuum as the representation of what is lattice- independent sits well with the ideas of the renormalization group where the continuum often represents merely a scale at which the underlying lattice blurs and vanishes. Yet continuum percolation turned out to be much richer than suggested by this conception.
    [Show full text]
  • CFT Interpretation of Merging Multiple SLE Traces
    CFT Interpretation of Merging Multiple SLE Traces Annekathrin Muller-Lohmann¨ ∗ Institut f¨ur theoretische Physik University of Hannover Appelstraße 2 D-30167 Hannover, Germany November 1, 2018 Abstract In this paper we give a physical interpretation of the probability of a Stochastic Lowner¨ Evolution (SLE) trace approaching a marked point in the upper half plane, e. g. on another trace. Our approach is based on the concept of fusion of boundary with bulk or other boundary fields in Conformal Field Theory (CFT). In this context we also state a proposal how the results can be extended to situations that happen not sufficiently far away from the boundary. Contents 1 Introduction 2 1.1 Motivation .............................. 2 1.2 Outline ................................ 3 2 Basic Definitions and Notations 3 2.1 SingleSLE .............................. 3 2.2 MultipleSLE ............................. 4 2.3 BoundaryCFTRevisited ...................... 5 2.4 SLE Martingales and Physical Quantities in BCFT . 7 2.5 FusionandtheOPEinCFT .................... 10 3 ProbabilitiesinBCFTandSLE 11 arXiv:0711.3165v1 [math-ph] 20 Nov 2007 3.1 Partition Functions and Probabilities in BCFT . 11 3.2 The SLE Probability of Intersecting a Disc . 12 4 TheEffectofFusionontheScalingProperties 13 4.1 TheL¨owner EquationDifferential Operators. 13 4.2 ThePurelyBoundaryDifferentialOperators. 14 5 Interpretation of Merging multiple SLE traces 15 5.1 SLE Traces Visiting a Point in the Upper Half Plane . 15 5.2 SLETracesMerging ......................... 17 5.3 TheAngularDependency . 18 ∗[email protected] 6 MultipleSLEasMartingaleWeightedSLE 19 6.1 The Associated Martingale Mt ................... 19 6.2 Probability Interpretation for Mt .................. 20 6.3 Fusion in the Associated Martingale . 21 7 Discussion 22 A Appendix: How to Compute “Fused” Differential Operators 23 1 Introduction 1.1 Motivation Stochastic Lowner¨ Evolutions (SLE) as introduced by O.
    [Show full text]
  • A Novel Approach for Markov Random Field with Intractable Normalising Constant on Large Lattices
    A novel approach for Markov Random Field with intractable normalising constant on large lattices W. Zhu ∗ and Y. Fany February 19, 2018 Abstract The pseudo likelihood method of Besag (1974), has remained a popular method for estimating Markov random field on a very large lattice, despite various documented deficiencies. This is partly because it remains the only computationally tractable method for large lattices. We introduce a novel method to estimate Markov random fields defined on a regular lattice. The method takes advantage of conditional independence structures and recur- sively decomposes a large lattice into smaller sublattices. An approximation is made at each decomposition. Doing so completely avoids the need to com- pute the troublesome normalising constant. The computational complexity arXiv:1601.02410v1 [stat.ME] 11 Jan 2016 is O(N), where N is the the number of pixels in lattice, making it computa- tionally attractive for very large lattices. We show through simulation, that the proposed method performs well, even when compared to the methods using exact likelihoods. Keywords: Markov random field, normalizing constant, conditional indepen- dence, decomposition, Potts model. ∗School of Mathematics and Statistics, University of New South Wales, Sydney 2052 Australia. Communicating Author Wanchuang Zhu: Email [email protected]. ySchool of Mathematics and Statistics, University of New South Wales, Sydney 2052 Australia. Email [email protected]. 1 1 Introduction Markov random field (MRF) models have an important role in modelling spa- tially correlated datasets. They have been used extensively in image and texture analyses ( Nott and Ryden´ 1999, Hurn et al. 2003), image segmentation (Pal and Pal 1993, Van Leemput et al.
    [Show full text]