BiometricsTerrorist or criminal? New software uses face analysis to find out
Pulling a poker face means betraying no visible emotion, so that opponents cannot tell what you are really thinking. But a Tel Aviv startup’s face-profiling technology recently proved fairly accurate at predicting which four players were most likely to beat out forty-six other contenders in an amateur poker tournament. The company say that its technology, which analyzes faces shown in photos and videos and classifies them according to fifteen parameters predictive of personality traits and types, can help identify terrorists.
Good hand or bad hand, the poker face hides the reality // Source: commons.wikimedia.org
Pulling a poker face means betraying no visible emotion, so that opponents cannot tell what you are really thinking.
But a Tel Aviv startup’s face-profiling technology recently proved fairly accurate at predicting which four players were most likely to beat out forty-six other contenders in an amateur poker tournament. Two of those four were among the event’s three finalists.
And now, the company reports that it has signed a contract with an unnamed “leading homeland security agency” to help identify terrorists through its technology, which analyzes faces shown in photos and videos and classifies them according to fifteen parameters predictive of personality traits and types.
Purportedly it can detect with high accuracy if you are, say, a genius, an extrovert, or a criminal.
“We understand the human much better than other humans understand each other,” Faception CEO Shai Gilboa told the Washington Post. “Our personality is determined by our DNA and reflected in our face. It’s a kind of signal.”
Gilboa said Faception evaluate faces with 80 percent accuracy for certain traits. “Utilizing advanced machine-learning techniques, we developed and continue to evolve an array of classifiers. These classifiers represent a certain persona, with a unique personality type, a collection of personality traits or behaviors. Our algorithms can score an individual according to their fit to these classifiers.
“Ultimately, we can score facial images on a set of classifiers and provide our clients with a better understanding of their customers, the people in front of them or in front of their cameras.”
Faception is offering the software as one tool among many that governments can use in the global war on terror.
Unlike face-recognition technology, which relies on matching faces to those already in a database, facial profiling relies on scientific studies suggesting that personality is determined by DNA and reflected in the face. Therefore, it can pinpoint potentially problematic people not previously known to authorities.
Only three of the eleven terrorists behind the November 2015 terror attacks in Paris had criminal records, Gilboa points out in a video about Faception. “Our technology classified nine of them as potential terrorists with no prior knowledge.”
Despite, or perhaps because of, the ethical controversy raised by its proprietary computer-vision and machine-learning technology, Faception has been getting a lot of press.
The company, founded in 2014, was a finalist in the LDV Vision Summit 2016 on 25 May in New York City. An alumnus of the 500 Startups accelerator in San Francisco, Faception is now a member of Sosa innovators’ community in South Tel Aviv.
Banks and marketers are among other professionals who might find Faception’s methodology valuable. Gilboa said he and his team believe their technology represents a multibillion-dollar opportunity.
Faception’s Web site describes the team as including “world-class experts in the areas of computer vision, face analysis, machine learning, psychology, technology and marketing.”
“Our mission is to revolutionize how companies, organizations and even robots understand people to dramatically improve public safety, communications, decision-making, and experiences.”
This article is published courtesy of Israel21c