• RRP: £59.99
  • You Save: £6.00 (10%)
FREE Delivery in the UK.
Only 1 left in stock (more on the way).
Dispatched from and sold by Amazon. Gift-wrap available.
Computer Vision: Models, ... has been added to your Basket
+ £2.80 UK delivery
Used: Like New | Details
Condition: Used: Like New
Comment: New, stamped 'damaged' to ISBN page: corners slightly bumped, spine slightly bumped, cover scuffed. No-hassle refunds are always available if your book is not as expected. In stock here - same-day midday dispatch from England.
Have one to sell?
Flip to back Flip to front
Listen Playing... Paused   You're listening to a sample of the Audible audio edition.
Learn more
See all 2 images

Computer Vision: Models, Learning, and Inference Hardcover – 18 Jun 2012

5 out of 5 stars 1 customer review

See all formats and editions Hide other formats and editions
Amazon Price
New from Used from
Kindle Edition
"Please retry"
"Please retry"
£46.44 £32.99
Note: This item is eligible for click and collect. Details
Pick up your parcel at a time and place that suits you.
  • Choose from over 13,000 locations across the UK
  • Prime members get unlimited deliveries at no additional cost
How to order to an Amazon Pickup Location?
  1. Find your preferred location and add it to your address book
  2. Dispatch to this address when you check out
Learn more
£53.99 FREE Delivery in the UK. Only 1 left in stock (more on the way). Dispatched from and sold by Amazon. Gift-wrap available.

Frequently Bought Together

  • Computer Vision: Models, Learning, and Inference
  • +
  • Computer Vision: Algorithms and Applications (Texts in Computer Science)
  • +
  • Multiple View Geometry in Computer Vision Second Edition
Total price: £180.67
Buy the selected items together

Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.

  • Apple
  • Android
  • Windows Phone

To get the free app, enter your e-mail address or mobile phone number.

Product details

  • Hardcover: 598 pages
  • Publisher: Cambridge University Press (18 Jun. 2012)
  • Language: English
  • ISBN-10: 1107011795
  • ISBN-13: 978-1107011793
  • Product Dimensions: 17.7 x 2.8 x 25.3 cm
  • Average Customer Review: 5.0 out of 5 stars  See all reviews (1 customer review)
  • Amazon Bestsellers Rank: 372,262 in Books (See Top 100 in Books)
  • See Complete Table of Contents

Product Description


'Computer vision and machine learning have 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

'This book addresses the fundamentals of how we make progress in this challenging and exciting field. I look forward to many decades with [this book] on my shelf, or indeed, I suspect, open on my desktop.' Andrew Fitzgibbon, from the Foreword

'Prince's magnum opus provides a fully probabilistic framework for understanding modern computer vision. With straightforward descriptions, insightful figures, example applications, exercises, background mathematics, and pseudocode, this book is self-contained and has all that is needed to explore this fascinating discipline.' Roberto Cipolla, University of Cambridge

'The author's goal, as stated in the preface, is to provide a book that focuses on the models involved, and I think the book has succeeded in doing that. I learned quite a bit and would recommend this text highly to the motivated, mathematically mature reader.' Jeffrey Putnam, Computing Reviews

Book Description

With minimal prerequisites, the book starts from the basics of probability and model fitting and works up to real examples that the reader can implement and modify to build useful vision systems. Primarily meant for advanced undergraduate and graduate students, the detailed methodological presentation will also be useful for practitioners of computer vision.

See all Product Description

Inside This Book

(Learn More)
Browse Sample Pages
Front Cover | Excerpt | Index
Search inside this book:

Customer Reviews

5.0 out of 5 stars
5 star
4 star
3 star
2 star
1 star
See the customer review
Share your thoughts with other customers

Top Customer Reviews

Format: Hardcover Verified Purchase
This book is a breath of fresh air in the machine learning field. Everything is being presented from a Bayesian point of view. Usual simple ML algorithms that are frequently just thrown out there in an encyclopedic list-like manner in other books, together with more advanced models, and no connection/thread is exposed between them, here are presented using a Bayesian hierarchical model formulation, that is used to explain how and WHY and WHERE several models work, and how they are connected. Each chapter ends with several applications and results of the models in the field of Machine Vision. The "pure" machine vision part of the book is a little more standard, but equally "fluidly" presented. Oh and did I mention that the graphs and figures are uber-explanatory? All in all, a great machine vision book, and even greater machine learning book.
Comment 2 of 2 people found this helpful. Was this review helpful to you? Yes No Sending feedback...
Thank you for your feedback.
Sorry, we failed to record your vote. Please try again
Report abuse

Most Helpful Customer Reviews on Amazon.com (beta)

