Biometric Verification
Verify any user by linking their face to their identity document.
We use advanced image analysis and deep learning technology to accelerate good users and stay ahead of fraudsters.
Liveness detection and face matching without bias
We've built our facial recognition technology ourselves, and skin tone is one of the primary factors we consider when matching a selfie with a user's identity document.
Security of live video less the dropoff
We live stream video back to our servers. Giving you liveness detection without the tradeoff between the friction of a video challenge or low security of selfie.
Intention context analysis
Using live video our neural network determines the context of face shown and reviews objects and surroundings in room - before, during and after facial biometric check.
Advanced spoof detection
Our deep neural network is built to detect pixel changes, deep fakes, screens, printouts and more - plus continues to learn new techniques in real-time.
Biometric Verification
Live Photo Verification
Like Apple’s live photo, OCR Labs captures the feed around the photo being taken and analyses it for liveness. We use our secret sauce of technology including analysing light refraction from the face and background objects to determine liveness giving you the security of a video challenge but the convenience of a live photo.
Intention Context Analysis
Before, during and after checking a user’s biometric verification, we’ll determine the context of any faces shown and a user’s surroundings to ensure only genuine users are securely onboarded.
Image Utilisation in Extreme Scenarios
When a user takes a photo of their identity document, we normalise that image to account for variability with lighting levels, lower quality cameras, aging progression, and even different skin tones. Then we verify that image against their live photo - which means we can onboard almost anyone, no matter their age, nationality or smartphone model.
Advanced Spoof Protection
Stay ahead of fraudsters with deep learning technology trained on one of largest datasets in existence. Our technology is built to detect pixel changes, deep fakes, masks, depth perception, screens, print outs and more - all while learning in real-time.