IREX 10 Evaluation
These comments provided by Neurotechnology are based on NIST IREX 10 results, reviewed on May 25, 2026.
Neurotechnology's iris recognition algorithm ranked first in all IREX 10 evaluation categories. It achieved the highest accuracy in both single-eye and two-eye assessments, for both FNIR@FPIR 0.01 and Rank 1 metrics.
The IREX 10 evaluation is an ongoing evaluation of automated iris recognition algorithms, which is run by NIST. Different vendors submit their biometric algorithms for the evaluation. The tests are run over operational data for identification (one-to-many) tasks. See IREX 10 official page for more information.
The main goals of the IREX 10 evaluation are: assess the current state of the art, facilitate research and development, assess the impact of demographics, twins and automated quality assessment.
The evaluation has started in October 2019 and continues till now. The participants can submit their algorithms every 3 months, but the results are shown only for the two latest submissions.
Our latest submission was done in May, 2026. There were 35 companies with 147 submissions participating in the evaluation as of May 25, 2026.
The provided accuracy metrics are: FNIR at FPIR 0.01 and Rank 1.
Two-eye assessment
The Two-eye assessment uses a biomettric dataset with 1,000,000 iris images, which correspond to 500,000 persons with 2 iris images per person. Neurotechnology ranked first in all categories, with a 99.83% Rank 1 accuracy rate.
The charts below show the results for our latest submission.
Click to zoom
Click to zoom
Click to zoom
Single-eye assessment
The Single-eye assessment uses a biometric dataset with 1,000,000 iris images, which correspond to 1,000,000 persons with 1 iris image per person. Neurotechnology ranked first in all categories, with a 99.58% Rank 1 accuracy rate.
The charts below show the results for our latest submission.
Click to zoom
Click to zoom
Click to zoom
See the IREX 10 official page and full report for more information on the IREX program and testing methodology.
