IDEMIA’s biometric technology stands out in the latest international NIST Facial Recognition Vendor Test 1:1 by combining fairness and accuracy

IDEMIA, the global leader in identity technologies, once again reinforces its leadership, as its facial recognition technology ranks first on the false match rate (“FMR”) fairness test among the 100 most accurate algorithms in the latest Face Recognition Vendor Test (FRVT) from the National Institute of Standards and Technology (NIST), with more than twice the fairness of the twenty most accurate.

This ranking is proof that IDEMIA commits to the highest level of technology for its AI solutions in line with its mission to make the world safer through developing state-of-the-art identity technologies. IDEMIA’s algorithm stands out for its capacity to combine both performance and fairness without compromising on either. This confirms its reliability regarding facial recognition solutions, at both government and consumer level.

IDEMIA’s false match rate between different demographic groups hardly differs. The algorithm identifies all subjects equally well, regardless of demographic. Its advances in reducing the risk of discrimination are in line with IDEMIA’s ambition to achieve responsible and ethical use in developing AI technologies.

These results are in line with IDEMIA’s previous rankings, which confirm its leading position in biometric technologies.

Indeed, IDEMIA has also maintained its position in the top 3 of the FRVT 1:N Identification ranking, with 99.88% rank 1 accuracy against a 12 million dataset.

Additionally, IDEMIA’s iris recognition technology renewed its 1st place for Single-eye Accuracy with its latest submission to IREX 10 benchmark.

On fingerprint recognition technology, IDEMIA’s AFIS-class algorithm ranked first on most datasets in the PFT III benchmark, which measures the performance of one-to-one fingerprint matching with proprietary templates.

IDEMIA technology leads the competition on all three main biometric modalities.

NIST’s FRVT results are further evidence of the highest standard we have set with our suite of facial recognition technologies, positioning fairness as a key criterion, in addition to accuracy. By being more than twice the fairness of the top 20 most accurate, we continue to lead the industry in terms of social responsibilities. IDEMIA is paving the way in the “battle for fairness” and I would like to congratulate our teams of experts on their excellent work meeting this priority.
Jean-Christophe Fondeur, Chief Technical Officer at IDEMIA

Results from the full NIST Face Recognition Vendor Test (FRVT) can be viewed here.

  • About us - As leader in identity technologies, IDEMIA is on a mission to unlock the world and make it safer. Backed by cutting-edge R&D, IDEMIA provides unique technologies, underpinned by long-standing expertise in biometrics, cryptography, data analytics, systems and smart devices.

    IDEMIA offers its public and private customers payment, connectivity, access control, travel, identity and public security solutions. Every day, around the world, IDEMIA secures billions of interactions in the physical and digital worlds.
    With nearly 15,000 employees, IDEMIA is trusted by over 600 governmental organizations and more than 2,300 enterprises spread over 180 countries, with an impactful, ethical and socially responsible approach.
    For more information, visit and follow @IDEMIAGroup on Twitter.

your press contact(s).

Subscribe to our newsletter

Receive our key news and keep up with the trends in our markets by subscribing to our newsletter.

By clicking on the "Subscribe" button, you confirm that you agree to IDEMIA’s Terms of Use and Privacy Policy, and agree to the processing of your personal data and acknowledge your related rights, as described therein.

Your email address will be used exclusively by IDEMIA to send you newsletters related yo your selected topics of interest. In accordance with the law, you have rights of access, rectification and erasure of your personal data, as well as opposition of processing, which can be exercised by writing to