Rank One Computing Corporation has achieved the top performance ranking in the National Institute of Standards and Technology’s Evaluation of Latent Fingerprint Technologies (ELFT), earning the lowest False Negative Identification Rate at Rank-1 on the U.S. Department of Defense-provided dataset. The DoD dataset, comprising 5,259 latent probes, is the largest in the evaluation, making it the most demanding subset of the benchmark.
ROC also achieved the top Rank-1 accuracy, fastest search speeds, and smallest template size on the dataset. The NIST ELFT program is widely regarded as the most rigorous independent benchmark for latent fingerprint matching and is routinely cited in agency procurement evaluations for automated biometric identification systems (ABIS).
The result comes days after ROC closed a $24M IPO on Nasdaq, and carries particular weight for agencies evaluating ABIS vendors at a moment when NIST fingerprint benchmark competition has intensified in early 2026. In February, Innovatrics had claimed the top NIST ELFT Rank-1 accuracy; ROC’s new result on the larger DoD dataset puts it ahead on the benchmark’s most demanding evaluation.
“Latent fingerprint identification is one of the most challenging problems in biometrics. Achieving the lowest FNIR at Rank-1 on the largest dataset in ELFT reflects years of focused algorithmic innovation. Our goal is not just to perform well in controlled settings, but to deliver consistent, high-confidence matching under real operational conditions,” said Dr. Joshua Engelsma, Principal Scientist at ROC.
The company also emphasized algorithmic efficiency as a differentiator. “Performance at scale demands more than just accuracy; it requires a critical balance of precision and efficiency. Our algorithms are optimized to deliver consistent, low-latency performance even across millions of records,” said Keyur Patel, Director of Machine Learning at ROC.
ROC has been building a portfolio of third-party validations: it achieved MOSIP certification in August 2025 and is now competing for large-scale ABIS contracts with law enforcement, intelligence agencies, and government identity programs. The company highlighted that its benchmark performance reflects algorithmic efficiency that reduces total cost of ownership, positioning its technology against what it characterized as “legacy technology providers.”
Latent fingerprint analysis remains central to law enforcement and intelligence investigations, where partial or degraded prints recovered from crime scenes must be matched against large enrolled databases. NIST ELFT specifically tests this scenario, evaluating both accuracy and speed across datasets of varying quality and scale.
Sources: Globe Newswire, NIST
–
By the ID Tech Editorial Team
