Markov Random Field modeling, inference & learning in computer vision & image understanding: A survey

• Published in: Computer vision and image understanding Vol. 117; no. 11; pp. 1610 - 1627
• Main Authors: Wang, Chaohui, Komodakis, Nikos, Paragios, Nikos
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.11.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Computer Science; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Computer vision; Computer Vision and Pattern Recognition; Discrete optimization; Exact sciences and technology; Graphical models; Inference; Information retrieval. Graph; Learning; Magnetorheological fluids; MAP inference; Markov models; Markov Random Fields; MRF learning; MRFs; Pattern recognition. Digital image processing. Computational geometry; Software; Theoretical computing; Visual perception; Discrete optimization; Graphical models; MAP inference; MRF learning; Markov Random Fields; MRFs; Computer vision; Image interpretation; Inference; Review; Markov model; Modeling; Graphical interface; Problem solving; Discrete programming; Graph method; MAP Inference; MRF Learning; Graphical Models; Discrete Optimization
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2013.07.004

•We present a comprehensive survey of Markov Random Fields (MRFs) in computer vision.•This is a compact and informative summary of literature in the development of MRFs.•Techniques in MRF modeling, inference and learning are included.•It helps readers rapidly gain a global view and better understanding for using MRFs.•It begins with basic notions and then goes onto cover important recent development. In this paper, we present a comprehensive survey of Markov Random Fields (MRFs) in computer vision and image understanding, with respect to the modeling, the inference and the learning. While MRFs were introduced into the computer vision field about two decades ago, they started to become a ubiquitous tool for solving visual perception problems around the turn of the millennium following the emergence of efficient inference methods. During the past decade, a variety of MRF models as well as inference and learning methods have been developed for addressing numerous low, mid and high-level vision problems. While most of the literature concerns pairwise MRFs, in recent years we have also witnessed significant progress in higher-order MRFs, which substantially enhances the expressiveness of graph-based models and expands the domain of solvable problems. This survey provides a compact and informative summary of the major literature in this research topic.