GammaCV

GammaCV is a computer vision library for the browser, accelerated with WebGL so that image processing and feature extraction run on the GPU rather than the CPU. It follows a data flow paradigm similar to TensorFlow, where operations are assembled into a graph that is then compiled and run, which lets a developer chain filters, transforms and feature detectors into a pipeline that processes camera frames or images at speed. The library is for front end and web developers adding vision features to web applications, progressive web apps and in browser demos, where sending frames to a server would be too slow or too expensive. Size is a stated design goal: the build is 87.5k uncompressed and 32.5k compressed, small enough to include in a progressive web app without a noticeable penalty. Because the work happens in WebGL, frame rates stay high without saturating the user's processor, and the maintainers test every capability across modern desktop, mobile and tablet browsers. Documentation, a set of runnable examples and the source repository are linked from the home page, and the site shows the current API version. Pricing is not published, and there is no pricing page on the site. GammaCV is distributed as a library through its public repository and package listing rather than sold as a hosted service, so there is nothing to subscribe to. It is worth noting that this is a developer library, not an application: using it means writing code against its graph API, and the examples are the fastest route to understanding what the operations do.