Neurotechnology, a provider of deep learning-based solutions and high-precision biometric identification technologies announced that the company returned to the top ranking in the National Institute of Standards and Technology (NIST) Proprietary Fingerprint Template III (PFT III) evaluation.
PFT III evaluation
The PFT III evaluation presents fingerprint verification benchmarks using four different datasets of fingerprints, in almost all of which Neurotechnology's latest algorithm submission presented the most accurate scores.
For several years Neurotechnology's algorithms were consistently leading the PFT III evaluations, however, the company's top position was challenged a few months ago. With this latest submission, Neurotechnology regained the leading position, demonstrating decades of experience in developing top-level algorithms.
Regaining top position
We were intrigued to see other submissions challenge our algorithm, which has been the leader in evaluation"
"We were intrigued to see other submissions challenge our algorithm, which has been the leader in the evaluation for years," said Evaldas Borcovas, biometric research lead at Neurotechnology.
"As competition arises, so does our team's motivation and dedication to push the boundaries of our technology even further, and we are thrilled to be at the top of the PFT III evaluation once again."
Accuracy with a new algorithm
The PFT III showcased results consisting of two criminal case datasets from the Arizona Department of Public Safety and the Los Angeles County Sheriff's Department as well as two border control datasets from the US Department of Homeland Security.
Fingerprint matching experiments were undertaken using each dataset separately with multiple benchmark scores for each participant. Neurotechnology's latest algorithm submission performed as the most accurate in the majority of experiments across all four datasets.
Biometrics
Neurotechnology, as a multi-biometric solutions developer, is also an active participant in other NIST evaluations of different biometric modalities.
Over the years, the company's algorithms have been among the top performers in evaluations including MINEX III, IREX 10, FRVT, ELFT, and SlapSeg III.