Face Liveness Detection Docker
An on-premise, Docker-distributed face liveness detection (anti-spoofing) server SDK that a developer runs on their own infrastructure and calls over a local HTTP API to check whether a submitted face image is a real, live person.
This SDK detects whether a face image is a live person or a spoof, such as a printed photo or a 3D mask, for use cases like remote identity verification before granting access to sensitive data. Processing happens entirely on the operator's own server; no data leaves it.
It is distributed as a Docker image, loaded and run locally, after which a license request file is generated and exchanged for a license key before the server can be used. Once running, it exposes HTTP endpoints such as check_liveness and check_liveness_base64 that accept an image and return a liveness result, along with a Gradio demo and a Python example client for testing the API.
Minimum requirements are Python 3.6 or newer, Linux, two or more CPU cores and 8 GB of RAM.