ROC Ranks Top 3 Globally for Accuracy at NIST ELFT – with Speeds 500x Faster Than Industry Standard

A thought leader in computer vision and biometrics, ROC continues to make a compelling case for U.S. homegrown technology with a strong showing in its first ever NIST Evaluation of Latent Fingerprint Technologies (ELFT)

Top 3 global algorithm in accuracy for latent fingerprint recognition.
Scoring on both distal prints and palm prints when aggregating rankings across all datasets and accuracy metrics.

#1 global algorithm in efficiency for latent fingerprint recognition.
At 15 seconds, ROC search is over 150x faster than the next closest competitor (42 minutes). 

ROC also ranked as the #2 most accurate global algorithm in the FBI Laboratory dataset and #2 most accurate global algorithm in latent palmprint search. All testing was performed on ROC SDK v3.0 by NIST ELFT as of February 2, 2024.  

Achieving top 3 global ranking for accuracy cements ROC as one of the top latent fingerprint matchers in the world. But what really has experts buzzing is their signature formula of top-tier precision paired with unprecedented velocity. ROC’s lightweight, edge-optimized algorithms are poised to unlock new opportunities across law enforcement, border security, counterterrorism, and beyond. 

“Law enforcement has relied on fingerprint technology for over 120 years. Algorithms have gotten very good at matching high-quality fingerprints, but matching latent or partial fingerprints has been a persistent challenge that typically requires 45+ minutes. The fact that our algorithm makes incredibly accurate latent matches in just seconds opens a whole new world of applications. Just think about the importance of speed and accuracy at border crossings as we begin to realize some of these new opportunities.”

 Scott Swann, CEO of ROC

The Need for Speed: Empowering a New Era of Public Safety

From crime scene investigations to cold cases, ROC latent fingerprint algorithms will enable powerful new use cases by cutting down response times to seconds and extending capabilities to edge and mobile. Potential scenarios include instantly verifying identities at traffic stops against forensic databases, missing persons lists, most wanted lists, and so on, removing critical bottlenecks to sensitive intelligence and enabling real-time decision making for officers in the field. 

“We are just beginning to shake up the world of fingerprint matching. By combining the latest developments in computer vision (CV) and machine learning (ML) with tried-and-true, decades-old methods of fingerprint matching, we have our sights set on substantial improvements to our already top-tier latent fingerprint matcher in the very near future.”

Dr. Joshua Engelsma, Senior Scientist, ROC

“We’re excited to push the state of machine-learned CV algorithms to other modalities beyond face recognition. Significant advancements in fingerprint technology have been few and far between. We are now turning that tide thanks to the efforts of our new fingerprint center of excellence in Grand Rapids, Michigan. We look forward to working closely again with fingerprint experts across the globe to bring these impactful capabilities to our customers.”

Dr. Brendan Klare, Co-Founder and Chief Scientist at ROC

Meet the Computer Visionaries

ROC has assembled a powerhouse team of industry veterans to augment their stable of young computer vision talent and propel ROC into the future. Along with Swann, the former CEO of IDEMIA National Security Solutions with nearly three decades of biometric experience, including 18 years at the FBI, ROC recently added Benji Hutchinson, who led similar major programs as President of NEC National Security Systems and President & COO of Paravision. Collectively, the ROC team has extensive knowledge in deploying cutting-edge fingerprint technologies and is well-versed in the standards and scientific underpinnings required to deliver these highly advanced, next-generation applications.   

As evidenced by NIST ELTF testing, we have begun to see a pattern of disruptive U.S.-based entrants emerging, often holding a fast-moving, innovative edge over traditional foreign biometric providers. Thanks to ROC, there is now an entrant putting America at the top of global rankings and proving that homegrown computer vision and artificial intelligence researchers are among the best in the world. 

Making the world smarter, safer, and stronger.
As the only American-made multimodal biometrics and computer vision provider, ROC is trusted by the U.S. military, law enforcement, and leading FinTech brands. The company has offices in Denver, CO, Morgantown, WV, and a new fingerprint center of excellence in Grand Rapids, MI. ROC multimodal solutions deliver game-changing results with battle-tested reliability across NIST government testing, military applications, and 200M+ annual identity proofing transactions. 


Share This