As iris biometrics takes on greater prominence, Neurotechnology touts NIST results

Iris recognition is taking a more prominent place amongst biometric modalities in recent months, between a series of developments on both the public sector and commercial sides of the market. As the technology and market for it mature, evaluations like one just completed by Neurotechnology go from indications of readiness to important data for decision-makers.

Apple’s latest consumer electronics device, the Vision Pro virtual reality headset, uses iris biometrics, adding Optic ID to the company’s established biometrics brands, Touch ID and Face ID.

Worldcoin has continued to raise hundreds of millions of dollars in funding for its project combining iris biometrics, digital identity and cryptocurrency.

National ID programs like those in Pakistan, Togo and Jordan are building in iris to enable high accuracy identity verification and deduplication at scale. In the Philippines, electoral authority Comelec has begun pushing for iris to be included in voter registration after finding half a million duplicates on its voter rolls.

As these and other important programs adopt the modality, the importance of independent testing grows.

Neurotechnology scores high marks in NIST evaluation

Neurotechnology recently submitted its latest iris recognition algorithm to the NIST IREX 10 evaluation, scoring single-eye accuracy of 99.14 percent and two-eye accuracy of 99.73 percent.

The miss rate for scored by Neurotechnology’s algorithm’s Rank1 results, meaning the top-ranked match is a correct match, are the best result the test has yet recorded, according to the announcement. The company emphasizes the importance of this metric for real-time use cases in law enforcement, civil registration, and visitor management systems.

The assessment shows higher accuracy for Neurotechnology’s latest algorithm across all categories, including a false non-identification rate (FNIR) of 0.0107 at false positive identification rate (FPIR) of 0.01 for single-eye matching. For both eyes, FNIR at FPIR 0.01 was 0.0033. These results placed Neurotechnology 5th and 6th, respectively, amongst the 29 algorithms on NIST’s leaderboard as of June, 2023.

“We are excited to achieve the top accuracy in NIST’s evaluation categories and are thrilled to see our algorithm’s miss rate almost twice as low as the closest competitor in some assessments,” says Evaldas Borcovas, biometric research lead at Neurotechnology. “I believe this submission to IREX 10 is one extra step toward our goal to develop overall the most accurate iris recognition algorithm.”

Article Topics

accuracy  |  biometric testing  |  biometrics  |  IREX  |  iris biometrics  |  Neurotechnology  |  NIST