## Markov random fields: theory and applicationThis book introduces the theory and applications of Markov Random Fields in image processing and computer vision. Modeling images through the local interaction of Markov models has resulted in useful algorithms for problems in texture analysis, image synthesis, image restoration, image segmentation, surface reconstruction and integration of low-level visual modules. All of the contributors are leading researchers from the United States and Europe. Presents statistical modeling of two- and three-dimensional images Includes Markov Random Fields, Gibbs Distribution, and Simulated Annealing Explains integration or fusion of images Covers image segmentation, texture analysis, and image restoration using MRF models of context Gives a systematic development of algorithms for image processing, analysis, and computer vision Presents parallel algorithms for image processing, analysis, and computer vision |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Stochastic Algorithms for Restricted Image Spaces | 39 |

Poggio T 447 Artificial Intelligence Laboratory and Center for Bio | 67 |

A Continuation Method for Image Estimation Using | 69 |

Copyright | |

22 other sections not shown

### Common terms and phrases

3D surface Analysis annealing algorithm approach approximation assume asymptotic autocovariances basis functions Bayesian boundary camera Chellappa classification clique functions Computer Vision constraints convergence corresponding cost function covariance D.B. Cooper defined denote density depth discontinuities disparity edge edge detection energy function equation Figure finite frame Gaussian Gaussian Random Fields Geman Gibbs distributions Gibbs Sampler given GMRF gradient graph IEEE IEEE Trans image interpretation image modeling Image Processing intensity interactions iterations labels lattice line process MAP estimation Markov chain Markov Random Fields matrix maximum likelihood method model-based MRF model neighbors noise object obtained optimization orientation parallel parameters parent texture patch Pattern photon pixel planar plane posterior prior probability problem properties reconstruction regions sample scene Section segmentation sequence shape shown in Fig simulated annealing spatial spectral Statistical stereo stochastic relaxation surface normal Theorem tion update values variables window zero

### References to this book

Handbook of Pattern Recognition & Computer Vision Chi-hau Chen,Louis-François Pau,Patrick Shen-pei Wang,Shen-pei Wang No preview available - 1999 |

Energy Minimization Methods in Computer Vision and Pattern ..., Volume 3 Mario Figueiredo,Josiane Zerubia,Anil K. Jain No preview available - 2001 |