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.

About the Author
Qiang Ji is in the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute, New York, USA

Reviews
"The book describes probabilistic graphical models in application to computer vision tasks. The theoretical concepts are accompanied by illustrative figures and algorithms in pseudocode. All the main categories of models are referred to. The applications range from image denoising and segmentation, object detection and tracking to 3D reconstruction and action recognition. It is a book that is valuable for theoreticians and practitioners alike." --zbMath/European Mathematical Society and the Heidelberg Academy of Sciences and Humanities



Book Information
ISBN 9780128034675
Author Qiang Ji
Format Hardback
Page Count 294
Imprint Academic Press Inc
Publisher Elsevier Science Publishing Co Inc
Weight(grams) 770g