Researchers at the University of Brigham, led by Heather Flowe, have developed an Interactive Face Recognition System (I-FRS) that utilizies naturalistic 3D models of faces that enable the user to dynamically view faces from multiple angles. This technology greatly improves human face recognition and face-matching accuracy, compared to other methods currently used by criminal justice, border control, and law enforcement agencies.
I-FRS improves upon traditional methods, since police lineup photos now only show the front-on view of the criminals, but this setup, tested on 3000 volunteers, shows various angles that could help witnesses identify suspects. One example would be the volunteer group being shown a video of a man in his thirties who stole a woman’s handbag. Some were shown a video in which which the man’s face was only seen from the left, while others saw a different angle.
- Aspect Ratio:16:9
- NVIDIA GeForce GTX 1650 Ti 4GB GDDR6 Graphics up to 1585MHz at 80W TGP.
- Quad-core Intel Core 15-10300H Processor (8M Cache, up to 4.5 GHz, 4 cores)
There are good reasons to predict that accuracy will be higher if witnesses are able to manipulate images and align them to be similar to the angle of the face in their memory. We know that retrieving memories accurately relies on the context in which they are retrieved being similar to when the memory was formed. The experiments we carried out show this theory in practice,” said Dr. Melissa Colloff, co-author of a paper on the study.
