TrueFace jumps into top ten in genuine face biometric template matching time in latest NIST testing

TrueFace jumps into top ten in genuine face biometric template matching time in latest NIST testing

The speed of TrueFace’s algorithm for face biometrics is shown by the latest Facial Recognition Vendor Test (FRVT) results from the National Institute of Standards and Technology (NIST), as the company’s software was ranked seventh among 199 algorithms in genuine template comparison time.

The company notes the importance of template comparison time to real-time streaming deployments at scale in the real world in a Medium post. Fast comparison, according to the company, enables seamless verification in access control applications, and faster alerts in security applications. In any scenario where an algorithm is presented with millions of potential matches each second, speed is essential, TrueFace says.

The latest version of the NIST Ongoing FRVT was published on February 28.

TrueFace technology was able to compare templates in 482 nanoseconds, a significant improvement over previous results, and a somewhat curious one, given that it is the same version of the algorithm being tested. In testing against imposter images, TrueFace’s algorithm ranked 13 out of 199.

“A scrupulous follower of the NIST FRVT reports may have noticed Trueface’s template comparison time improved significantly in the latest report, despite not having made another submission,” TrueFace Computer Vision Software Developer Cyrus Behroozi writes. “Curiously, our very own engineers noticed that our initial submission’s match times did not correlate with the results we had achieved on equivalent testing hardware and operating system and repeatedly contacted NIST several times to explain the difference. While NIST can neither confirm nor deny that Trueface’s own investigative reporting and flagging had anything to do with the updated speeds in their report, let’s just say we’ve stopped calling them.”

TrueFace Founder Shaun Moore explores the importance of automating data control requests with strong identity verification and the role of technologies like face redaction in complying with CCPA regulations in a recent Biometric Update guest post.

Related Posts

Article Topics

 |   |   |   |   |   | 

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics