New lie detector relies on full-body suit for better accuracy

New lie detector relies on full-body suit for better accuracy

Suits normally used by 3D graphics animators could help law enforcement spot lies

When you are hooked up to a polygraph lie detector there is only a 60 percent chance a skilled examiner will spot a lie, giving you pretty good odds to get away with one or two untruths. However, Dutch and British scientists have found a way to amp up the accuracy of lie detection to 75 percent by monitoring a suspect's movements with a full-body suit.

Current lie detection methods aided by polygraphs are only slightly better than what people can achieve on their own. Without a machine, most people can only tell truth from lies about 55 percent of the time.

But when using a full body motion capture suit which records the position, velocity and orientation of 23 points in the subject's body, a better signal of deception can be achieved, according to scientists from the University of Cambridge and Lancaster University in the U.K., and the universities of Utrecht and Enschede in the Netherlands.

For the study, 90 pairs of volunteers were put in MVN motion capture suits from Xsens, a Dutch company that manufactures motion capture suits for professional animators. The suits start at $12,000 and have been used to create animations for movies like X-Men: Days of Future Past and games like Tomb Raider.

The researchers told the volunteers to interview each other and instructed half the volunteers to lie. This process showed that full body motion is a reliable indicator of guilt: the sum of joint displacements was indicative of lying approximately 75 percent of the time.

"Put simply, guilty people fidget more; and this turns out to be fairly independent of cultural background, cognitive load and anxiety -- the factors that confound most other deception detection technologies," said Ross Anderson , professor of Security Engineering at Cambridge University.

What's more, the researchers believe that accuracy can be improved to over 80 percent by analyzing individual limb data and using effective questioning techniques. This year, they are planning to redevelop the method for low-cost commodity hardware and test it in a variety of environments.

"Of course, a guilty man can always just freeze, but that will rather give the game away; we suspect it might be quite hard to fidget deliberately at exactly the same level as you do when you're not feeling guilty," Anderson said.

Loek is Amsterdam Correspondent and covers online privacy, intellectual property, online payment issues as well as EU technology policy and regulation for the IDG News Service. Follow him on Twitter at @loekessers or email tips and comments to

Join the CIO New Zealand group on LinkedIn. The group is open to CIOs, IT Directors, COOs, CTOs and senior IT managers.

Join the CIO New Zealand newsletter!

Error: Please check your email address.

Tags securitybiometricsXsens

More about Cambridge UniversityEUIDGNews

Show Comments