Last week, a trio of Google researchers published a paper on a new artificial intelligence system dubbed FaceNet that it claims represents the most-accurate approach yet to recognizing human faces. FaceNet achieved nearly 100-percent accuracy on a popular facial-recognition dataset called Labeled Faces in the Wild. The paper.[pdf] (title song reference)
An awkward resemblance to a certain eigenface might get you pulled aside in Las Vegas. Prof. Hilbert is probably spinning in his grave.
The MPEG-7 Standard, due for release this spring, has a strong information retrieval focus, including face recognition technology fast enough to locate a scene containing a particular person out of 24 hours of video in one second on a conventional computer.
Tampa drops face-recognition system The Tampa Police Department says the system, which scans faces in a crowd and compares them with a database of criminals, didn't help them catch even one criminal. Could it be that law enforcement is starting to understand that technology is no substitution for good old fashioned police work?