Pub. Date:
MIT Press
Markov Random Fields for Vision and Image Processing

Markov Random Fields for Vision and Image Processing


Current price is , Original price is $70.0. You

Temporarily Out of Stock Online

Please check back later for updated availability.


State-of-the-art research on MRFs, successful MRF applications, and advanced topics for future study.

This volume demonstrates the power of the Markov random field (MRF) in vision, treating the MRF both as a tool for modeling image data and, utilizing recently developed algorithms, as a means of making inferences about images. These inferences concern underlying image and scene structure as well as solutions to such problems as image reconstruction, image segmentation, 3D vision, and object labeling. It offers key findings and state-of-the-art research on both algorithms and applications.

After an introduction to the fundamental concepts used in MRFs, the book reviews some of the main algorithms for performing inference with MRFs; presents successful applications of MRFs, including segmentation, super-resolution, and image restoration, along with a comparison of various optimization methods; discusses advanced algorithmic topics; addresses limitations of the strong locality assumptions in the MRFs discussed in earlier chapters; and showcases applications that use MRFs in more complex ways, as components in bigger systems or with multiterm energy functions. The book will be an essential guide to current research on these powerful mathematical tools.

Product Details

ISBN-13: 9780262015776
Publisher: MIT Press
Publication date: 07/22/2011
Series: The MIT Press
Pages: 472
Product dimensions: 7.10(w) x 9.10(h) x 1.10(d)
Age Range: 18 Years

About the Author

Andrew Blake is Managing Director of Microsoft Research Cambridge (UK), where he has led the Computer Vision Research Group since 1999.

Andrew Blake is Managing Director of Microsoft Research Cambridge (UK), where he has led the Computer Vision Research Group since 1999.

Alan Yuille is Professor in the Department of Statistics, University of California, Los Angeles.

Yair Weiss is Senior Lecturer in the School of Computer Science and Engineering at The Hebrew University of Jerusalem.

Table of Contents

1 Introduction to Markov Random Fields Andrew Blake Pushmeet Kohli 1

I Algorithms for Inference of MAP Estimates for MRFs 29

2 Basic Graph Cut Algorithms Yuri Boykov Vladimir Kolmogorov 31

3 Optimizing Multilabel MRFs Using Move-Making Algorithms Yuri Boykov Olga Veksler Ramin Zabih

4 Optimizing Multilabel MRFs with Convex and Truncated Convex Priors Hiroshi Ishikawa Olga Veksler

5 Loopy Belief Propagation, Mean Field Theory, and Bethe Approximations Alan Yuille 77

6 Linear Programming and Variants of Belief Propagation Yair Weiss Chen Yanover Talya Meltzer 95

II Applications of MRFs, Including Segmentation 109

7 Interactive Foreground Extraction: Using Graph Cut Carsten Rother Vladimir Kolmogorov Yuri Boykov Andrew Blake 111

8 Continuous-Valued MRF for Image Segmentation Dheeraj Singaraju Leo Grady Ali Kernal Sinop René Vidal 127

9 Bilayer Segmentation of Video Antonio Criminisi Geoffrey Cross Andrew Blake Vladimir Kolmogorov 143

10 MRFs for Superresolution and Texture Synthesis William T. Freeman Ce Liu 155

11 A Comparative Study of Energy Minimization Methods for MRFs Richard Szeliski Ramin Zabih Daniel Scharstein Olga Veksler Vladimir Kolmogorov Aseem Agarwala Marshall F. Tappen Carsten Rother 167

III Further Topics: Inference, Parameter Learning, and Continuous Models 183

12 Convex Relaxation Techniques for Segmentation, Stereo, and Multiview Reconstruction Daniel Cremers Thomas Pock Kalin Kolev Antonin Chambolle 185

13 Learning Parameters in Continuous-Valued Markov Random Fields Marshall F. Tappen 201

14 Message Passing with Continuous Latent Variables Michael Isard 215

15 Learning Large-Margin Random Fields Using Graph Cuts Martin Szummer Pushmeet Kohli Derek Hoiem 233

16 Analyzing Convex Relaxations for MAP Estimation M. Pawan Kumar Vladimir Kolmogorov Philip H. S. Torr 249

17 MAP Inference by Fast Primal-Dual Linear Programming Nikos Komodakis 263

18 Fusion-Move Optimization for MRFs with an Extensive Label Space Victor Lempitsky Carsten Rother Stefan Roth Andrew Blake 281

IV Higher-Order MRFs and Global Constraints 295

19 Field of Experts Stefan Roth Michael J. Black 297

20 Enforcing Label Consistency Using Higher-Order Potentials Pushmeet Kohli Lubor Ladicky Philip H. S. Torr 311

21 Exact Optimization for Markov Random Fields with Nonlocal Parameters Victor Lempitsky Andrew Blake Carsten Rother 329

22 Graph Cut-Based Image Segmentation with Connectivity Priors Sara Vicente Vladimir Kolmogorov Carsten Rother 347

V Advanced Applications of MRFs 363

23 Symmetric Stereo Matching for Occlusion Handling Jian Sun Yin Li Sing Bing Kang Heung-Yeung Shum 365

24 Steerable Random Fields for Image Restoration Stefan Roth Michael J. Black 377

25 Markov Random Fields for Object Detection John Winn Jamie Shotton 389

26 SIFT Flow: Dense Correspondence across Scenes and Its Applications Ce Liu Jenny Yuen Antonio Torralba William T. Freeman 405

27 Unwrap Mosaics: A Model for Deformable Surfaces in Video Alex Rav-Acha Pushmeet Kohli Carsten Rother Andrew Fitzgibbon 419

Bibliography 433

Contributors 457

Index 459

Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews