Innovatrics wins NIST FRVT 1:1 Wild category with highest biometric accuracy

Innovatrics has scored a win in the “Wild” category of NIST’s Ongoing Facial Recognition Vendor Test (FRVT) 1:1, providing a testament to the biometric algorithm’s highly reliable and accurate performance for digital onboarding for retail, surveillance, and security applications, according to a company announcement.

The accuracy and efficiency of Innovatric’s face recognition algorithms are constantly enhanced by the deep convolutional neural networks they utilize, enabling faces to be identified and verified in low-grade conditions, the company says.

“Our long-term focus is on leveraging AI technology to identify and verify real-world faces as accurately as possible. This result is a confirmation of our team’s efforts to continuously improve and deliver the best face recognition solutions on the market,” explains Marián Beszédeš, Head of Research and Image Processing at Innovatrics.

The winning algorithm is a core part of Innovatric’s IFace library, which the company’s flagship ABIS, SmartFace, and Digital Onboarding Toolkit products use. Innovatrics launched the 7th edition of its ABIS product just weeks ago.

CyberLink has announced it scored a False Non-Match Rate (FNMR) of only 2.1 percent in VISA matching under 1E-06 conditions, putting it among the top 20 vendors in the NIST FRVT 1:1 test category.

The algorithm used in CyberLink’s FaceMe Facial Recognition Engine also performed faster than those of all but two vendors in the VISA 1E-06 top 20.

“This ranking will help further FaceMe’s prominence as one of the world’s leading facial recognition SDK and makes our solution one of the best options for smart retail, banking, security, government, and AIoT services and products,” comments CyberLink CEO Jau Huang.

The company added face tagging to its photo editing software in a release earlier this week.

Article Topics

accuracy  |  biometrics  |  CyberLink  |  facial recognition  |  Innovatrics  |  NIST  |  testing