// the find
WebDevSimplified/Face-Detection-JavaScript
A tutorial repo from WebDevSimplified showing how to do real-time face detection in the browser using face-api.js and the webcam. It's squarely aimed at beginners who want to see ML in the browser without a backend. Not a library, not a production tool — a learning exercise.
Ships bundled face-api.js models so it works offline after clone with no build step. Covers detection, landmark tracking, and expression recognition in one small demo, which is a decent surface area for the code volume. The README proactively documents two real bugs and their fixes, which is more than most tutorial repos bother with.
The entire project is a single HTML file plus one script — there's essentially nothing to learn about architecture, module structure, or how you'd integrate this into a real app. face-api.js itself is unmaintained (last release 2020) and wraps an old version of TensorFlow.js, so you're building on a dead dependency. The bundled model files are committed directly to git, which is a bad habit to pick up from a tutorial. Forks vastly outnumber stars (1364 vs 1035), a reliable sign people are forking it for a course assignment rather than because they find it useful.