Probabilistic Graphical Models for Computer Vision.

Probabilistic Graphical Models for Computer Vision  introduces probabilistic graphical models (PGMs) for computer vision problems and teaches how to develop the PGM model from training data. This book discusses PGMs and their significance in the context of solving computer vision problems, giving the basic concepts, definitions and properties. It also provides a comprehensive introduction to well-established theories for different types of PGMs, including both directed and undirected PGMs, such as Bayesian Networks, Markov Networks and their variants.

Discusses PGM theories and techniques with computer vision examplesFocuses on well-established PGM theories that are accompanied by corresponding pseudocode for computer visionIncludes an extensive list of references, online resources and a list of publicly available and commercial softwareCovers computer vision tasks, including feature extraction and image segmentation, object and facial recognition, human activity recognition, object tracking and 3D reconstruction

1. Introduction 2. Probability Calculus 3. Directed Probabilistic Graphical Models 4. Undirected Probabilistic Graphical Models 5. PGM Applications in Computer Vision