5.0 out of 5 stars One of the BEST books I have ever read

A. · October 12, 2016

(function() { P.when('cr-A', 'ready').execute(function(A) { if(typeof A.toggleExpanderAriaLabel === 'function') { A.toggleExpanderAriaLabel('review_text_read_more', 'Read more of this review', 'Read less of this review'); } }); })(); .review-text-read-more-expander:focus-visible { outline: 2px solid #2162a1; outline-offset: 2px; border-radius: 5px; } My expertise is in signal-image-video processing, video compression, digital communications, and information theory. I have read many books in all the mentioned areas; Simon Prince's book is one of the best books I have ever read. The book is written beautifully and it is evident that Prince has spent a lot of time in writing the book; I really appreciate his efforts and wish we had more talented book authors like him.I had intermediate knowledge in machine learning and zero knowledge in computer vision when I started reading the Prince's book. All the material are presented in very well organized order. Pictures are excellent and some of them are really masterpiece! In introducing any new topic, the book first gives you a concise intuition about the topic and then presents the mathematical stuff beautifully. Another important aspect of the book is that it never leaves you in the middle of the mathematical arguments and takes you to the end; this is missing in almost all of the advanced-level book I have read. Notation is great and always consistent.I should mention that this book is not written for readers who are not familiar with estimation theory and machine learning. I believe the reader should have an intermediate knowledge in machine learning and estimation theory.

5.0 out of 5 stars Great book

Z.K. · October 30, 2012

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 KalalTLD Vision

5.0 out of 5 stars This book is my favorite when it comes to probability and computer vision

V.I. · May 29, 2015

This book is my favorite when it comes to probability and computer vision. Much better and more concise than Hartley and Zisserman and much more logically structures than R. Szelinski ones. Chapters 14-16 may be all you need to get a quick intro into Computer Vision. For me it helped to score a job at Google. Last but not least - very intuitive graphs and examples plus a great motivational task in the beginning of every chapter.

4.0 out of 5 stars Four Stars

h.a. · February 1, 2018

I recommend it for start.

5.0 out of 5 stars Excellent

m. · August 27, 2015

This book is filled with wonderfully intuitive explanations of key topics backed up by careful formal arguments. The author tells a very convincing Bayesian story about computer vision and makes a clear separation between the models driving the thinking and the concrete algorithmic techniques for realizing and evaluating those models.

5.0 out of 5 stars It's an excellent book, and view CV from a statistical view

R. · June 5, 2015

It's an excellent book, and view CV from a statistical view.But why I can't download the errata from the author's webpage.Is there any one can help me? e-mail: ryan153770@163.comThanks.

5.0 out of 5 stars Amazing coverage

r. · July 25, 2013

The most updated, lucid and complete machine vision book. I liked Trucco and Verri very much due to its completeness and simplicity. But since its kinda old now, this is the best in the market for both beginner and grads.

5.0 out of 5 stars Great book for both ML and Vision fields

P. · August 2, 2013

Not only this is a great vision book, but also it can be a great introduction to machine learning with applications far beyond vision. The figures make it super-easy to understand rather complex concepts. I highly recommend this book.

must have for computer vision

m.h. · February 26, 2014

(function() { P.when('cr-A', 'ready').execute(function(A) { if(typeof A.toggleExpanderAriaLabel === 'function') { A.toggleExpanderAriaLabel('review_text_read_more', 'Read more of this review', 'Read less of this review'); } }); })(); .review-text-read-more-expander:focus-visible { outline: 2px solid #2162a1; outline-offset: 2px; border-radius: 5px; } Very good for getting a bayesian background in computer vision. very nice visualisation and colorful pictures help understand the basic principles.

The book I have been waiting for on Vision

H. · September 4, 2012

If there is a better book out there on Computer Vision book I have yet to read it. I expect to see this included in a number of curriculums as required reading moving forward

Makes a technical subject accessible

A.C. · December 20, 2016

I'm taking the machine vision course that the author used to teach, and it relies heavily on the book. The field's theory-heavy nature had me worried to start with, but this book's clear exposition (mirrored in excellent slides), the extra-illustrative figures, and the neatly organised narrative have helped tremendously.At the risk of sounding like a fanboy, I really admire Simon Prince's clarity of thought. He breaks a complicated set of ideas down into manageable chunks that build on each other. Until the final chapters, it's something of an intro to machine learning with machine vision applications, and as such it's also helping me make sense of material in other ML-related courses.The better one's maths and stats, the easier it is to digest a technical subject, but I've found that my moderate background sufficient. In comparison to Szeliski's book, this one seems less advanced and gets you started, whereas the other delves deeper and is probably a good reference book for practitioners. Both are available on the authors' website, but I've found the money well spent - maybe my favourite textbook yet!

Eine prima Einführung in die Materie!

J. · July 21, 2013

Ich habe für meine Masterarbeit einen tiefer gehenden Einstieg in die Wahrscheinlichkeitsrechnung gesucht und wurde von diesem Buch nicht enttäuscht. Die erste Hälfte des Buches ist den Grundlagen der Wahrscheinlichkeitsrechnung gewidmet. Diese ist sehr ausführlich und verständlich geschrieben.Es folgt ein Einstieg in die wichtigsten Themen der Computer Vision. Es werden Grundlagen wie das Lochkameramodell sowie die wichtigsten state-of-the-art Themen (z.B. SIFT-Features, ...) behandelt. Ich habe diesen Teil auf Grund meiner Vorkenntnisse nur überflogen, er macht jedoch einen guten Eindruck auf mich. Die letzten Kapitel behandelt weiterführende Anwendungsmöglichkeiten, welche beide Themenkomplexe kombinieren.Mein persönliches Fazit: Wer einen guten Einstieg oder ein gutes Nachschlagewerk aus dem Bereich der probabilistischen Computer Vision sucht ist mit diesem Buch gut beraten. Es ist ausführlich und verständlich geschrieben und hat mir den Weg in das Thema geebnet.

Want to learn Bayesian modeling?

P.A. · May 15, 2013

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.