This Docker image allows a user to bypass manual installation steps and quickly use the binaries to perform facial-based feature extraction from videos such as facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation. More details can be found at OpenFace. This image is built using the
ubuntu:16.04 based on this OpenFace github commit on 08/02/2017. Docker base image, and the working directory defaults to
openface-cambridge is named as such to differentiate from the other OpenFace by CMU for face recognition purposes.