Books on computer vision
As I have mentioned before, I am thinking about writing a book on elementary computer vision and image analysis. Of course, I’ll follow what’s already in the wiki. It will take a while and in the process I research some of the better books related to the subject. I think Digital Image Processing Using MATLAB by Gonzalez, Woods, and Eddins is one of the best and closest to what I have in mind. Here is a short analysis.
|
Pros: |
Cons: |
|
“[T]extbook format not a software manual”. |
|
|
Comprehensive coverage of image processing. |
|
|
Many illustrations. |
|
|
Some mathematics is explained. |
Required:
|
|
Many examples of MATLAB code. |
|
|
Website: a lot of supplementary material (even PowerPoint slides for instructors). |
|
|
Many projects online. |
No exercises in the book. |
|
Based on MATLAB which is ubiquitous. |
|
|
Accessible to “individuals with a basic background in digital image processing, mathematical analysis, and computer programming, all at the level typical of that found in a junior/senior curriculum in a technical discipline.” |
These requirements make it an intermediate book. |
The bottom line is that even though this may be the most elementary book on the subject, it’s still intermediate with serious prerequisites.
Recently, there has been a growing interest in applying machine learning techniques for approaching computer vision problems. I posted an entry about the courses offered at some universities that talk about these aspects of computer vision on my blog ( http://vimsu99.blogspot.com/2008/10/intro-to-vision-courses.html )
People with machine learning background who are looking at computer vision as an application domain may get some help if your upcoming book could introduce this stuff.
Viditjain:
Thanks for the idea. The problem is that what I have in mind is really elementary – no calculus, linear algebra etc (see this link http://inperc.com/wiki/index.php?title=The_Mathematics_of_Computer_Vision). That said, there must be a machine learning method based on elementary probability. I’ll give this some thought.