Lighting
Changes in light can affect how a face appears.
Biometric Recognition with Liveness Detection
We developed a face-recognition and liveness-detection pipeline with real-time video processing for cloud and edge scenarios, for security, identity and attendance use.

What stood in the way.
Identity systems need reliable recognition across different lighting, different angles and spoofing attempts.
Changes in light can affect how a face appears.
Faces are not always seen straight on.
Photos or videos may be used to try to fool the system.
How we answered it.
We developed a face-recognition pipeline with liveness detection and real-time video processing, designed for cloud and edge scenarios. It uses RetinaFace for detection and FaceNet and ArcFace for recognition.
The parts that made the difference.
RetinaFace and Dlib locate faces in video frames.
FaceNet and ArcFace recognise faces.
The system checks that a real, live person is in front of the camera.
Video is processed in real-time, in the cloud or at the edge.
What changed for the client.
The pipeline supports reliable, real-time biometric recognition.
What it was built with.
Part of our AI and machine learning work.
The next big thing starts with a conversation.
An idea, a challenge, a “what if”. Tell us what you have in mind, and we’ll figure out the next step together.
What happens next
Find us on