TadasBaltrusaitis/OpenFace

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

7740 stars · 1911 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenFace is a facial behavior analysis toolkit that performs facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation. It runs in real-time from a simple webcam and provides source code for both running and training the models.

Use cases

• detect facial landmarks in images and videos
• estimate head pose from a webcam
• recognize facial action units (AUs)
• track eye gaze in real time
• analyze facial behavior for affective computing research
• build interactive applications based on facial expressions

When to choose

• you need state-of-the-art facial landmark detection or AU recognition with source code
• you want real-time facial behavior analysis from a standard webcam
• you are doing computer vision or affective computing research and need trainable models

When to avoid

• you need a maintained Python-first API or pip-installable package
• you need general object detection or full-body pose estimation rather than facial analysis
• you require a permissive license for commercial use without review

Facets

application · maturity active

computer-vision image-processing machine-learning computer-vision artificial-intelligence windows cpp facial-landmark-detection head-pose-estimation action-units gaze-estimation facial-behavior-analysis affective-computing research linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="TadasBaltrusaitis/OpenFace")