Javascript Library for Precise Tracking of Facial Features

Clmtrackr is a javascript library for fitting facial models to faces in videos or images. It currently is an implementation of constrained local models fitted by regularized landmark mean-shift, as described in Jason M. Saragih’s paper. Clmtrackr tracks a face and outputs the coordinate positions of the face model as an array.

The library provides some generic face models that were trained on the MUCT database and some additional self-annotated images. The aim is to also provide a model builder for building your own facial models. The library requires ccv.js (for initial face detection) and numeric.js (for matrix math).

Requirements: JavaScript Framework
Demo: https://github.com/auduno/clmtrackr
License: MIT License