Cognitec lauds combination of biometric accuracy and speed shown in NIST test

Cognitec has announced that the latest results from the U.S. National Institute of Standards and Technology’s (NIST’s) face biometrics testing show its algorithm delivers the best tradeoff between biometric accuracy and speed.

In the September 21 Face Recognition Vendor Test (FRVT) 1:N report, the cognitec-005 algorithm showed the best combination of fast template generation time and low false negative identification rate for mugshot databases among entries from 85 vendors, the company claims.

The identification tests apply a very high matching threshold, with a false match rate of only 0.3 percent, making it a suitable evaluation for biometric algorithms used in the detection of duplicates in image databases and fraud detection during passport and driver’s license applications, according to the announcement.

Cognitec also recently supplied the face biometric algorithm for automated gates deployed by Veridos to an airport in Bangladesh.

“We are proud to also see significant accuracy advances in comparison to the algorithm we submitted to the last test in early 2021,” says Cognitec Director of Algorithm Development Dr. Thorsten Thies. “For the test with 12 million mugshot images, Cognitec achieved rank 24 of 165 algorithms with a match rate of 98.5 percent. In the test with 1.6 million mugshots, with a 99.4 percent match rate, we ranked 26 of 299 algorithms. These results show remarkable performance consistency, regardless of database size.”

Article Topics

accuracy  |  algorithms  |  biometric identification  |  biometric testing  |  biometrics  |  Face Recognition Vendor Test (FRVT)  |  facial recognition  |  NIST