Open Source Computer Vision Library

What is OpenCV

OpenCV means Open Source Computer Vision Library. It is a collection of C functions and a few C++ classes that implement many popular Image Processing and Computer Vision algorithms.

OpenCV Book

The official book for OpenCV is published by O'Reilly Press Learning OpenCV Computer Vision with the OpenCV Library by Gary Bradski and Adrian Kaehler http://www.amazon.com/Learning-OpenCV-Computer-Vision-Library/dp/0596516134

This book is:

  1. A tutorial on computer vision in general
  2. A user's guide to OpenCV
  3. A source of useful working sample code and detailed function descriptions.

The key features

OpenCV provides cross-platform middle-to-high level API that includes about 300 C functions and a few C++ classes. Also there are constantly improving Python bindings to OpenCV, see interfaces/swig/python and samples/python. OpenCV has no strict dependencies on external libraries, though it can use some (such as libjpeg, ffmpeg, GTK+ etc.) when it is possible.

OpenCV is free for both non-commercial and commercial use (see the license for details).

OpenCV provides transparent interface to Intel® Integrated Performance Primitives (IPP). That is, it loads automatically IPP libraries optimized for specific processor at runtime, if they are available. More information about IPP can be retrieved at http://www.intel.com/software/products/ipp/index.htm

Who created it

The list of authors and major contributors can be found in the file THANKS.

What's New

See the ChangeLog.

Where to get OpenCV

Go http://www.sourceforge.net/projects/opencvlibrary. If it does not work, type "OpenCV" in Google (http://www.google.com).

If you have a problem with installing/running/using OpenCV

  1. Visit OpenCV Wiki-pages at http://opencvlibrary.sourceforge.net and look for the information there (and/or add it when you have found a solution)
  2. Read FAQs
  3. Search through OpenCV archives at www.yahoogroups.com (http://groups.yahoo.com/group/OpenCV/)
  4. Join OpenCV mailing list at yahoo groups (see FAQs on how to do it) and mail your questions (the mailing list will probably migrate to OpenCV's SourceForge site)
  5. Look at the OpenCV sample code, read the reference manual :)

OpenCV Reference Manuals

You may also look at the PDF manual, but do not trust it much - it is pretty out of date, especially, the reference part.