UB team's software is set to eyeball liars

Mar 08, 2012 by Nancy Owano report
eye

(PhysOrg.com) -- A study team at the University of Buffalo, State University of New York, is working on video analysis software to analyze eye movements to spot liars. So far, they say their results show that their software can spot liars with a promising level of accuracy. Their claim is based on their study using 40 people. Their system correctly identified who was telling the truth and who was lying 82.5 percent of the time.

“What we wanted to understand was whether there are signal changes emitted by people when they are lying, and can machines detect them? The answer was yes, and yes,” Ifeoma Nwogu, a co-author of the study and professor at the Center for Unified Biometrics and Sensors, told the UB Reporter.

According to a report in Scientific American, their work was inspired by findings from a professor of psychology at the University of California in San Francisco, School of Medicine, Paul Ekman. He has focused on emotions as they relate to facial expressions.

As for interrogators themselves, their experiences indicate that the use of such software for telling who is lying and who is telling the truth would not be practical in all instances and may not always lead them to the right targets. Just as polygraphs have drawn controversy over how reliable they really are, face-detection tools might also generate its share of false positives.

Undaunted, the researchers last year presented their study results at the 2011 IEEE International Conference on Automatic Face and Gesture Recognition and now they are set to broaden their investigations to account for body language too.

Also, said Nwogu, faster algorithms may raise the ’s ability to spot behavioral deviations in near real-time. The system that they are using tracks using a statistical technique that models the movements. Nwogu and others on the team, in the course of their 40 interviews, used the beginning of each interview to establish what normal, baseline eye movements looked like for each subject. The team focused on such details as the rate of blinking and the frequency with which people shifted the direction of their gaze. The researchers then used their system to compare each subject’s baseline eye movements with eye movements during the critical section of each interrogation.

Another goal as they continue their research is to expand the sample size. They used a sampling of 40 people, which they said was too small to be statistically significant.

Other researchers involved in this study include Nisha Bhaskaran, Venu Govindaraju, and Mark Frank, a professor of communication and behavioral scientist.

Explore further: Touch-responsive 3-D maps provide independence to the visually impaired

More information:

Related Stories

Technology would help detect terrorists before they strike

Oct 05, 2007

Are you a terrorist? Airport screeners, customs agents, police officers and members of the military who silently pose that question to people every day, may soon have much more than intuition to depend on to determine the ...

Recommended for you

Self-driving cars could be the answer to congested roads

11 hours ago

If cars with drivers still suffer under gridlock conditions on roads, how will driverless cars fare any better? With greater computerisation and network awareness, driverless cars may be the answer to growing ...

Gecko inspired pads allow researchers to climb glass wall

Nov 19, 2014

A team of researchers working at Stanford University has used prior research involving the means by which gecko's climb walls to create pads that allow a human to do very nearly the same thing. In their paper ...

User comments : 18

Adjust slider to filter visible comments by rank

Display comments: newest first

Expiorer
2.3 / 5 (3) Mar 08, 2012
another pointless device you can not use in court
TheSpiceIsLife
5 / 5 (3) Mar 08, 2012
I stopped reading at "Their claim is based on their study using 40 people."

Mayday
3 / 5 (2) Mar 08, 2012
These tricks seem rather easy to defeat, don't they? The subject just needs to "lie" in every response from the get-go. My guess is that "the machine" can not detect the scale of the fib, so minor and insignificant departures from the truth are easily spun without creating an impossible-to-maintain story. Me thinks these researchers need to get out more often.
Bowler_4007
1 / 5 (1) Mar 08, 2012
@Mayday or a second way to beat it would be to utterly convince yourself that the lies are true, i really think thats possible for someone in control of themselves
extremity
1 / 5 (1) Mar 08, 2012
Only 82.5% because its new. After people become aware of their "tells" and that lies can be partly detected in this fashion they will consciously and subconsciously adapt to counter it. Just like a poker player would, and just like people and lie detectors.

And TheSpiceIsLife is absolutely correct. 40 people is hardly enough to publish a paper on if you consider a vast majority of people, and possibly everyone, lies. Its funny how they do actually address that in the conclusion of the article rather than the introduction.

