SAFR

The Premier Facial Recognition Platform for Live Video in the Real World

[Accuracy]

SAFR has high recognition accuracy and requires only 60*60 pixels min for facial recognition.  SAFR recognizes faces with proven 99.86 percent accuracy for Labeed Faces in the Wiley (LFW) based on the University of Massachusettes benchmark.   SAFR edge intellingence recognizes a face moving through live video in under 100 milliseconds, 3-5x as fast a competing algorithms. In July 2019, the National Instititue of Standards and Technology (NIST) results, SAFR tested as both the fastest and most compact algorithm among algorithms for wild images with less than 0.0335 FNMR (False Non-Match rate). This means SAFR is able to sample a face multiple times during the same period of time of other algorithms, subsequently compounding SAFR's accuracy.

[Fast & Accurate]

SAFR is optimized for recognizing faces in live video, even under challenging conditions where faces are in motion, at different angles, under poor lighting conditions, or partially obscured and provides a high-quality, excellent  facial recognition based on different scenes. In addition to accurate recognition, SAFR also detects as gender, age, and sentiment.

[Flexible deployment] SAFR can be deployed on premises, in the hybrid edge/SAFR cloud, or the hybrid edge/customer cloud. It can be installed on macOS, Windows, or Linux. The full range of SAFR capabilities are available through the SAFR SDK and SAFR APIs to build custom applications, integrate into existing systems, connect hardware and IoT devices, create custom actions based on recognition events, or to export data for insights and reports.

[Easy Registration]

SAFR's unique algorithm simplifies registration, eliminating the need to provide a visa photo in advance, by simply standing in front of the camera for a while, or providing a recent photo.

[Distributed architecture]

SAFR’s distributed architecture allows for efficient bandwidth consumption, reducing roundtrip latency, even over 3G networks. The low-bandwidth requirements, edge processing, efficient algorithm, off-the-shelf hardware, and ability to leverage inexpensive GPUs differentiate SAFR – and result in significant cost savings.

[Private and Secure]. Proprietar biometric signatures cannot be used by other systems. Fully supports opt-in and opt-out. All facial data and images are encrypted in transit and at rest. When deployed on premises, no facial data is transmitted online.