Amazon.com: HASH(0x9146a270) out of 5 stars 19 reviews
22 of 24 people found the following review helpful
HASH(0x9166ecb4) out of 5 stars Pretty easy, considering... 19 July 2012
By GBrostow - Published on Amazon.com
Format: Hardcover
I teach the Machine Vision class at UCL from this textbook (for advanced undergrads + grad students). It's the same class Simon Prince used to teach, so we cover the whole book (ok, skipping a few bits and one whole chapter) in 11 weeks of lectures. The two main reasons I like it are 1) its unified explanation of all the major topics, and 2) the extra materials for students and teachers (free online):

1) Everything is explained in terms of (essentially) the same probabilistic models. That probably doesn't sound seriously exciting, but imagine the alternative of having to learn all the complicated math for doing object recognition, camera pose estimation, tracking, pose regression, shape modeling etc, but each one using ITS OWN notation and completely different "slices" of applied machine learning! It was hard to learn, and very hard to teach. Here, almost everything is consistent (even Structure from Motion is somehow made to fit the same notation). So if you can survive Chapters 2-4 (spread gently over ~40 pages), you'll likely absorb the rest without the usual agony.

2) On the book's website, Prince has built a collection of slides (pretty plain, but good), and an AMAZING (still evolving?) 75-page booklet of algorithms. While the textbook is accurate, there's normally quite some head-scratching to turn the equations into code. You obviously still have to write the code yourself, but now you have a recipe! It's clear the book would be unreadable if each algorithm's details had been included in the main text, so this seems like an ok compromise. This really could be the next "Numerical Recipes in C," but for vision :) There are interesting links to other people's data and code online too, and solutions to some of the problem sets.

My one request would be for the Algorithm booklet to be part of (or just link to) a Matlab-Central-like forum, where people could help each other work through the implementation details, and suggest improvements and tricks (for different problem domains or when the data is too big for memory). When computer-savvy biologists etc. need help with some automated-monitoring project, I sometimes hand them a vision research paper, and point them to the relevant chapter in this book to better understand it.
8 of 10 people found the following review helpful
HASH(0x9166ed08) out of 5 stars An awesome book for Machine Vision! 5 Aug. 2012
By Arun Sarath Nair - Published on Amazon.com
Format: Hardcover
The Computer Vision: Models, Learning, and Inference is an excellent book for learning Vision from an Machine Learning perspective. The first few chapters gives you a firm grounding in basic Machine Learning concepts. The language is easy to understand. One of the unique things about this book is that the pictures accompanying complex algorithms gives you an easy way of understanding what each step in the algorithm does. The book makes it very easy to understand the Bayesian concepts and also to visualize them. Though it does not cover all the state-of-the art methods, it gives a firm grounding in the basics and gives you the confidence to explore more complex algorithms.

This book has been instrumental in helping me though a very grueling masters course in Machine Learning at University College London(UCL). It has been responsible for me developing a passion for Vision as it gave me the courage to explore the state-of-the art algorithms and try to make them better. A definite buy for someone looking to do Vision but lacks the knowledge and confidence in dealing with the mathematics behind it.
8 of 10 people found the following review helpful
HASH(0x914eac3c) out of 5 stars Great book 30 Oct. 2012
By Zdenek Kalal - Published on Amazon.com
Format: Hardcover Verified Purchase
Computer vision is very active field with increasing number of papers being published every year. While the new papers slowly push the knowledge boundary forward, it is often difficult to separate useful information from noise. At the same time, only a few core principles keep repeating over and over again. This book is absolutely brilliant at presenting these principles and mapping them to the already discovered applications in computer vision. This is a connection that I have not found in any other computer vision book available. A connection that allowed me to better understand my own work and to discover new ways forward. I humbly recommend to buy this book to any person seriously interested in computer vision.

Dr. Zdenek Kalal
TLD Vision
4 of 5 people found the following review helpful
HASH(0x917a1bac) out of 5 stars Beautiful book and explaining concepts others take for granted 29 May 2014
By Anne van Rossum - Published on Amazon.com
Format: Hardcover
This book I cannot recommend more! It is absolutely of super high quality compared to many other text books (and I buy a lot of them).

Just one example, Simon's explanation of the Expectation-Maximization algorithm in which he shows in two nice graphs how the algorithm step-wise improves its estimation. Brilliant!

I'm a critical reviewer, but this author knows how to combine in-depth exposition with proper visualizations. He is not just having some exposition of the material at hand, he has the reader in mind, and tries to answer questions that pop up in your head. His emphasis on machine learning makes it also a very coherent book. You'll enjoy it!
4 of 5 people found the following review helpful
HASH(0x91a771ec) out of 5 stars Prince actually wants the student to understand him, and that shows 9 Dec. 2014
By lisprambo - Published on Amazon.com
Format: Hardcover
This book by Prince is simply the best book I have ever read on machine learning. Forget Bishop, Murphy, Barber, Hastie and others. Some of those are actually quite good books, but Prince supersedes them all. No-one explains the models and algorithms as clearly as he does. And suddenly, machine learning appears actually quite understandable.
Were these reviews helpful? Let us know