OpenVL is the future of developer-friendly computer vision - existing vision frameworks provide access at a very low level, such as individual algorithm names (often named after their inventor), while OpenVL provides a higher-level abstraction to hide the details of sophisticated vision techniques: developers use a task-centred API to supply a description of the problem, and OpenVL interprets the description and provides a solution.

The OpenVL computer vision abstraction will support hardware acceleration and multiple platforms (mobile, cloud, desktop, console), and therefore also allows vendor-specific implementations. We are committed to making it an open API available to everyone (and hope to make it an open standard); Continue reading...
Face Front
Face Profile
OpenVL (the Open Vision Language) is a developer-friendly computer vision framework, hiding the complexity of sophisticated computer vision algorithms and their parameters through a description-based abstraction layer. Application developers describe a vision problem through a task-centred API, and OpenVL uses the description to provide a solution.

OpenVL is research software, with many bugs and features still to be implemented - it is not designed for use in a production environment. If you come across any bugs, please inform Gregor (include a description of the problem, and code if possible). Bear in mind that OpenVL is not directly supported and it may be a while before a fix is released.

OpenVL is distributed under a non-commercial license for academic use only. The license is available from

  • The release includes C++ headers and static library binaries
  • Source code is not currently available for the OpenVL libraries
  • This first release provides solutions to image segmentation; other vision problems will be released as we progress
  • This release is a desktop implementation; mobile and server implementations of the OpenVL API are currently under active development
  • This release supports OS X (Xcode/GCC), Windows (Visual Studio 2010) and Linux (GCC)
  • Contributions are welcome: either in the form of a collaboration or as an algorithm donation for a particular problem domain; contact Gregor for more details
  • We are looking for industry partners to help develop OpenVL: if you are interested in a partnership, please contact Gregor or Sidney (details above)


Dr. Daesik Jang, Kunsan National University, Korea
Constant Thomas, TÚlÚcom Saint-Etienne, UniversitÚ Jean Monnet Saint-Etienne, France
Nicolas Pajnic, TÚlÚcom Saint-Etienne, UniversitÚ Jean Monnet Saint-Etienne, France
Lo´c Duron, TÚlÚcom Saint-Etienne, UniversitÚ Jean Monnet Saint-Etienne, France


SLIC Superpixels ( used with permission from Radhakrishna Achanta at EPFL.

Our research has been supported directly by the National Sciences and Engineering Research Council of Canada (NSERC-CRSNG) and Bell Canada.

Release Notes

*** 2013/07/01 OpenVL v0.1a ***

First release
  • Image segmentation
  • Desktop implementation (designed for use on desktop/laptop systems)
  • OSX-Xcode, Windows-VisualStudio and Linux-GCC supported

Proceed to download