On Saturday, hockey fans at the Tri-City Americans game in Kennewick, Wash., will have a chance to participate in a test of facial recognition technology. To opt out, they’ll have to avoid the cameras by following designated routes.
The test, being conducted by researchers from the Pacific Northwest National Laboratory for the U.S. Department of Homeland Security, will involve 20 researchers whose images have been stored; half will just behave randomly, sitting in the stands, visiting the bathrooms, buying a snack or two; half will follow predetermined routes. Computers will comb the video feeds to spot them. So the test can be graded later, they’ll wear ankle bracelets that will let researchers know when and where they passed in front of cameras.
Sporting events, where streams of crowds are guaranteed to pass through a contained area, are a popular place to test face recognition technology. French company Vesalis tested its technology during a soccer game at the Parc des Princes, the largest soccer stadium in France; Germany’s Karlsruhe Institute of Technology (KIT) tested its system during home matches of the KSC soccer club. In Brazil, police officers plan to use wearable-computer-based face recognition to look for wanted criminals in the crowds attending the 2014 World Cup.
While these kind of tests continue to advance the technology, it is by no means ready for prime time, as James Wayman, former director of the National Biometric Test Center at San Jose State University told Spectrum’s Steven Cherry. The problems involve image quality (mug shots, often the only photo of a criminal available, are typically quite low in resolution), the size of the potential databases, and the legal and privacy issues of using the technology. (For Wayman’s complete analysis, see “Will Face Recognition Ever Capture Criminals?”)
Photo: Jim Davis/The Boston Globe/Getty Images
Tekla S. Perry is a senior editor at IEEE Spectrum. Based in Palo Alto, Calif., she's been covering the people, companies, and technology that make Silicon Valley a special place for more than 30 years. An IEEE member, she holds a bachelor's degree in journalism from Michigan State University.