November 13, 2013
The U.S. intelligence community is pushing a leap forward in facial recognition software that will enable it to determine better the identity of people through a variety of photographs, video and other images.
Called Janus, the program run by the Intelligence Advanced Research Projects Agency (IARPA), “seeks to improve face recognition performance using representations developed from real-world video and images instead of from calibrated and constrained collections. During daily activities, people laugh, smile, frown, yawn and morph their faces into a broad variety of expressions. For each face, these expressions are formed from unique skeletal and musculature features that are similar through one’s lifetime. Janus representations will exploit the full morphological dynamics of the face to enable better matching and faster retrieval.”
Documents released by IARPA over the weekend show that the Janus program will start in April 2014 and run for four years. During that time, the agency hopes to “radically expand the range of conditions under which automated face recognition can establish identity.”