Face recognition accuracy of forensic examiners, super recognisers, and face recognition algorithms

This is the first study to measure face identification accuracy for an international group of professional forensic facial examiners, working under circumstances that apply in real world casework. Examiners and other human face “specialists”, including forensically trained facial reviewers and untrained super-recognizers, were more accurate than the control groups on a challenging test of face identification.

Therefore, specialists are the best available human solution to the problem of face identification. We present the first data comparing state-of-the-art face recognition technology to the best human face identifiers. The best machine performed in the range of the best humans, professional facial examiners. However, optimal face identification was achieved only when humans and machines worked in collaboration.

The talk is based on Phillips, P. J., et al. "Face recognition accuracy of forensic examiners, super recognizers, and face recognition algorithms." Proceedings of the National Academy of Sciences (2018):201721355.

Short biography

Dr P. Jonathon Phillips received BS degree in mathematics and MS degree in Computer and Electronic Engineering from George Mason University, and PhD degree from Rutgers University. Jonathon is a leading researcher in the fields of computer vision, face recognition, biometrics, and forensics at the National Institute of Standards and Technology's Information Technology Laboratory. He has published over 100 peer reviewed papers in face recognition, computer vision, biometrics, psychology, forensics, statistics, and neuroscience. His papers have received over 30,000 Google citations.  He is an IEEE Fellow and an International Association of Pattern Recognition (IAPR) Fellow.

Dr. Phillips pioneered competitions to improve technology in face recognition, computer vision, and biometrics. The programs and competitions that Jonathon managed were instrumental in advancing face recognition from its infancy in research labs to deployment in real-world applications. He won the IEEE inaugural Mark Everingham Prize, the IEEE Biometrics Council Leadership Award, the Dept. of Commerce Gold Medal, the Dept. of Commerce Bronze Medal, Office of the Secretary of Defense Medal for Exceptional Civilian Service, and Federal Bureau of Investigation CJIS Assistant Director’s Award for Outstanding Scientific Achievement.