Face recognition and anti-spoof liveness running fully on-device across ESA Automation’s industrial fleet: the perception layer for agents that gate machine controls, triage failed checks, and monitor model drift across sites.
Passwords on a factory floor
Operators authenticated into ESA’s HMIs and industrial PCs with typed usernames and passwords, with gloves on, in dust and vibration, across multiple machines per shift. In practice, credentials got shared, sessions stayed open, and there was no reliable record of who was actually at the machine.
Cloud face recognition was a non-starter: factory networks are segregated, latency matters at the machine, and biometric checks had to stay on site. Everything had to run on the device itself, across the two hardware architectures already in the field.
Six stages, all on the device
Face detection
A detection model finds and locks the operator’s face in the device camera stream, in factory light conditions.
Recognition
An embedding model matches the face against the enrolled operator registry, entirely on the device.
Liveness anti-spoof
A liveness layer rejects photos, screens, and replays before any match is trusted.
Access decision
Grant or deny in milliseconds. Machine controls unlock only for a live, recognised operator.
Failed-check triage
Agents triage denied checks: unknown faces, spoof attempts, and repeated failures are escalated with context.
Drift monitoring
Model performance is monitored across the fleet, so lighting changes, new PPE, or camera wear surface before they become failures.
Watch it work
Nothing leaves the device: no images, no calls.
What changed in production
Every inference runs on the device. Nothing leaves the site.
One stack across ARM and Intel IoT hardware.
Detection, recognition, and liveness anti-spoof.
Operators authenticate hands-free, gloves on.
Millisecond decisions, no network dependency.
The foundation for agents that gate controls and triage failures.
What it runs on
Models
- Face detection
- Recognition embeddings
- Liveness anti-spoof
- Drift monitoring
Edge platform
- ARM v8 devices
- Intel IoT devices
- On-device inference
- Zero network dependency
Operations
- Operator enrolment
- Failed-check triage
- Fleet health monitoring
- On-device model updates