|Embedded Vision: An Introduction (Mercury Learning)|
|Written by Harry Fairhead|
Author: S. R. Vijayalakshmi and S. Muruganand
This book seems to be a guide to the subject of machine vision on small machines, but it only is if you want to keep well away from the details. This is a type of book that I like to think of as "listy books". They take a subject and attempt an exhaustive enumeration of every possible facet. In most cases such books rarely dig into the material, they are simply happy to have named everything. In this case there is the occasional attempt at explaining something, but never deep enough to understand it or to argue about it. I'm never quite sure who these books are aimed at and sometimes resort to "suitable for managers" - no disrespect intended - but I also think they may be of use to anyone trying to wing their way into a subject with a quick crash course. The only problem with this idea is that there is nothing quick about reading this particular book! I also have no idea how you could remember any of this stuff without a theoretical framework to pin it on.
The book starts off with the most listy of chapters outlining all of the basics of embedded vision. I really don't know what anyone would make of this long list of ideas. Next we have a repeat exercise, but on industrial automation and vision. Then the same again for medical vision.
Chapter 4 beaks the mold a little by looking at analytics which includes machine learning. Then image processing is listed, but here we have some examples of operators and filters - this is about as practical as the book gets.
Chapter 6 is a bit off topic, but only just, and tells us about cameras. Chapter 7 is about machine vision - wait wasn't the entire book about machine vision? Chapter 8 is about applications, Chapter 9 is about AI (again) and finally we have a chapter on research.
If you are looking for anything practical then you need a different book. There are some attempts at explaining some of the ideas, but not so much that they would be useful to a beginner. Even when I encountered a technique I knew something about, the book left me wondering what it was all about. It is a shame because the book is well-written and in places almost breaks out of the listy approach and starts to tell you something. But at the end of the day it just doesn't. If you need a bluffer's guide to machine vision you might find something useful in this book, but if you really want to know something about it start elsewhere and be prepared to put in a lot more effort.
|Last Updated ( Tuesday, 13 April 2021 )|