18 of 18 people found the following review helpful
4.0 out of 5 stars
Good survey of specific machine vision techniques, Jun 16 2006
By calvinnme - Published on Amazon.com
This review is from: Machine Vision: Theory, Algorithms, Practicalities (Hardcover)
To begin with, the latest edition of this book was published in 2004, so all reviews dated earlier than that are referring to a previous edition. This book is a good one on issues and algorithms as they pertain to machine vision versus general computer vision. If you want a good general textbook on computer vision try "Computer Vision" by Linda Shapiro. It has all of the background material and a firm foundation in all of the topics you would expect in a course on computer vision. This book also has a section on introductory computer vision topics, I just don't think it is as clear and as comprehensive as Shapiro's book, especially for students.
However, if you want an excellent treatment of the kinds of problems specific to machine vision - the detection of lines, holes, corners, circles, elipses, and polygons, for example, along with specific algorithm details, this book is very good. It also has good sections on pattern matching, motion estimation, and 3D machine vision. I would recommend it especially for those individuals who are already familiar with the basics of computer vision and would like a book on algorithms for solving specific problems in machine vision. I notice that Amazon only shows the table of contents for the previous edition, so I show the table of contents for the new edition next:
1. Vision, The Challenge
PART 1 - LOW-LEVEL VISION
2. Images and Imaging Operations
3. Basic Image Filtering Operations
4. Thresholding Techniques
5. Edge Detection
6. Binary Shape Analysis
7. Boundary Pattern Analysis
8. Mathematical Morphology
PART 2 - INTERMEDIATE-LEVEL VISION
9. Line Detection
10. Circle Detection
11. The Hough Transform and Its Nature
12. Ellipse Detection
13. Hole Detection
14. Polygon and Corner Detection
15. Abstract Pattern Matching Techniques
PART 3 - 3D VISION AND MOTION
16. The Three-Dimensional World
17. Tackling the Perspective n-Point Problem
18. Motion
19. Invariants and their Applications
20. Egomotion and Related Tasks
21. Image Transformations and Camera Calibration
Part 4 - TOWARDS REAL-TIME PATTERN RECOGNITION SYSTEMS
22. Automated Visual Inspection
23. Inspection of Cereal Grains
24. Statistical Pattern Recognition
25. Biologically Inspired Recognition Schemes
26. Texture
27. Image Acquisition
28. Real-Time Hardware and Systems Design Considerations
PART 5 - PERSPECTIVES ON VISION
29. Machine Vision, Art or Science?
3 of 3 people found the following review helpful
3.0 out of 5 stars
Book with basic techniques, Jun 6 2011
By M.Davydov - Published on Amazon.com
This review is from: Machine Vision: Theory, Algorithms, Practicalities (Hardcover)
It is a good book for beginners in image processing. Basic techniques are well described with mathematical formulas and algorithms. There is a lot of models considering computer vision geometry.
On the other side there is a lack of modern techniques in the book. You will find no info about Haar features, Bayesian fields, Gabor filters. Neural networks, Ada-boost, SVM, PCA are described superficially. You will need more info to implement them.
4 of 5 people found the following review helpful
5.0 out of 5 stars
use it to understand OpenCV, Dec 17 2007
By W Boudville - Published on Amazon.com
This review is from: Machine Vision: Theory, Algorithms, Practicalities (Hardcover)
For the analyst wanting to get into image recognition, Davies offers a detailed look at the many methods used in the last 30-40 years. These include neural networks, support vector machines, and the Hough transform.
If you are tempted to use [or are using] the OpenCV code base for image research, then the book can be a vital theoretical framework. OpenCV is about the best open source image code out there on the net, but it is poorly documented. It does come with many methods for basic and vital operations like make a grayscale image from a colour image, and making a binary image from a grayscale image. But why the code does certain things (actually many things) is rarely explained. Try using this book for understanding. Plus, the text lets you get an idea of how to modify OpenCV for your purposes.
And if you are going to use this book with OpenCV, look closely at the section on using multiple classifiers for training and then testing against unknown images. It is the basic idea for the cascading classifiers used by OpenCV.
Along these lines, one improvement for a future edition of the book could be an analysis of code packages that are currently available for image processing. Just a thought. But it would greatly help people wanting an expert assessment on the efficacies of available packages. Or, on a more basic level, it would aid simply in delineating what is out there.