Yitu Technology ranks first in NIST global facial recognition benchmark test
Chinese facial recognition firm Yitu Technology ranked first in four different categories of National Institute of Standards and Technology’s (NIST) Face Recognition Vendor Test (FRVT) benchmark, beating out top facial recognition firms, Vocord and OT-Morpho.
FRVT serves as the official guideline for U.S. government purchases, while the test results are recognized as the golden standards of global security industry in practice.
The test datasets of FRVT all stem from real-world scenarios provided by the U.S. Department of Homeland Security, such as the massive number of photographs taken by border control agencies and in criminal investigations.
The test dataset scale in the order of millions and are not publically available, ensuring that the results are not susceptible to algorithmic over-fitting or other unfair practices.
Yitu ranked in first place by achieving a 95.5 percent accuracy rate, subjected to the false match rate of ten-millionth (based on 10 billion samples). The firm’s results are 2 percent higher than Vocord, whose accuracy is 93.5 percent.
This marks the highest accuracy rate achieved in a public evaluation based on the large scale dataset, which shows a significant increase from 2014 when NEC, a Japanese company, ranked first.
FRVT evaluates recognition performance in details concerning different scenarios, ethnicities, genders and ages, while the benchmark’s test dataset covers real-world scenarios such as border control, ID passes and city-level security.
Yitu’s algorithm was consistent in its performance in detailed ethnicities and gender tests. However, as the difficulty increases, the algorithms submitted by its competitors declined in recognition accuracy.
The results justify the adaptability of Yitu’s algorithm on different datasets of various real-world scenarios.
The full report as of June 19, 2017 can be viewed on NIST’s website.