ROC заняла первое место в мире по точности и скорости поиска отпечатков пальцев в тестах NIST

Demonstrates category-leading speed, strong Rank-1 accuracy, and the operational efficiency of ROC’s American-made technology NIST ELFT benchmarks for the FBI and DoD are a key factor in determining technologies selected by U.S. government agency investigative programs Multiple #1 Rank-1 accuracy results across real-world investigative data strengthens technical position in biometrics and forensics markets DENVER, CO, July 16, 2026 (GLOBE NEWSWIRE) -- Rank One Computing Corporation d/b/a ROC, (Nasdaq: ROC) ("ROC” or the "Company”), a U.S. leader in Vision AI, building unified biometric, video analytics, and decision intelligence solutions, announces its latest technical achievement demonstrating the fastest latent fingerprint search speed along with multiple Rank-1 accuracy wins in the NIST Evaluation of Latent Fingerprint Technologies (ELFT) across key datasets utilized by the FBI and U.S. Department of Defense (DoD). This recognition reinforces ROC’s American-made technology as a category leader in speed, accuracy, and efficiency, when evaluated against the benchmark consisting of 22 total vendors. Additionally, ROC’s performance amplifies the scale and operational readiness the Company delivers as a trusted domestic ABIS alternative to legacy foreign biometric technology. Notable NIST ELFT accuracy results include a #1 global Rank-1 accuracy on the Extended Feature Set (EFS) subset of the FBI-Provided Solved Dataset, a tie for #1 among Western providers in Rank-1 accuracy on the FBI Laboratory Dataset, and error-rate improvements of up to 2x across evaluated FBI and DoD benchmark conditions. "Latent fingerprint recognition is one of the most technically challenging evaluations in biometrics, due to distorted or partial evidence utilized in analysis against sizable identity databases. These latest NIST ELFT results show that ROC is delivering the speed, accuracy, and scalability the FBI and DoD, our country’s most critical agencies, need to move investigations forward faster. They also reinforce a broader point: American-made biometrics can lead globally in the technologies that support public safety, national security, and the critical identity infrastructure America depends on,” said ROC CEO B. Scott Swann. ROC’s technical excellence is reflected by earning its position as the fastest latent fingerprint algorithm in the NIST ELFT. ROC’s score was approximately 64x faster than the mean of the top five vendors evaluated in the benchmark across the FBI and DoD investigative datasets. Importantly, when evaluated against this same benchmark cohort and dataset, ROC delivered this impressive speed while retaining top-tier accuracy in False Negative Identification Rate (FNIR) at Rank-1. This third-party support presents compelling results for agencies to consider, proving they do not have to choose between faster searches and stronger candidate returns, or between operational efficiency and investigative performance. With consistent technical execution across real-world investigations by high-stakes government agencies, ROC is well-positioned to assume its role as the trusted domestic technology building critical identity infrastructure. ROC believes the combination of high accuracy and top search speed strengthens both the operational and economic rationale for large-scale deployments. ROC designs its algorithms for efficiency, offering solutions that reduce processing requirements, improve system throughput, and support a lower total cost of ownership. This aligns with government agencies, national security, and law enforcement’s objectives to expand their use of technical applications and modernize biometric infrastructure as they evaluate next-generation high-throughput Automated Biometric Identification System (ABIS) and digital forensic capabilities. The results build ROC’s credibility following its NIST ELFT submission in the first quarter of 2026, delivering the highest Rank-1 accuracy, fastest search speeds, and smallest template size in the DoD dataset, the largest dataset in the evaluation. Additionally, ROC’s recent outperformance in the NIST Friction Ridge Image and Features (FRIF) Technology Evaluation resulted in #1 global identification accuracy across several benchmarks used to evaluate national identity and border-control applications. Collectively, these independent NIST evaluations fortify ROC’s technical position across variable environments and datasets for fingerprint recognition, reinforcing its ability to support high-performance fingerprint identification across ABIS applications. Dr. Brendan Klare, ROC Chief Scientist and Co-founder added, "What stands out in this ELFT submission is ROC’s optimization of both accuracy and throughput. The low error rates across multiple benchmark conditions, combined with the fastest search speed, shows continued leadership and progress on the two outcomes that materially affect large-scale latent search: candidate quality and system throughput. These gains are especially meaningful in large-scale deployments, where performance, compute, and total cost of ownership must be considered together.” NIST benchmarks are widely referenced in federal, defense, and international agency vendor evaluations. With its unified Vision AI platform, ROC addresses the escalating market demand for forward-thinking identification and intelligence solutions, strengthening both mission outcomes and business fundamentals. For customers, it delivers NIST-ranked biometric accuracy with reduced infrastructure complexity and total cost of ownership. For ROC, it supports a scalable software model with a durable recurring revenue profile and attractive margins. The NIST Evaluation of Latent Fingerprint Technologies (ELFT) is an independent benchmark for measuring the performance of automated latent fingerprint matching algorithms. For agencies evaluating latent fingerprint capabilities, NIST ELFT provides a common framework for understanding how algorithms perform across challenging forensic search scenarios, helping them assess accuracy, speed, and operational fit before making technology decisions. NIST evaluations do not constitute endorsement of any vendor, product, or technology. Read ROC’s Blog Post and Full NIST Scores here. About ROC ROC is a leading U.S. developer and manufacturer of Vision AI, delivering sovereign biometrics, video analytics, and mission intelligence through a unified platform. This enables agency and integrator partners to unlock faster, more accurate, and cost-efficient capabilities. At its core, ROC transforms raw pixels into real-time operational awareness for defense, public safety, and digital commerce. The Company is headquartered in Denver, Colo., with additional hubs in Grand Rapids, Mich., and Morgantown, W.V. For more information, please visit the Company’s website: www.roc.ai. Media inquiries: Matt Aitken, VP of Marketing Investor inquiries: CORE IR