Communications of the ACM
Ub Team's Software Is Set to Eyeball Liars
Credit: iStockPhoto.com
University of Buffalo researchers have developed video-analysis software that can analyze eye movements and determine when people are lying with significant accuracy.
In a test involving 40 people, the system correctly identified who was telling the truth and who was lying 82.5 percent of the time. The software tracks eye movements using a statistical technique that models the movements.
The team interviewed the 40 subjects, and used eye-tracking equipment to establish what normal, baseline eye movements looked like for each participant at the beginning of the sessions. The researchers focused on details such as the rate of blinking and the frequency with which people shifted the direction of their gaze. The team then used the software to compare each participant's baseline eye movements with their eye movements during the key section of each interrogation.
"What we wanted to understand was whether there are signal changes emitted by people when they are lying, and can machines detect them?" says Buffalo professor Ifeoma Nwogu. "The answer was yes, and yes." The researchers now plan to extend their system to also monitor body language.
From PhysOrg.com
View Full Article
Abstracts Copyright © 2012 Information Inc. 
, Bethesda, Maryland, USA
No entries found