Entrust face biometrics show major gains in NIST FRTE

A face biometrics algorithm submitted by Entrust to the NIST Face Recognition Technology Evaluation (FRTE) 1:1 Verification has made significant gains in accuracy over the previous versions.

The latest version of the Onfido facial recognition algorithm placed 178th in the VISA-BORDER category as of the January 23, 2026 update. That represents a leap of more than 100 places from 289th, where its predecessor placed  in the same category. The algorithm was also ranked 131st in the BORDER-KIOSK comparison, 146th in the BORDER-BORDER category and 181st for comparisons of BORDER probes to a gallery of VISA images with Yaw equal to or greater than 45 degrees.

Submitted to NIST during December, onfido_002 is the third Onfido algorithm entered into FRTE. The previous two were submitted in 2023 and earlier in 2025, respectively.

“We’re going for top-100 soon, then hopefully top-10,” Entrust Director of Engineering Daniel Serrano told Biometric Update in an email.

Entrust acquired Onfido for more than $400 million in the first half of 2024, and has integrated its face biometrics into its digital and government services portfolio. Serrano had spent nearly eight years with Onfido by then, including in the same role he now holds with Entrust.

The company also formed a strategic collaboration with Google earlier this month to bring its identity verification tools to Google Cloud.

Article Topics

algorithms  |  biometric testing  |  biometrics  |  Entrust  |  face biometrics  |  Face Recognition Technology Evaluation (FRTE)  |  facial recognition  |  NIST