This detailed book presents a comprehensive study on the use of Markov Random Fields for solving computer vision problems. Various vision models are presented, and this third edition includes the most recent advances with new and expanded sections.

Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms systematically when used with optimization principles. This book presents a comprehensive study on the use of MRFs for solving computer vision problems. Various vision models are presented in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This third edition includes the most recent advances and has new and expanded sections on topics such as: Bayesian Network; Discriminative Random Fields; Strong Random Fields; Spatial-Temporal Models; Learning MRF for Classification. This book is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition and applications of MRFs. It is also suitable as a text for advanced courses in these areas.

Comprehensive coverage over a broad range of Markov Random Field Theory Provides the most recent advances in the field Includes supplementary material: sn.pub/extras

Inhalt
Mathematical MRF Models.- Low-Level MRF Models.- High-Level MRF Models.- Discontinuities in MRF#x0027;s.- MRF Model with Robust Statistics.- MRF Parameter Estimation.- Parameter Estimation in Optimal Object Recognition.- Minimization Local Methods.- Minimization Global Methods.