Computer Vision Primer: beginner's guide to image analysis, data analysis, related mathematics (calculus, topology, linear algebra), image analysis software, and applications in sciences and engineering.

From Computer Vision Primer

This is an online textbook of mathematics needed for computer vision, image and data analysis, and related fields.

This site contains over 450 articles with over 1200 illustrations. The main source of the courses presented here are the ones that I taught recently at Marshall University.

To get started with computer vision, prerequisites are minimal:

• First, some calculus. Very little is required because integer (or binary) arithmetic can be applied exclusively.
• Second, some familiarity with linear algebra would help. In the more advanced articles, I use vectors and matrices of arbitrary dimensions. Finitely dimensional vector spaces, subspaces, linear operators and their matrix representations also appear.
• Third, a basic knowledge of C++ or another computer language might be needed for some articles. However, the code is written as a mere illustration of the algorithms. Pseudo-code is also provided.

That said, the long-term goal is to make the site completely self-contained. I would like this site to cover a big chunk of the math curriculum, interlinked with the computer vision / image analysis topics.

The content comes directly from my lectures. I use SMART Tablet PC with Windows Journal. I started doing this last fall and I really love the results: bright, colorful slides, but with the spontaneity and flexibility of the chalkboard. I transcribe the lectures into text, put it on the site, and simply copy the illustrations. (Plus, I don’t have to deal with chalk on my shoes, pants, and lungs!) I think this approach has huge advantages over the common practice of simply posting video lectures online: search-ability, edit-ability, link-ability, speed of download, the ability to read and work at one's own pace, etc.

The wiki format was chosen for its simplicity. There is no intent to make is Wikipedia-like in terms of completeness, definitiveness, etc. On the other hand, "trivial" details, "elementary" examples, "easy" exercises, etc have to be included in a textbook. The format is also very informal and most of the articles are somewhat unpolished, just like the lectures they came from. I am still considering converting the text into TeX. The site is work in progress...

Drop me a line if you have any questions!

Best of luck!

Peter Saveliev

Articles in category "Courses"