Book Cover

Computer Vision:  Models, Learning, and Inference

Simon J.D. Prince

A new machine vision textbook with 600 pages, 359 colour figures, 201 exercises and 1060 associated Powerpoint slides

Published by Cambridge University Press

NOW AVAILABLE from Amazon and other booksellers.


Reviews

"Simon Prince’s wonderful book presents a principled model-based approach to computer vision that unifies disparate algorithms, approaches, and topics under the guiding principles of probabilistic models, learning, and efficient inference algorithms.  A deep understanding of this approach is essential to anyone seriously wishing to master the fundamentals of computer vision and to produce state-of-the art results on real-world problems.  I highly recommend this book to both beginning and seasoned students and practitioners as an indispensable guide to the mathematics and models that underlie modern approaches to computer vision."
Richard Szeliski, Microsoft Research

"Computer vision and machine learning have gotten married and this book is their child. It gives the machine learning fundamentals you need to participate in current computer vision research. It's really a beautiful book, showing everything clearly and intuitively. I had lots of 'aha!' moments as I read through the book. This is an important book for computer vision researchers and students, and I look forward to teaching from it."
William T. Freeman, Massachusetts Institute of Technology

"With clarity and depth, this book introduces the mathematical foundations of probabilistic models for computer vision, all with well-motivated, concrete examples and applications. Most modern computer vision texts focus on visual tasks; Prince's beautiful new book is natural complement, focusing squarely on fundamental techniques, emphasizing models and associated methods for learning and inference. I think every serious student and researcher will find this book valuable. I've been using draft chapters of this remarkable book in my vision and learning courses for more than two years. It will remain a staple of mine for years to come."
David J. Fleet, University of Toronto

Further reviews at

For students

For teachers

Errata

Please mail errata to s.prince(at)cs.ucl.ac.uk.  I will incorporate them into the next printing of the book and add your name to the list of acknowledgements. 

Citation Information

@BOOK{princeCVMLI2012,
author = {Prince, S.J.D.},
title= {{Computer Vision: Models Learning and Inference}},
publisher = {{Cambridge University Press}},
year = 2012}

Resources by chapter

Below are listed a number of additional resources that complement the data in each chapter. These include links to project pages, other descriptions of the same material and useful datasets.  Feel free to mail me to suggest other useful material.

Chapter 1 - Introduction

Chapter 2 - Introduction to probability

Chapter 3 - Common probability distributions

Chapter 4 - Fitting probability models

Chapter 5 - The normal distribution

Chapter 6 - Learning and inference in vision

Chapter 7 - Modeling complex data densities

Chapter 8 - Regression models

Chapter 9 - Classification models

Chapter 10 - Graphical models

Chapter 11 - Models for chains and trees

Chapter 12 - Models for grids

Chapter 13 - Image preprocessing and feature extraction

Chapter 14 - The pinhole camera

Chapter 15 - Models for transformations

Chapter 16 - Multiple cameras

Chapter 17 - Models for shape

Chapter 18 - Models for style and identity

Chapter 19 - Temporal models

Chapter 20 - Models for visual words

Appendix B - Optimization

Appendix C - Linear algebra