SAFR platform

SAFR is distinguished from other facial recognition platforms by accuracy, performance, and flexibility.

A highly accurate, machine learning facial recognition platform, architected to economically scale with high performance and rapid processing to detect and match millions of faces in real time.

PROVEN ACCURACY

Dependable accuracy and performance are central to any viable recognition solution. Latency, false positives, and questionable results render a system unusable. The algorithms powering the SAFR platform were tested by NIST and contrasted with over eighty other algorithms submitted by companies and institutions from around the world. SAFR achieved an enviable level of accuracy and performance that squarely established its position in a best-in-class category. The superior accuracy and performance achieved by SAFR was the result of a greater diversity in the data set and the use of only real faces (vs. simulated faces) to train the algorithm.

SAFR was designed to connect, adapt, and extend to different environments, specialized applications, existing hardware, or custom integrations. Secure access, door lock activation, biometric entry control, event and venue monitoring, school safety, digital signage, camera integration, retail insights, and physical space analytics are just some of the use cases where SAFR can add real value.

All Features In One Platform

Fast & Accurate

SAFR’s 99.87 percent accuracy is balanced by industry-leading performance that delivers results 3-5 times as fast as competing facial recognition algorithms. In the July 2019 National Institute of Standards and Technology (NIST) results, the SAFR algorithm tested as both the fastest and most compact among algorithms for wild images with less than 0.0335 False Non-Match Rate (FNMR). Compared to the other high-accuracy algorithms, SAFR is 2x faster than average, and 35 percent smaller than the second-smallest algorithm. SAFR was the fastest algorithm tested in the April 2019 NIST results and its speed improved by 30% in the July 2019 results. This rapid performance allows SAFR to sample video image frames considerably faster than competing algorithms. Increased sampling increases accuracy. The superior accuracy achieved by SAFR is also a result of a greater diversity in the data set and the use of only real faces (vs. simulated faces) to train the algorithm. The SAFR database is optimized for rapid matching against millions of records in near real time, making identification extraordinarily fast. With edge intelligence, SAFR detects a face moving through live video, and then recognizes it, in under 100 milliseconds.

Distributed & Flexible

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. From desktop to mobile, SAFR enables new applications for security, convenience, and more. SAFR is built for the real world, where different environments, policies, hardware systems, and applications necessitate different requirements. Designed for flexibility, 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 platform extends to Android and iOS mobile devices via the SAFR mobile app. Mobile devices can be configured as kiosks for people to register into the system for a specific use case. They can also be configured as a secure access point that can recognize a registered individual and unlock a door.

Built for Privacy

All facial signatures and facial images in transit or at rest use AES-256 encryption, and no data is passed over the Internet if run on premises. Privacy is thoughtfully addressed from the full suite of administrative tools – including easy opt-in/opt-out capabilities – to the Implementation Best Practices.

Deployment Neutral

Unlike other solutions requiring full video uploads to the cloud – incurring significant bandwidth costs and expensive overhead – the SAFR platform can be deployed on a single computer to monitor a handful of IP cameras, or scaled to thousands of cameras to meet the challenges security professionals face every day. The distributed architecture enables optimized performance, hosted on premises, in the hybrid edge/SAFR cloud, or the hybrid/edge customer cloud.

Actionable

The SAFR platform makes it easy to assign people and roles while viewing security cameras through the SAFR interface. Fully configurable alerts enable powerful custom actions and alarms based on recognition events: unlocking a door, turning on lights, sounding an alarm, denial of entry, logging demographic information, generating reports, notifying police, deploying security guards, initiating a building lockdown – any response is possible. SAFR also provides actionable data for live analytics of traffic volumes, demographic composition, dwell times, and data exports.

SAFR Platform In Use

Secure Access

Wherever access control is required SAFR can allow staff, employees, or guests to identify themselves with just their face. At home, at work, in a shared space, stadium, or venue. A recognized face can unlock a door and register a visit. Secure access is a popular use case for the SAFR platform.

Event & Venue Monitoring

Monitoring a large crowd is challenging and requires alert and capable staff. SAFR can augment any monitoring environment. It can help locate a lost child. It can alert security when a known threat or unwelcome guest is identified. VIPs can be recognized and offered priority queues or promotional premiums. Security and convenience are primary benefits of the SAFR platform solution.

Insights & Analytics

Physical world analytics are a powerful, passive application for the SAFR platform. By utilizing existing cameras systems, SAFR can generate reports for a retail store, event venue, stadiums, or any place where real-world insights can help with scheduling, traffic flow, staffing, signage and merchandising.