“We’re proud that Paravision has not just the most accurate face recognition but we’ve achieved it with AI ethics at the forefront.” – Joey Pritikin, Chief Product Officer, Paravision
Paravision‘s top-ranking facial recognition technology is now commercially available, with the company’s launch of fifth-generation product suite.
The platform’s flagship solution is its updated facial recognition algorithm, which recently proved to be an industry leader in the National Institute of Standards and Technology’s Face Recognition Vendor Test. In evaluating various algorithms’ capabilities for 1:N matching, the testing program found Paravision’s technology to be the most accurate in the Visa/Border testing category and in the self-service immigration kiosk category – both of which are aimed at testing performance under challenging scenarios in terms of the lighting and positioning of subjects.
The strong performance was the result of enhancements to Paravision’s facial recognition algorithm that had reduced its error rate by 70 percent, attesting to the company’s commitment to research and development.
In announcing the upgraded platform, Chief Product Officer Joey Pritikin emphasized not only the company’s efforts to improve accuracy and usability, but to ensure that its facial recognition product meets an ethical standard.
“Accuracy is essential because reducing errors improves inclusivity and performance for everyone,” he said. “Usability is fundamental since face recognition must work in a wide variety of environments and adverse conditions. Equally important to us is that face recognition must be ethically trained and conscientiously deployed. We’re proud that Paravision has not just the most accurate face recognition but we’ve achieved it with AI ethics at the forefront.”
COO Benji Hutchinson, meanwhile, emphasized that Paravision is “the only U.S.-based company to consistently rank among the top” in NIST testing, adding that this means that “partners can be confident in the performance and integrity of our platform.”
In addition to the facial recognition algorithm at its heart, the upgraded product suite features new facial recognition Software Development Kits for mobile devices on Android and iOS, and an updated Edge AI SDK for the Ambarella platform. The update means that Ambarella-based Edge devices will be able to leverage Paravision’s sophisticated liveness detection and anti-spoofing technology to detect and thwart presentation attacks, even sophisticated attacks using 3D masks.
February 17, 2022 – by Alex Perala