FaceLivenessDetection - Windows

This demo demonstrates 3D passive face liveness detection python SDK by mitigating biometric fraud on Windows server.

view

This is the Face Liveness Detection Python project for Windows Server.

It stands for 3D passive face liveness detection python, face anti-spoofing python, face fraudulent check python, face liveness check python, fraud prevention python, spoof prevention python, face fraud detection python and biometric fraud with liveness detection on Windows server.

SDK

Face Liveness Detection SDK - Server

Github

Test Online

Postman

To test the API, you can use Postman. Here are the endpoints for testing:

How to Run

We have not published facesdk1.dll. If you need the SDK DLL, please get in touch with us.

1. System Requirements

CPU: 2 cores or more (Recommended: 8 cores)

RAM: 4 GB or more (Recommended: 8 GB)

HDD: 4 GB or more (Recommended: 8 GB)

OS: Windows 7 or later

Dependency: OpenVINO™ Runtime (Version: 2022.3), ncnn Runtime(20220721), Vulkan SDK Runtime(1.3.250)

2. Install SDK from DockerHub

SDK could be installed easily from DockerHub repository pushed by KBY-AI team as discribed in the follwing link.

  • Pull docker image from the repository.

sudo docker pull kbyai/face-liveness-detection:latest
  • Get machine code with the following command.

sudo docker run -e LICENSE="xxxxx" kbyai/face-liveness-detection:latest 

To request the license, please provide us with the machine code obtained from your console.

How to get machine code
  • Run docker container with license key file from KBY-AI team.

sudo docker run -v ./license.txt:/root/kby-ai-live/license.txt -p 8080:8080 -p 9000:9000 kbyai/face-liveness-detection:latest

3. Install SDK from GitHub

  • Clone the project:

git clone https://github.com/kby-ai/FaceLivenessDetection-Windows.git
  • Download the model from Google Drive and unzip it: click here

  • Run the Python code:

python test.py
  • Send us the machine code and replace the license.txt file you received. Then, run the Python code again.

Last updated