Facial Landmark Detection
The computer-vision step that locates anatomical reference points on the face — eye corners, nose, jaw, lip outline — used as the input to Action-Unit detection.
Modern facial analytics typically begins by detecting between 68 and 478 landmarks per face per frame using a deep neural network. Landmarks track the geometry of the face across head poses and partial occlusions.
Action Unit detectors operate on the landmark stream plus image regions, producing per-frame AU intensity estimates that can support source-linked facial-movement review.
Related terms: action unit, emotion ai, affective computing
Back to Facial Analytics Glossary