Facial Action Coding System (FACS)
The research-grade taxonomy that decomposes every observable human facial movement into discrete, anatomically defined Action Units.
The Facial Action Coding System (FACS) is the most widely adopted framework for objectively describing facial behavior. It was developed by Dr. Paul Ekman and Dr. Wallace V. Friesen in 1978 and updated in 2002, and is used by behavioral researchers, clinicians, animators, security analysts, and emotion-AI developers worldwide.
FACS catalogs roughly 44 facial Action Units (AUs), each tied to the contraction of a specific muscle or muscle group. By scoring which AUs activate, with what intensity (A–E), and in what combination, a trained coder or computer-vision model can describe a facial expression without making assumptions about the underlying emotion.
Because FACS is grounded in anatomy rather than interpretation, it is the de facto standard for peer-reviewed emotion research and the foundation that most modern facial analytics platforms — including Mental Edge — build on.
Example: A genuine (Duchenne) smile is FACS-coded as AU6 (cheek raiser) + AU12 (lip corner puller). A polite social smile typically shows AU12 alone.
Related terms: action unit, paul ekman, duchenne smile, emfacs, micro expression
Back to Facial Analytics Glossary