Even the world’s best available training – used to train police, border control agents and other security personnel – does not compensate for natural talent in face recognition.
The first study to compare performances of trained facial examiners, super-recognisers, and facial-recognition algorithms, has revealed a combination of human and computer decision-making is most accurate.
Face-matching experts using automatic face recognition software at the Australian Passport Office are 20% more accurate than average people at detecting fraud, new research shows.
The first study to test the skills of FBI agents and other law enforcers trained in facial recognition has found they perform better than the average person or even computers on this difficult task.
Improving human performance in matching unfamiliar faces in passport control will help ensure the security and safety of Australians, writes David White.