Facial Action Coding System (FACS)
FACS is an anatomically based system for describing visually discernible facial movement through Action Units.
Origins and reference materials
Paul Ekman Group describes FACS as a comprehensive system for visually discernible facial movement. The organization credits Swedish anatomist Hjortsjö with groundwork in 1970. Ekman and Wallace V. Friesen first published the manual in 1978. The 2002 revision is credited to Ekman, Friesen, and Joseph C. Hager.
The manual is a 527-page PDF, accompanied by a 197-page Investigator's Guide. Paul Ekman Group estimates roughly 50 to 100 hours for self-instruction. Its Final Test contains 34 video items and is described as the proficiency standard. Those details describe training, not evidence that software has achieved equivalent proficiency.
Describe movement before interpreting it
FACS describes visible movement through anatomically based Action Units, rather than assigning a person's feelings. Intensity runs from A, meaning trace, to E, meaning maximum. Codes can also distinguish right, left, unilateral, or asymmetric movement. Action descriptors are separate from Action Units. For a review project, define the observation and intensity rule before comparing clips.
Software estimates and human coding
OpenFace is one example of a toolkit offering landmarks, head pose, Action Unit recognition, and eye gaze. That example does not describe Mental Edge's implementation. Reliable FACS work usually relies on certified coders, with agreement between independent coders recommended. A shortage of manually coded reference data remains a limit for automated Action Unit detection.
Limits of emotional interpretation
Barrett and colleagues explain that facial configurations vary across people, situations, and cultures. A configuration can express different emotions, or none. Jack and colleagues found differences between Western and East Asian representations of basic expressions. A reply argued that commonalities outweigh differences, so the debate remains active. Neither an Action Unit nor a category score proves feelings, intent, or truthfulness.
The Mental Edge review boundary
Mental Edge surfaces observable expression and movement signals from recorded video for contextual human review. Frame-by-frame scores are associated with seven expression categories, not verified inner states. Use a time-coded signal to revisit the footage and ask an open question. Do not use these outputs for hiring, promotion, diagnosis, deception detection, threat assessment, student scoring, or surveillance.
Review expression signals in context
Mental Edge provides time-coded expression signals from recorded video for human review, not proof of feelings or intent.
Start a free trial