Mike Burton, professor of psychology at Glasgow University, and lecturer Rob Jenkins claim to have achieved 100% accuracy with facial recognition technology.
Lighting, angle of the photo and other factors typically interfere with getting an accurate facial match. Burton and Jenkins got around this by taking 20 different photos and producing an average photo.
“We modeled human familiarity by using image averaging to derive stable face representations from naturally varying photographs,” the two say in a paper published in the January issue of Science. “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.”
Law enforcement and government officials have tried to use facial recognition biometrics to identify individuals in a crowd, but it hasn’t been very successful.
Read the full story here. ![[end]](/resources/bullet/thirdfactor-4.gif)
