The use of Markov Random Fields as models of texture

Hassner, M.; Sklansky, Jack

doi:10.1016/0146-664x(80)90019-2

Cited by 148 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, visual realism or the similarity between synthetic and training textures types is achieved in many cases by bringing their size-independent sufficient signal statistics closer together for a particular MGRF model (see, e.g., [3,12,18]). After identifying a model by a training image, well-known Markov Chain Monte Carlo (MCMC) processes of pixel-wise stochastic relaxation or simulated annealing allow for generating images distributed in accord with the MGRF [3,18] or conforming eventually to the global maximum of the GPD [9], respectively. An alternative MCMC-based stochastic approximation process called controllable simulated annealing in [12,13] As a result of approaching selected signal statistics, synthetic textures are "homogenized" translation invariant counterparts of training images.…”

Section: Mgrf-based Texture Synthesis-by-analysismentioning

confidence: 99%

“…This avenue of investigations originated in the late seventies -early eighties [3,9,18] and persists up to the present. Each MGRF model relates image probabilities to explicit spatial geometry and quantitative strengths of statistical dependence or interactions between grey levels and/or region labels in sites (pixels) of an arithmetic lattice supporting the images.…”

Section: Introductionmentioning

confidence: 96%

“…Its translational invariance stems from a fixed neighborhood of a single pixel. Quantitative interaction strengths are given by Gibbs potential functions on a certain subset of cliques in the graph [5,18].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Texture Analysis by Accurate Identification of Simple Markovian Models

Gimel’farb

Farag

2005

Cybern Syst Anal

View full text Add to dashboard Cite

A more accurate identification (estimation of parameters) of simple Markov-Gibbs random field models of images results in a better segmentation of specific multimodal images and realistic synthesis of some types of natural textures. Identification algorithms for segmentation are based in part on a novel modification of an unsupervised learning algorithm published first in "Cybernetics and Systems Analysis" ("Kibernetika i Sistemnyi Analiz") almost four decades ago. A texture synthesis algorithm uses an identified model for selecting a characteristic geometric shape of and a placement grid for texture elements sampled from a training image utilized for the identification.

show abstract

Section: Mgrf-based Texture Synthesis-by-analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Texture Analysis by Accurate Identification of Simple Markovian Models

Gimel’farb

Farag

2005

Cybern Syst Anal

View full text Add to dashboard Cite

show abstract

“…Hence the algorithm discovers a neighbor in each run of the innermost loop and finds all the neighbors of a given node i in exactly i iterations of the outer loop. Set T (i ) = N (i ) 5:…”

Section: A Recursive Greedy Algorithmmentioning

confidence: 99%

Improved Greedy Algorithms for Learning Graphical Models

Ray

Sanghavi

Shakkottai

2015

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

We propose new greedy algorithms for learning the structure of a graphical model of a probability distribution, given samples drawn from the distribution. While structure learning of graphical models is a widely studied problem with several existing methods, greedy approaches remain attractive due to their low computational cost. The most natural greedy algorithm would be one which, essentially, adds neighbors to a node in sequence until stopping; it would do this for each node. While it is fast, simple and parallel, this naive greedy algorithm has the tendency to add non-neighbors that show high correlations with the given node. Our new algorithms overcome this problem in three different ways. The recursive greedy algorithm iteratively recovers the neighbors by running the greedy algorithm in an inner loop, but each time only adding the last added node to the neighborhood set. The second forward-backward greedy algorithm includes a node deletion step in each iteration that allows non-neighbors to be removed from the neighborhood set which may have been added in the previous steps. Finally, the greedy algorithm with pruning runs the greedy algorithm until completion and then removes all the incorrect neighbors. We provide both analytical guarantees and empirical performance for our algorithms. We show that in graphical models with strong non-neighbor interactions, our greedy algorithms can correctly recover the graph, whereas the previous greedy and convex optimization-based algorithms do not succeed.

show abstract

“…(16) is achieved by an extended Hebbian rule as follows: rji (k + 1) = rji (k) -qrji (k)xi (k) y, (k) = rji (')(I -P i (' 1 Y (' 1) (22) where 7 > 0 is a growing constant and xi and y j are outputs of sensory and cognitive neurons, respectively. By a structural adaptation, any connection from sensory neuron i to cognitive neuron j, wji(k) , can be formed by growth of an axon branch of neuron i and a dendrite of neuron j.…”

Section: Extended Hebbian Rule For Structural Adaptationmentioning

confidence: 99%

Applied Research in Uncertainty Modeling and Analysis

Attoh-Okine¹,

Ayyub²

2005

International Series in Intelligent Technologies

View full text Add to dashboard Cite

Other books in the series: Zirnrnermann, H.-J.; Tselentis, G.; van Someren, M.; Dounias, G. (Eds.):in Computational Intelligence and Learning Angstenberger, Lurisa: Dynamic Fuzzy Pattern Recognition with Applications to Finance and Engineering Jain, Lukhrni; De Wilde, Philippe (Eds.): Practical Applications of Computational Intelligence Techniques Teodorescu, H.-N.; Mlynek, D.; Kandel, A.; Zirnrnermann, H.-J. (Eds.): Intelligent Systems and Interfaces Verbruggen, H.B.; Zirnrnermann, Hans-Jiirgen; Babuska, Robert (Eds.): Fuzzy Algorithms for Control Teodorovic, Dusan, Vukadinovic, Katarina: Traffic Control and Transport Planning: Babuska, Robert: Fuzzy Modeling for Control: Ayyub, Bilal M.; Gupta, Madan M. (Eds.): Uncertainty Analysis in Engineering and Sciences Kacprzyk, J.; Nurmi, H.; Fedrizzi, M. (Eds.): Consensus under Fuzziness Sebastian, Hans-Jiirgen; Antonsson, Erik K. (Eds.): Fuzzy Sets in Engineering Design and Configuration

show abstract

The use of Markov Random Fields as models of texture

Cited by 148 publications

References 7 publications

Texture Analysis by Accurate Identification of Simple Markovian Models

Texture Analysis by Accurate Identification of Simple Markovian Models

Improved Greedy Algorithms for Learning Graphical Models

Applied Research in Uncertainty Modeling and Analysis

Contact Info

Product

Resources

About