New face recognition technology from NEC that can identify suspicious individuals among crowds has been successfully trialled at a stadium in the US.

The Intel-powered NEC NeoFace was found to be able to quickly and accurately identify faces within a crowd of moving people in tests conducted by the US National Institute of Standards and Technology (NIST). NEC NeoFace uses Intel Arria 10 field programmable gate arrays (FPGAs) operating on Intel Xeon processor–based servers to increase performance to a level where an individual can be identified smoothly from a high-resolution image with dozens of faces.

The NIST tests compared NEC NeoFace against rival products in two real-life situations, with one taking place at an airport and another at an indoor stadium. NEC NeoFace was ranked No.1 in almost all tests, specifically for face-in-video evaluation.

In the NIST stadium test, the technology was asked to detect suspicious individuals. An individual was situated far from the camera, with their face direction changing frequently. NEC’s face recognition technology won first place with an error rate half that of the second place error rate.

“Facial recognition in a moving crowd requires highly advanced techniques when compared to still images because these cameras are affected by many factors: camera location, image quality and lighting, along with the subject’s size, walking speed and face direction,” said Tadashige Kadoi, general manager of IoT Platform Development Division, NEC Corporation.

“Intel FPGAs and their parallel processing capability help NEC to enable fast and accurate collection and processing of images from even 4K high-resolution remote cameras.”

Fans attending this season’s Uefa Champions League final were scanned by face recognition cameras in Cardiff’s Principality Stadium as part of a police operation.

Image: NEC