Author: Tronserve admin
Friday 30th July 2021 06:49 AM
NEC Face Recognition Tech Ranks First in U.S. Test
NEC Corp reveals that its face recognition technology attained the highest matching accuracy in the Face Recognition Vendor Test (FRVT) 2018 executed by the U.S. National Institute of Standards and Technology (NIST), at an error rate of 0.5% when registering 12 million people.
NEC’s technology placed No. 1 in NIST testing for the fifth time, since its top placement in the face recognition testing for video in 2017. The high performance of NEC’s technology is shown in the test results which put the company dramatically ahead of the runner-up.
In recent times, the flourishing convenience of biometric authentication technology, improved security awareness, and the exceptional development of artificial intelligence (AI), have driven companies everywhere to start adopting biometric authentication technology. Specifically, the use of face recognition technology is dramatically stretching across a wide range of fields throughout the world. Face recognition technologies are now being used in areas that require high reliability, convenience and long-term use, for example identity verification and national infrastructure, transaction settlements, bank account establishment, and passport verification.
Forty-nine organizations, including companies from the United States, China, Russia, Europe, and Japan, participated in the NIST’s FRVT 2018, where the evaluation of face recognition accuracy was conducted. These tests are the most extensive and fair benchmarks implemented by the NIST as each organization is required to submit and be evaluated on programs that were developed during the same period. By performing multi-stage matching, an impressive search speed of 230 million matchings per second was achieved. Not only that, leveraging NEC's deep learning methods to considerably reduce the identification error rate, NEC accurately matched images of a subject taken over a 10-year interval with an error rate that was 4 times lower than the runner-up.