Markov Random Field Modeling in Computer Vision

1. Front Matter

   Pages I-XVI

   PDF

2. Introduction

   • S. Z. Li

   Pages 1-35

3. Low Level MRF Models

   • S. Z. Li

   Pages 37-61

4. Discontinuities in MRFs

   • S. Z. Li

   Pages 63-81

5. Discontinuity-Adaptivity Model and Robust Estimation

   • S. Z. Li

   Pages 83-99

6. High Level MRF Models

   • S. Z. Li

   Pages 101-130

7. MRF Parameter Estimation

   • S. Z. Li

   Pages 131-156

8. Parameter Estimation in Optimal Object Recognition

   • S. Z. Li

   Pages 157-184

9. Minimization — Local Methods

   • S. Z. Li

   Pages 185-206

10. Minimization — Global Methods

    • S. Z. Li

    Pages 207-230

11. Back Matter

    Pages 231-264

    PDF

Markov random field (MRF) modeling provides a basis for the characterization of contextual constraints on visual interpretation and enables us to develop optimal vision algorithms systematically based on sound principles. This book presents a comprehensive study on using MRFs to solve computer vision problems, covering the following parts essential to the subject: introduction to fundamental theories, formulations of various vision models in the MRF framework, MRF parameter estimation, and optimization algorithms. Various MRF vision models are presented in a unified form, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This book is an excellent reference for researchers working in computer vision, image processing, pattern recognition and applications of MRFs. It is also suitable as a text for advanced courses in the subject.

• Markov Random Field
• Markov random field theory
• algorithms
• computer vision
• image processing
• image restoration
• pattern
• pattern recognition

• School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

  S. Z. Li

Policies and ethics