NtechLab scores highest biometric matching accuracy rates in three NIST test categories
NtechLab is trumpeting its success in the recent Face Recognition Vendor Test (FRVT) from the U.S. National Institute of Standards and Technology (NIST), in which the company’s facial recognition algorithm was found to have the highest biometric matching accuracy ever in three different categories of the 1:1 Verification benchmark.
The algorithm from NtechLab scored the lowest error rate in the Visa Photos, Visa Border and Border Photos categories, and second for the Mugshot Photos database. The company says it has also tested in the top three for efficiency in identifying people wearing masks.
More than 100 algorithms were submitted for the NIST benchmark from developers around the world.
“In the last few years, the competition in the field has increased, as well as the accuracy and the of the competitor algorithms,” states NtechLab Co-founder and Head of its Neural Network Research Lab Artem Kukharenko. “Today we can say with certainty that the NtechLab intelligent video-analytics platform is the best worldwide judging by a whole range of criteria. To achieve this result NtechLab engineers used the most innovative methods for neural network training and new algorithms for data processing and preparation for machine learning. The results of these developments are already implemented in NtechLab products and will serve to improve the safety and comfort of smart cities’ population across the world.”
Kukharenko told Biometric Update in an interview last year that the company’s algorithms can process feeds from 100 video cameras on a single GPU.
NtechLab has also had strong showings in testing by IARPA, the WIDER Pedestrian Challenge, and the ActEV-PC, according to the announcement.
The company also raised $15 million to expand the adoption of its face biometrics around the world in 2020.
Related Posts
Article Topics
accuracy | algorithms | biometric identification | biometric matching | biometric testing | biometrics | facial recognition | NIST | NTechlab | Russia
Comments