Passive Liveness Detection and Analysis
SAFR’s passive liveness detection enhances security for face biometric authentication solutions. It adds detection and alerting capabilities when a printed photo or digital image or video is presented for identity authentication or physical access control workflows.
The SAFR algorithm uses a multi-faceted approach, analyzing texture and context, based entirely on the RGB visual spectrum field from a standard 2D COTS camera. Unlike the more costly approaches employed by most face recognition companies, which rely upon projected light, IR, or specialized stereoscopic / depth sensing cameras that are expensive, SAFR’s solution can be used to analyze video streams from IP camera embedded in an access control terminal, in kiosks and ATMs, built into an Android or iOS app, or an end-user’s USB or laptop camera.
Presentation attacks and spoofing attempts, such as a static image on paper or a mobile device displaying a static photo or video clip are successfully detected.
Sends spoofing alert notifications
Requires no active participation from user
Detects presentation attacks or spoofing attempts
SAFR’s approach provides system integrators and engineers the ability to customize liveness detection thresholds to balance speed and confidence, enabling the creation of solutions that meet each customer’s need for security, convenience, and end-user experience.
Passive Liveness Detection for Face Biometric Access
- Evaluates liveness within 330ms
- Receive real-time alerts when spoofing attempts or presentation attacks are detected
- Configurable settings to suit liveness requirements for varying use cases
- Real-time viewing of video and liveness analysis results
- Event-based history records the analysis result including cropped face and full video frame
- Compatible with commercial, off-the-shelf (COTS) hardware for low total cost of ownership
- Rapid deployment using existing data and networks
Request a free demo or get in contact with one of our sales or techical representatives to learn more.