Recognize every fan, customer, employee, or guest – and get actionable insights
SAFR from RealNetworks is a highly accurate facial recognition platform powered by artificial intelligence that works with IP cameras and readily available hardware to match faces in real-time. SAFR gives you an unprecedented level of visibility into the attendees and activities in your venue.
Real-time recognition through machine learning and AI
SAFR gives you a new level of situational awareness and supports numerous secure access use cases where facial recognition can replace the use of an ID badge, securely automate entry to facilities, recognize VIP guests, trigger notifications, and log events for analytics.
Facial detection Find and track faces in real time from within live video streams, such as CCTV, smartphone and tablet cameras, live broadcast feeds, photos, archived video, and more. Rejects unclear or less distinct faces and duplicates.
Facial recognition Dynamically scales with high performance to achieve matches against millions of records. Provides a Facial ID match and confidence score. Designed to enable businesses to adapt the platform and recognition information to fit their business needs.
Facial learning database Uses advanced machine learning algorithms to build facial recognition models to achieve far more accurate results than human beings.
Customizable Allows error rate tuning to minimize false rejections, false acceptances, or can be configured to optimize between the two.
Alerts on match Supports setting security alerts or triggers on thresholds the system needs to hit before sending notifications. Notifications are signals, such as messages to your phone, triggering door openings, or turning on a light.
SAFR platform Programmers access the platform via a RESTful API. Platform includes a web-based dashboard to fine tune and calibrate the system to meet business requirements.
SEI embedding of metadata Various metadata information is available and inserted into output streams.
Deployment Available as an SDK, a standalone app, or as APIs. SAFR can run on mobile devices, Macs, blade servers, in the cloud, on or off premises.
Private and secureSupports opt-in facial recognition. All facial information is encrypted.
“Privacy concerns are paramount in our design thinking. SAFR can be deployed securely in the cloud or purely on-premises, where all face and event data remain on site. In both cases private data is encrypted in transit and at rest.”
Reza Rassool, CTO of RealNetworks
World class accuracy
SAFR recognizes faces with proven 99.8 percent accuracy for Labeled Faces in the Wild (LFW), based on the University of Massachusetts benchmark. In addition, the National Institute of Standards and Technology (NIST), ranked SAFR’s recognition algorithm for “Wild Faces” False Non-Match-Rate (FNMR), as the best of any platform submitted by a United States-based company and as one of the world’s top recognition algorithms.
Extraordinary efficiency and flexibility
SAFR works seamlessly with existing IP-based cameras and readily available hardware to recognize people in real time, helping to enhance secure access and surface insights. SAFR supports both cloud and local storage. System integrators and application developers can easily integrate with the SAFR platform through RESTful API’s, an SDK, and dashboard.
Recognition in real-world conditions
Scale – Recognize faces at varying degrees and distances from cameras
Pose – Recognizes images in profile or at different angles
Occlusion – Identifies faces that are partially obscured
Sentiment – Detects facial expression from smiling to frowning
Makeup – Unique technology identifies painted or heavily made-up faces
Illumination – Detects and recognizes faces in varying lighting conditions