Mantra Softech joins NIST facial recognition tests for verification and identification

Mantra Softech has participated for the first time in The National Institute of Standards and Technology (NIST)’s Face Recognition Vendor Tests (FRVT) 1:1 and 1:N for biometric accuracy.

In the November 22 update of the FRVT 1:1, which assesses the accuracy of biometrics systems in matching faces against individual images, Mantra had the 57th lowest false non-match rate (FNMR) in the VISA Photos category.

In the FRVT 1:N, which assesses the accuracy of biometric algorithms in matching faces against large databases, Mantra Softech’s top result was 29th in matching mugshots against webcam images in investigation mode, with a false negative identification rate (FNIR) of 0.010.

Mantra Softech specializes in facial recognition for access management, public security, and border control.

“Mantra Softech has long supported the responsible and ethical usage and development of biometric technology,” comments Hiren Bhandari, technical director of Mantra Softech, according to APN News.

According to the executive, the test results demonstrate the company’s competence in AI-based facial recognition research as well as the sophistication of its technology.

“We strive to be innovative by introducing new biometric technologies on a regular basis. We take pride in being one of the few companies capable of developing biometric hardware and software,” Bhandari concludes.

The announcement of the FRVT results come weeks after Mantra Softech announced it will deploy almost 25,000 of its mTerminal100 biometric devices across various businesses in Uttar Pradesh.

Article Topics

accuracy  |  biometric identification  |  biometric matching  |  biometric testing  |  biometrics  |  face biometrics  |  Face Recognition Vendor Test (FRVT)  |  facial recognition  |  facial verification  |  identity verification  |  Mantra Softech  |  NIST