The OpenCV library

Headnote

An open-source library for processing image data

OpenCV is an open-source, computer-- vision library for extracting and processing meaningful data from images. That meaningful data might include finding all or parts of objects, recognizing all or parts of objects, tracking the movement of (parts of) objects in 2D or 3D between successive images, determining the 2D or 3D shape of objects from one or more images, and associating image data with a categorical meaning, such as mapping a handwave to the category "goodbye." Developed by an Intel research group (of which I'm a member), OpenCV is freely available at http://www.intel .com/research/mrl/research/cvlib/. In this article, I'll provide an overview of OpenCV and present an example of gesture recognition for conducting music using the library.

OpenCV Overview

All in all, OpenCV contains more than 500 functions. While the API of the library is C/C++, the bulk of the library is made up of C functions and the objects themselves are mostly self contained. Objects and func tions are Externed as C to avoid name mangling, allowing OpenCV to be used with Visual Basic and Java. Object-oriented design is mostly intended to take place at a COM or CORBA level for use in applications.

OpenCV is aimed at making computer vision accessible to programmers and users in the area of real-time human-computer interaction and mobile robotics. Thus, the library comes with source code and hand-- tuned assembly language binaries optimized for Intel processors, so that users can both learn from the library and make use of its performance. Figure 1 is an example of OpenCV-based gesture recognition used to control music. When you build and run an app using OpenCV, a built-in DLL switcher is called at run time to automatically detect the processor type and load the appropriate optimized DLL for that processor. If the processor type cannot be determined (or if the appropriate DLL is not available), an optimized C code DLL is used. Included in the OpenCV download is the optimized Intel Image Processing Library (IPL) on which OpenCV partially depends. Although it is included with OpenCV, you can also get IPL and other libraries for signal processing, matrix math, JPEG, and pattern recognition at http://developer.intel.com/vtune/ perflibst/.

OpenCV ships with an HTM overview...