Easy Computer Vision is a library of tools to simplify the high-level operations on computer vision methods. It provides access to algorithms in the CV Algorithm Collection (CVAC) through well-defined interfaces, it links annotation tools (LabelMe, VATIC) to algorithms, and it permits creation of new detectors and their performance evaluation. You can connect to remotely running vision services, run algorithms as services on your computer, or embed algorithms into your program space. You can obtain and share a "corpus" of labeled objects for training or testing. And you can easily exchange one algorithm for another without modifying your code (much).

Easy! Computer Vision ...

... is a framework for anybody who wants to tap into the power for computer vision quickly and easily: application developers that would like to use computer vision, computer vision algorithm developers, contracting officers, and program managers.

... connects algorithms with data sets, e.g. from the Computer Vision Algorithm Collection (CVAC) or from OpenCV and from the Caltech101 corpus or LabelMe.

... enables transparent remote service invocation, cross-language communication, and a plug-and-play approach to model training, testing, and deployment.

Download and Install

Please see the download and installation page for binary installers for various operating systems, for installation instructions, as well as for source code download instructions.

Documentation

Start with the user documentation which includes an EasyCV Quickstart guide on how to use EasyCV and run your first examples. Of course, there is a FAQ.

In addition, there are several tutorials and the API documentation:

• Mini tutorials (demos) to get you started quickly;
• The Python EasyCV library API for high-level functionality;
• The cvac:: namespace for data and service definitions;
• Documentation for building from source including 3rd-party dependencies;
• Instructions for adding your algorithms to EasyCV and CVAC (see also Contributing below);
• Frequently Asked Questions;
• Overview of a Tutorial at CVPR 2013, including a better-formatted manual to an earlier version of EasyCV.
• And, last but not least, some Troubleshooting help.

Contributing

More detailed instructions are here. In summary:

1. Fork it. (Press the "Fork" button)
2. Create a branch off the devel branch (git checkout -b my_CVAC devel)
3. Commit your changes (git commit -am "Added parsing for MyAnnotations")
4. Push to the branch (git push origin my_CVAC)
5. Open a Pull Request
6. Wait for the request to be merged