OpenCV

From Wikipedia, the free encyclopedia

OpenCV is an open source computer vision library originally developed by Intel. It is free for commercial and research use under a BSD license. The library is cross-platform, and runs on Mac OS X, Windows and Linux. It focuses mainly on real-time image processing, as such, if it finds Intel's Integrated Performance Primitives (IPP) on the system, it will use these commercial optimized routines to accelerate itself.

OpenCV's application areas include

• Human-Computer Interface (HCI)
• Object Identification
• Segmentation and Recognition
• Face Recognition
• Gesture Recognition
• Motion Tracking
• Ego-motion
• Motion Understanding
• Structure from motion (SFM)
• Mobile Robotics

To support some of the above areas, OpenCV includes a statistical machine learning library that contains:

• Naive Bayes classifier
• k-nearest neighbor algorithm
• Support Vector Machine
• Decision Trees
• Boosting
• Random forest
• Expectation Maximization
• Neural Networks

[edit] Successful applications

• OpenCV was of key use in the vision system of Stanley, the winning entry to the 2005 DARPA Grand Challenge race.
• OpenCV is [widely used] in video surveillance systems
• OpenCV is the key tool in the software Swistrack, a tracking tool for understanding self-organization in insects and swarm robotics

[edit] Windows prerequisites

The DirectShow SDK is required to build some camera input-related parts of OpenCV on Windows. This SDK is found in the Samples\Multimedia\DirectShow\BaseClasses subdirectory of the Microsoft Platform SDK, which must be built prior to the building of OpenCV.

[edit] External links

• OpenCV Documentation Wiki
• OpenCV SourceForge site
• OpenCV homepage at intel
• OpenCV China site
• Cheat sheet
• An open source .NET wrapper for OpenCV
• .NET Wrapper For Face Detection
• Small example project for using OpenCV with VC++.net