Rank One Computing launches iris biometrics with fastest speed in NIST test
Rank One Computing (ROC.ai) has announced the launch of their iris recognition software, complementing its established business lines in face and fingerprint biometrics, as well as weapons and object detection.
In NIST’s IREX evaluation, ROC.ai has the fastest mean search speed of all vendors at 0.11 seconds when tested on a database of 1 million iris scans, with an algorithm submitted in October. It also has a true match accuracy in searching two eyes at 99.3 percent and false positive identification rate of 1.0 percent.
According to a release, ROC.ai managed to create an algorithm with a competitive speed in less than six months, demonstrating the potential of American biometrics companies. Its algorithm is 100 times faster than those of NEC, Idemia, and Thales.
The company notes that iris biometrics are gaining traction in sectors like national security and access control, due to the modality’s high accuracy.
ROC.ai is also the top ranking global face recognition provider in combined accuracy and efficiency. Earlier in the year, ROC.ai announced its first fingerprint matching algorithms. Its tenprint fingerprint segmentation algorithm achieved the top rank by NIST for accurate segmentation of biometrics with a 95.7 percent accuracy for detecting 8 fingers.
“We’re developing from the ground up, here in the U.S., and competing head-to-head with established foreign biometric giants,” says Scott Swann, CEO of ROC.ai. Brendan Klare, chief scientist and co-founder, says the development of iris recognition capabilities builds on past efforts that delivered the industry-leading face and fingerprint recognition algorithms which ROC.ai is known for.
“It is a combination of the pattern recognition scientific principles espoused by the seminal textbook pattern classification, a blue-collar work ethic and mentality, and software engineering trade secrets that for nearly a decade now have landed ROC as the fastest and most efficient computer vision algorithm developer in the world,” Klare says.
