SAFR® Inside: World-class face recognition, now on the edge

P3255-LVE

Real-time, in-camera face detection for watchlist and more

SAFR Inside brings NIST-leading live video face recognition and video analytics features to smart edge devices. Embedded directly into the camera, SAFR Inside utilizes onboard compute functionality — eliminating the need for servers dedicated to processing video streams.

By eliminating server hardware, SAFR Inside saves you on average $500 per camera in on-premises server hardware. Leverage powerful video analytics capabilities, in real-time with dramatic reductions in total cost of ownership.

Greater intelligence, lower TCO

By performing key processing tasks on-camera, SAFR Inside reduces network bandwidth and server hardware demands. As more cameras with onboard processing are deployed these efficiencies grow, meaning as fewer servers are needed – or server needs are completely eliminated – total cost of ownership savings increase. Additional savings are achieved from reduced data center rack space and power demands and elimination of server maintenance and support contracts. Operating real-time face recognition and video analytics is now more affordable for a wider variety of customers whether you deploy on one camera or hundreds.

SAFR Inside + the SAFR Platform supports:

Enrolled person recognition
Recognize faces in real time be they opted-in VIPs or persons of concern on a watchlist.

Demographic analysis
Estimate and track age, gender, and sentiment for detected faces. Attach information to known person records, or anonymously track data without collecting or storing PII.

Mask detection and alerting
Detect faces of persons entering your business, and trigger an audio or visual reminder if they are not wearing a protective face mask in accordance with facility guidelines.

Touchless secure access
Couple with an access control system to verify identity using face recognition, even for masked faces. Or deny entry to persons not wearing masks.

Face Recognition Accuracy

Accuracy

SAFR camera embedded face recognition achieves accuracy level of 99.87% on the publicly available LFW dataset and 0.0334 FNMR @ 0.0001 FMR on wild faces at NIST FRVT 1:1. It is measured by NIST to be the fastest and smallest algorithm out of top performing algorithms on wild faces. Network is also measured by NIST to have one of the least biased performance characteristics across skin tones and gender.

 

Metrics

Accuracy:  99.687 %

Precision: 99.897 %

Recall: 96.66 %

F1 Measure: 0.9825

 

NIST World-wide demographic uniformity rank: 2/103 (top 2%)

Above metrics are indicative of real-world algorithm performance on unconstrained face images with wide range of resolutions and wide yaw and pitch pose variations (wild images). The algorithm was measured on over 1 million positive matches and over 10 million negative (impostor) matches on population of over 10000 individuals. In above measurements, algorithm was configured to produce few face positives (1/10000) and thus above numbers do not represent maximum achievable accuracy but accuracy one would expect in practical deployments. The algorithm exhibits stable false match rates on increasing population sizes. Low false match rates, fast rate of operation and low memory requirements enable SAFR algorithm to be highly effective on video where multiple face images are available.

Algorithm also exhibits high performance uniformity across gender and skin tones. SAFR ranks 2nd (out of 103 algorithms) as least variable algorithm across gender and skin-tones according to evaluation by NIST on sampling of world-wide population.

 

For comparative evaluation, additional metrics are provided below. They reflect achieved accuracy on the LFW (Labeled Faces in the Wild) data set in unconstrained, labeled outside data category after applying known and documented error corrections to the benchmark data-set.

 

Accuracy:  99.867 %

Precision: 99.9 %

Recall: 99.833 %

F1 Measure: 0.98667

SAFR Inside Axis

SAFR Inside is currently available on the AXIS P3255-LVE and AXIS Q1615 Mk III. SAFR Inside is easily installed via the Axis web-based camera administration apps tab or using the AXIS Device Manager. Once installed on the camera, simply sign into your SAFR Server whether located on premises or in the Cloud. SAFR Inside is available at no additional charge and is part of a standard SAFR Platform license.

Support for additional cameras and formats coming soon.

Request a free demo or get in contact with one of our sales or technical representatives to learn more.