Rank One Computing (ROC), the most trusted provider of Facial Recognition algorithms to the U.S. Military, achieved 30-40% improvement in accuracy in its latest algorithm according to NIST FRVT Ongoing benchmarking. No other vendor matched the combination of accuracy and efficiency that Rank One delivered in the report.

“The accuracy of this algorithm is representative of how powerful ROC’s AI/ML face recognition has become on diverse imagery, with accuracy measured on persons from around the world,” said Scott Swann, ROC’s CEO. “The result of this unparalleled accuracy and efficiency is simple: there is almost no FR application that ROC’s algorithm cannot support.”

In this test, Rank One’s new algorithm achieved a 99.21% accuracy rate when False Match Rate is set to 1 in 1,000,000. Further proof of ROC’s leadership from the NIST FRVT report includes:

?  Top 5% of all vendors in template size, comparison speed, and binary size efficiency metrics

?  Top 20% of all vendors in 7 of the 8 benchmark accuracy metrics and template generation speed

?  20x smaller face templates than other comparable algorithms

Dr. Brendan Klare, ROC’s Chief Scientist indicated that “this new release is the first in a promising new line of algorithm R&D being pursued by Rank One and includes several new SDK enhancements and features.” The SDK v1.26 release will be followed by another new algorithm release at the start of 2022 that is poised to further deliver substantial reductions in error rates.

As security and trustworthiness continues to be a primary consideration for both government and commercial buyers, Rank One continues to surge as the only trusted top-tier, U.S.-owned developer of FR Algorithms. Come see us at Connect ID in Washington, DC Oct 5-6 or contact us at [email protected] today to learn more about our Artificial Intelligence, Computer Vision, and software system solutions and how they can solve your mission’s needs.


Press Release 

Share This