Action Units

Understanding the emotional expression of human beings.
LEARN MORE
Facial Expression and Emotions
One of the central questions of human evolution is the origin of human culture. Human intelligence can be explained in part by increasing social demands for human prehistory (Dunbar, 1998). However, social intelligence is also reflected in any adaptation that enables humans to interact successfully in social groups. The face serves as a visible signal in social interactions, and facial expressions are a crucial variable.

The universality of facial expressions and emotions

 

Facial expression is considered a human universality. Consisting of basic expressions represented in all known human populations (Brown, 1990), or it is considered a natural outgrowth of cultural differences (Birdwhistell, 1975). The six basic expressions are evident in all cultures: Disgust, Fear, Joy, Surprise, Sadness, and Anger. They are universal in their execution and perception (Ekman and Keltner, 1997).

In The Expression of Emotions in Man and Animals (1872/1998), Darwin first described disgust, fear, pleasure, surprise, sadness, and anger as universals. They have been recognized in people from very different cultural and social backgrounds and in the faces of people born deaf and blind (Darwin, 1872/1998; Eibl-Eibesfeldt, 1989; Izard, 1977; Ekman and Keltner, 1997).

What are action units?
Action units are the movement of a facial muscle or muscle groups that configure the expression of an emotion, based on Paul Ekman’s Facial Action Coding System (FACS). Ekman worked with fellow psychologist and researcher, Wally Friesen, to develop FACS as a more comprehensive system of facial measurement that even scientists could use to understand facial expressions. Ekman and Friesen identified a total of 40 action units and found hundreds of combinations when more than one action unit was used at the same time.
Image module
Image module
READ MORE ABOUT EKMAN
How Emotiva uses Action Units
Emotiva detects and measures 23 Action Units plus a neutral state, which helps to identify the expression of emotions.
Image module
LEARN MORE
ACTION UNITS
HOW IT WORKS
Computer vision and machine learning algorithms detect and classify face muscle activations encoded as Action Units that configure the expression of an emotion. Analysis occurs through a standard webcam used to recognize and measure facial muscle activations and head movements of the opted-in subjects.
Defining four layers of emotional states using Action Units
We detect and measure 23 Action Units, such as Inner Brow Raiser, Brow Lowerer, and Cheek Raiser, and the correlation between them to define primary, compound, and complex emotional states.
Primary
Joy
Sadness
Fear
Disgust
Surprise
Anger
Complex (Secondary)
Amusement
Boredom
Confusion
Contentment
Coyness
Desire
Embarrassment
Interest
Pain
Pride
Shame
Sympathy
Compound
Happily surprised
Happily disgusted
Happily sad
Sadly fearful
Sadly angry
Sadly surprised
Sadly disgusted
Fearfully angry
Fearfully surprised
Fearfully disgusted
Angrily surprised
Angrily disgusted
Disgustedly surprised
Appalled
Hatred
Awed
State
Pain detection
Fatigue detection
Learn more about action units
Our team of action unit experts is available to answer any questions.