Collaborating Authors

Home - SAFR from RealNetworks Secure Accurate Facial Recognition


SAFR is a highly accurate, AI-based facial recognition platform architected to economically scale at high performance with rapid processing to detect and match millions of faces in real time. Recognize every fan, VIP, employee, or guest and surface key insights for a better experience.

Even facial recognition supporters say the tech won't stop school shootings


After a school shooting in Parkland, Florida left 17 people dead, RealNetworks decided to make its facial recognition technology available for free to schools across the US and Canada. If school officials could detect strangers on their campuses, they might be able to stop shooters before they got to a classroom. Anxious to keep children safe from gun violence, thousands of schools reached out with interest in the technology. Dozens started using SAFR, RealNetworks' facial recognition technology. From working with schools, RealNetworks, the streaming media company, says it's learned an important lesson: Facial recognition isn't likely an effective tool for preventing shootings.

NIST Results Once Again Demonstrate SAFR's Consistency and Fairness Among Racial Groups - SAFR from RealNetworks Secure Accurate Facial Recognition


WIRED recently highlighted unacceptable levels of bias in facial recognition in the article The Best Algorithms Struggle to Recognize Black Faces Equally. They cited the poor test scores of leading facial recognition vendors, as reported by the National Institute of Standards and Technology (NIST) in its July 2019 results. WIRED specifically called out Idemia but generalized their concerns. "The NIST test challenged algorithms to verify that two photos showed the same face, similar to how a border agent would check passports. At sensitivity settings where Idemia's algorithms falsely matched different white women's faces at a rate of one in 10,000, it falsely matched black women's faces about once in 1,000 -- 10 times more frequently. A one in 10,000 false match rate is often used to evaluate facial recognition systems."

Company Offers Free Facial Recognition Software to Boost School Security


With the wave of school shootings that have swept the U.S. in recent years, concerns about physical security and safety have overwhelmed parents, teachers and school administrators alike. Facial recognition technology, which would allow schools and law enforcement to quickly identify who is entering their schools and when could give school districts a powerful means to make schools even safer. Last month, RealNetworks, the streaming media company that garnered attention in the '90s and early 2000s for developing the first audio streaming solution, announced it would offer its facial recognition software, SAFR, for free to over 100,000 school districts. "School safety has become one of the top national issues in the United States in 2018," said Rob Glaser, chairman and CEO of RealNetworks in a press release. "We are proud to give our leading-edge SAFR for K-12 technology solution to every elementary, middle, and high school in America and Canada.

RealNetworks reports continued growth from facial recognition in Q3 financial report


Digital media software company RealNetworks has announced significant financial progress in the third quarter financial report, the company says in a press release. RealNetworks had already announced great success for its SAFR biometric facial recognition software in its Q2 2019 report that saw revenues of $44.2 million. According to current figures, the third quarter revenue rose to $45.0 million from just $17.6 million during the same timeframe last year. The SAFR live video artificial intelligence and biometric facial recognition platform was recently integrated with the Nvidia Metropolis Software Partner Program to improve technology deployment in smart city projects. In June, SAFR biometric facial recognition was rolled out in a museum in Europe on MOBOTIX cameras to provide live analytics.