Facial-scanning system for crowds shows improvement in tests by Homeland Security
Posted Aug 21, 2013 7:40 AM CST
By Debra Cassens Weiss
The U.S. Department of Homeland Security tested a crowd-scanning system last fall that could be used to identify faces of people on a terrorism watch list.
The government decided the technology wasn’t ready to be used, though the test results showed that researchers are making significant progress, the New York Times reports. The newspaper obtained documents chronicling the tests from privacy advocate Ginger McCall, who used the Freedom of Information Act to get the information when she was part of the Electronic Privacy Information Center.
“This technology is always billed as antiterrorism, but then it drifts into other applications,” McCall told the newspaper. “We need a real conversation about whether and how we want this technology to be used, and now is the time for that debate.”
The scanning system is known as Biometric Optical Surveillance System, or BOSS. It uses a computer to build a “3-D signature” from photos taken at different angles, then compares the results with a watch-list database. A computer professor and an official with the company developing BOSS said advances in computer processing will eventually result in speedier and more reliable matches. Currently, the system’s accuracy is only 60 percent to 70 percent at longer distances. And it takes 30 seconds to process the images.
The story also reports significant progress in facial recognition using photos taken under better conditions, such as passport pictures and mug shots. The FBI is spending $1 billion on a Next Generation Identification system to help local police verify identities through a national mug shot database.