OpenCV (Open Source Computer Vision Library) has been in development since June 2000, when it began as a research initiative inside Intel aimed at advancing computer vision and giving the field a common, optimized code base. The official OpenCV project page dates the library’s origin to that month.
OpenCV provides more than 2,500 algorithms for tasks such as image filtering, feature detection, object recognition, camera calibration, motion tracking, and, in later versions, running deep neural networks. It is written in C++ with bindings for Python, Java, and other languages, and it is released under the permissive Apache 2 license, which makes it straightforward for companies to use and modify. The project page notes a user community in the hundreds of thousands and an estimated 40 million-plus downloads per month, with users ranging from hobbyists to companies like Google, Microsoft, and Intel and bodies such as NASA.
OpenCV is the default toolkit for classical computer vision and a common companion to deep learning frameworks. Much of the practical image-processing code in robotics, manufacturing inspection, medical imaging, and consumer apps runs on it, often invisibly.