Sets a new standard for face detection when wearing PPE
SAFR from RealNetworks announced improved face detection and recognition accuracy for both masked and unmasked faces with the release of SAFR 3.0. Available now, SAFR?s 3.0 release introduces a new default high sensitivity face detector.
Customers running the high sensitivity face detector will see a 95.1% detection rate and 98.85% recognition accuracy rate for faces covered by PPE face masks ?including non-surgical fabric masks of varying patterns? in surveillance-style videos of faces in motion.
Detection efficiency has also been improved when multiple faces are simultaneously in the field of view to ensure detection and recognition speeds remain high.
?With the 3.0 release, SAFR continues its track record of maintaining high-accuracy under challenging real-world conditions, including the new norms brought by this global pandemic. SAFR?s accuracy improvements will enable customers to deploy face-based contactless secure access without requiring removal of PPE and ensure persons of interest and registered VIPs don?t go unrecognized while wearing face masks,? said Brad Donaldson, VP Computer Vision, SAFR.
SAFR 3.0 also includes a new mask detection dashboard that enables customers to anonymously track mask usage rates and view and filter by age, gender, location, and time. This dashboard joins the existing occupancy and traversal dashboards available in the SAFR web console.
?NTT DOCOMO provides facial recognition service with RealNetworks to the Japanese market. With SAFR?s new functionalities, and in particular the new mask detection feature, we believe that we can enhance the safety and security of people and organizations. We will continue to work with various partners to create new value-added solutions to help solve social issues,? said Hisakazu Tsuboya, Senior Vice President, General Manager of 5G & IoT Business Department, NTT DOCOMO, INC.
SAFR foremost facial recognition platform for live video intelligence. It taps the power of AI to help the world get back to work.