This book aspires to provide an easy entry point for creative experimentation with computer vision. It introduces the code and concepts necessary to build computer vision projects with the Processing creative coding environment and OpenCV, the definitive open source computer vision library. It is designed to be accessible to a beginner audience, but also to instill the fundamental concepts of the field, enabling readers to not just follow recipes, but build their own projects.
This book is being developed in parallel with OpenCV for Processing, a Processing library that provides access to OpenCV. All of its code examples use that OpenCV for Processing and it acts as the definitive documentation for that library.
Getting Started with Computer Vision is an in-progress community project begun in May of 2013. It is generously supported by O'Reilly Media and will be published for public consumption by them. It's text is available freely here under a Creative Commons license.
Getting Started with Computer Vision is currently highly incomplete but under rapid development. Suggestions, contributions, corrections, and pull requests are highly welcome. If you're looking for places to help, check out the proposed table of contents Contributions are especially welcome in the form of examples, particularly in the area of camera calibration and machine learning.
This book is organized to be useful both as reference and as tutorial. Each page introduces its topic in a manner that should stand alone, providing links to other relevant pages that may be required as prerequisites. The overall order of the book is designed to lead a beginner through the material in a sensible and useful way if read linearly.
Given the visual nature of computer vision work, each page also takes maximum advantage of the multi-media capabilities of the web to cover its material, including video and interactive code examples as well as text explanations, documentation, and links.