RealNetworks launches school facial recognition product SAFR in India
RealNetworks Indian subsidiary has launched the company’s SAFR facial recognition technology, which is designed for use in schools, as well as at events and public venues, in the world’s second most populous country.
SAFR achieved a 99.8 percent accuracy score with the Labeled Faces in the Wild (LFW) dataset, based on the University of Massachusetts benchmark, and it has also been ranked as one of the world’s top facial recognition algorithms in “Wild Faces” False Non-Match Rate (FNMR) testing by NIST, according to the company. It works with existing IP-based cameras to provide real-time recognition, and supports both local and cloud storage. The software encrypts all facial data and images, and does not transmit personal or facial data over the internet when used locally.
“SAFR supports numerous secure access use cases where facial recognition can replace the use of an ID badge, securely automate entry to facilities, trigger notifications, and log events for analytics,” notes RealNetworks Vice President and APAC region Head Noriaki Takamura. “SAFR provides facial detection and tracking of many faces in a single camera feed. Each face can be selectively analyzed for age, gender, sentiment, and liveness. Faces are rapidly matched to a database of enrolled faces, returning each identity with a recognition confidence score. SAFR works with off-the-shelf IP cameras and runs on mobile devices and readily available computers.”
The SAFR platform also offer RESTful APIs, an SDK, and dashboard for easy integration by system integrators and developers, the company says.
“SAFR has been designed to scale with high performance and fast processing time, even in rural areas with very low bandwidth,” says Bikas Jha, Country Manager for RealNetworks India. “Delivering best-in-class facial recognition, SAFR leverages the latest machine learning and artificial intelligence techniques to detect and differentiate individuals in complex surroundings. SAFR is continuously improving and expanding in real-world environments. Building on its legacy and leadership in streaming media – including compression, media delivery, digital rights management, and efficient scalability – RealNetworks’ expertise now extends to AI, machine learning and deep neural networks: the foundation of SAFR.”
SAFR is being offered to K-12 schools in the U.S. and Canada free of charge, and RealNetworks co-founder Rob Glaser, who is a former member of the EFF’s board and a current member of the ACLU, says he is sensitive to privacy concerns.