http://www.sciencemag.org/cgi/content/abstract/319/5862/435
Scanned by: Fishkaover 5 years ago
Dr.s Jenkins and Burton from the University of Glasgow modeled human familiarity by using image averaging to derive stable face representations from naturally varying photographs. This simple procedure increased the accuracy of an industry standard face-recognition algorithm from 54% to 100%, bringing the robust performance of a familiar human to an automated system.