“In addition to the upgrades to Rank One’s facial recognition algorithms, the improved SDK also delivers a new ‘periocular’ algorithm designed to identify an individual based on the area around their eyes…”
Rank One Computing has announced considerable enhancements to its flagship Software Development Kit solution.
The most important upgrade comes by way of a new facial recognition algorithm delivering a 50 percent error rate reduction and a 50 percent improvement in template generation time, Rank One says. Version 1.22 of the ROC SDK also delivers a 15 to 40 percent reduction in the error rate of its “FR Fast” algorithm, and a 10 percent reduction in that algorithm’s template generation time.
“ROC SDK version 1.22 represents the culmination of more than a year’s research,” explained Rank One Chief Engineer Scott Klum in a statement announcing the SDK upgrade. “For the firsttime, we’ve been able to deliver not only significant accuracy improvements but also significantspeed improvements in our face recognition pipeline – a noteworthy achievement as we already had one of the fastest face recognition algorithms on the market.”
In addition to the upgrades to Rank One’s facial recognition algorithms, the improved SDK also delivers a new ‘periocular’ algorithm designed to identify an individual based on the area around their eyes, a capability that Rank One has framed as a solution for the COVID-19 age, when wearing face masks has become commonplace around the world. Additionally, ROC SDK v1.22 features a new tattoo recognition algorithm aimed at aiding law enforcement investigations.
Rank One is bringing the improvements to all clients currently using active-maintenance licenses, and is offering technology demonstrations to any new prospective customers, who are invited to reach out to the company directly.
May 14, 2020 – by Alex Perala