OpenFace is an advanced facial behavior analysis toolkit intended for computer vision and machine learning researchers, those in the affective computing community, and those who are simply interested in creating interactive applications based on facial behavior analysis. The OpenFace toolkit is capable of performing several complex facial analysis tasks, including facial landmark detection, eye-gaze estimation, head pose estimation and facial action unit recognition. OpenFace is able to deliver state-of-the-art results in all of these mentioned tasks.
OpenFace is available for Windows, Ubuntu and macOS installations. It is capable of real-time performance and does not need to run on any specialist hardware, a simple webcam will suffice.
Features
- facial landmark detection
- head pose estimation
- facial action unit recognition
- eye-gaze estimation
- available source code for both running and training the models