Achievement
Facial expressions and deception detection
Project
Vision and Learning in Humans and Machines
University
University of California at San Diego
(La Jolla, CA)
Research Achievements
Facial expressions and deception detection
IGERT trainee Paul Ruvolo, Adrienne Moore, and Megan O'Rourke collaborated on a project to investigate whether there is an association between the degree to which a subject spontaneously mimics facial expressions of others and his/her ability to determine when they are being deceived. Subjects watched videos of actors that were either in real pain (hand submerged in ice cold water) or fake pain (hand submerged in lukewarm water, but instructed to exhibit characteristics of real pain) and then asked to categorize each of 18 videos according to whether they perceived the person in the video to be exhibiting genuine or faked pain. Synchronized video data of the viewers and actors were analyzed using a computer vision tool for automatically coding facial expressions with the Facial Action Coding System. The correlation between the facial expressions of viewer and actor was highly predictive of the viewer's ability to determine whether each actor was exhibiting genuine or faked pain.
- “Research Achievements”
- Achievements for this Project