Get Started with SAFR SDKs
We currently offer two powerful computer vision SDKs that use SAFR’s fast and highly accurate core machine learning algorithm and are compact enough to be deployed on virtually any device with a camera. See below to determine which is right for you.
Feature Breakdown
SAFR SDK
- Face detection in still images and live video streams
- Face recognition in still images and live video streams
- Person detection
- Face tracking
- Characterization (age, gender, sentiment)
- Identity management
- Event generation and reporting
- Configurable SAFR Actions
- Access via REST APIs
SAFR Embedded SDK
- Face detection in still images
- Face recognition in still images
- Identity management (+/-) 10,000 signatures (can be increased based on available hardware)
- Access via CLI
- Offline deployment
- Characterization (age, gender, sentiment)
- Live video support – Coming soon
We’re always working to improve SAFR’s performance and feature set. Tell us what you’d like to see.
The SAFR SDK
Access the full capabilities of the SAFR platform through RESTful APIs on all major platforms and operating systems and deploy on-prem or in the cloud.
Platforms
GPU Support
NVIDIA
Accuracy
99.87% LFW, 0.0334 FNMR
Recognition Speed
<100ms per face
Detection Speed
~15-60ms, @1080p and 15FPS
The SAFR Embedded SDK
Optimized for embedded systems and camera-equipped devices with resource constraints as well as those that lack connectivity, the SAFR Embedded SDK runs entirely offline with no connection to the cloud.
GPU Support
NVIDIA
Accuracy
99.87% LFW, 0.0334 FNMR
Detection Speed
300ms @720p on a single core, 1.8GHz ARM processor
Recognition Speed
900ms @720p on a single core, 1.8GHz ARM processor
Size
<30MB
Let’s Get Something Started
Request a developer account to get a free 30-day trial of the SAFR SDKs