facenox/face-antispoof-onnx

Ultra-lightweight (600KB) Face Anti-Spoofing classifier. Optimized MiniFASNetV2-SE implementation validated on 70k+ samples with ~98% accuracy for edge devices.

56
/ 100
Established

This tool helps secure systems by detecting fake faces during identity verification. It takes a live camera feed or an image of a face and determines if it's a real person or a spoof attempt like a printed photo or screen display. It's designed for anyone managing security or access control systems, especially on devices with limited computing power.

184 stars.

Use this if you need a highly accurate and extremely lightweight solution to prevent fraudulent access by distinguishing real faces from fakes in real-time, even on low-spec hardware.

Not ideal if your application primarily involves poorly lit conditions, extreme face angles, or requires processing very small faces, as these can affect accuracy.

identity-verification access-control biometric-security fraud-prevention edge-ai
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 20 / 25

How are scores calculated?

Stars

184

Forks

33

Language

Python

License

Apache-2.0

Last pushed

Mar 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/facenox/face-antispoof-onnx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.