University academics are using facial recognition technology to predict when a person is telling a lie.
Silent Talker is a lie detector device built by experts at Manchester Metropolitan University which monitors a person鈥檚 face when they are asked a series of questions then classifies their behaviour.
Jim O鈥橲hea, a senior lecturer in computing, maths and digital technology, came up with the device which looks at 鈥渇ine grained gestures鈥� 鈥� those that the human eye does not necessarily detect.
During extensive research, the system has learned by example to identify behaviours that suggest lying, O鈥橲hea says, adding that it has been 87 per cent accurate based on sample groups.
He tells 老九品茶Cloud it would be impossible to list the exact gestures people make when lying.
鈥淲e tried converting the learning to a rule-based system but that would need thousands of rules to explain what鈥檚 going on,鈥� he says.
鈥淚t doesn鈥檛 look at smiles but at the things that happen in between the gestures 鈥� a change of gaze or an eye moving from half open to fully open.”
The patented system began as a research topic in 2000 and a limited company was formed in March 2016 after O鈥橲hea had identified the right investors.
He is about to start a Horizon 2020-funded project to use the system at border crossing points in Europe.
鈥淭he potential applications commercially are enormous,鈥� he adds.
鈥淭here are big opportunities in security, in war zones where there is risk of green on blue attacks, at airports or in schools to protect from random shooters.
鈥淚鈥檝e also been asked if we can do a system for traders in the City to predict when somebody is going rogue.
鈥淧eople might have an occasional interview with the system and we鈥檙e train it to detect precursors to this activity happening.
鈥淭he idea is to intervene to stop these things happening in the first place.鈥