Another goal as they continue their research is to expand the sample size. They used a sampling of 40 people, which they said was too small to be statistically significant.


The phrase above should never have to be published in a science article.
Lurker2358
1 / 5 (1) Mar 08, 2012
The moment you start to judge, convict, or hire or fire human beings based on the "judgement" of a computer, you have forfeited human sovereignty to a machine.
mortoo
5 / 5 (1) Mar 08, 2012
Holden: You reach down and you flip the tortoise over on its back, Leon.
Leon: Do you make up these questions, Mr. Holden? Or do they write 'em down for you?
Holden: The tortoise lays on its back, its belly baking in the hot sun, beating its legs trying to turn itself over, but it can't. Not without your help. But you're not helping.
Leon: What do you mean, I'm not helping?
Holden: I mean: you're not helping! Why is that, Leon?

Holden: They're just questions, Leon. In answer to your query, they're written down for me. It's a test, designed to provoke an emotional response... Shall we continue?
Holden: Describe in single words only the good things that come into your mind about... your mother.
Leon: My mother?
Holden: Yeah.
Leon: Let me tell you about my mother...
naqe
not rated yet Mar 08, 2012
I use the eye technique on the kids... It works well.
But there is no eye movement that signals a lie.
Just how things are remember, what is being remember. etc.
I guess the programming would not be that difficult though.
But the eyes are not the only form of a story being told.
The body also gives clues. Program and analyze body language along with the eyes, and then we're getting somewhere.
Telekinetic
1 / 5 (2) Mar 08, 2012
If the person in question floats- witch! If they drown- innocent. Still an effective truth-seeking technique, 100% correct.
bredmond
1 / 5 (1) Mar 08, 2012
There is some tribe in a developed nation that also has a good way. They put a hot knife up near the leg of the person, if the person gets cut, they are a liar, if they don't, they are being honest.
robbor
Mar 08, 2012
This comment has been removed by a moderator.
MandoZink
5 / 5 (1) Mar 08, 2012
I was just recently informed from many legal sources that even if a lie-detector is developed that is 100% effective, it will still not be allowed as court evidence. Why? Because you would be able to make the arresting officer take the test. That would seriously affect the operations of the police. Unfortunately, I have an upcoming court case in which three officers are lying their butts off. Previous to this, I had thought lying by police was sort of rare. I have been told a very different story from people in the legal system in the last few months.
Sanescience
5 / 5 (1) Mar 09, 2012
I would be interested in measuring the difference between sociopaths and normal people. That is usually where you get into trouble with this kind of thing.
James_Mooney
not rated yet Mar 09, 2012
Can we install this system in Congress?
James_Mooney
not rated yet Mar 09, 2012
Previous to this, I had thought lying by police was sort of rare. I have been told a very different story from people in the legal system in the last few months.


People who think police don't lie probably think their insurer won't cheat them on a large claim. As someone who was an adjuster, and then a consumer advocate against the industry, I can qualitatively say that Insurance is America's Largest Organized Criminal Enterprise.
MandoZink
not rated yet Mar 09, 2012
James Mooney,
You might suppose that, but oddly enough I have had the occasion to be in 3 different accidents over a couple of decades in which I got more money that I was initially offered in each case. They also underestimated me. I like to think people are good (like the cops I expected to protect me), but I'm not stupid.
Vendicar_Decarian
not rated yet Mar 09, 2012
They had better keep that device away from Republicans.
robbor
not rated yet Mar 10, 2012
They had better keep that device away from Republicans.


..........Republicants, Bladerunner
Au-Pu
1 / 5 (1) Mar 10, 2012
If you were to put such a device into any government you would struggle to find anyone telling the truth.
A survey of senior Judges in Australia produced the stunning result that Judges believed that about 25% of the convictions they handed down were gained on fabricated evidence. So much for honesty.
The USA's largest organised criminal organisation is sadly the CIA.
Tausch
Mar 12, 2012
This comment has been removed by a moderator.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.