ID Document Liveness Detection SDK

This stands for ID document liveness detection, ID document liveness check, ID document anti-spoofing, ID document fraudulent check, fraud prevention, biometric fraud by mitigating biometric fraud.

Features

License

We offer lifetime license(perpetual license) based on machine ID from the server. The license is available for a one-time payment.

To request a license, please contact us:

Email: contact@kby-ai.com

System Requirement

1. Windows

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

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

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

  • OS: Windows 7 or later

  • Architecture: x64

2. Linux

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

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

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

  • OS: Ubuntu 20.04 or later

  • Architecture: x64

How To Test SDK

To validate our ID document liveness SDK, you need to get project resource from us.

Please reach out to us at the above contact address(Email, WhatsApp, Telegram or Skype).

After getting the project resource from us, please run the following commands in the project root path.

build docker

sudo docker build --pull --rm -f Dockerfile -t kby-ai-idcard:latest .

run docker

sudo docker run -v ./license.txt:/root/kby-ai-idcard/license.txt -v ./license2.txt:/root/kby-ai-idcard/license2.txt -p 8082:8080 kby-ai-idcard

If you execute the above CLI, you would get 2 kinds of machine code as follows:

Here, the machine code 1 is for ID document reader library, and the machine code 2 is for ID document liveness detection.

If you send us 2 kinds of machine code, we will give you 2 licenses based on your machine codes.

And then please replace license.txt with license 1 for machine code 1, and license2.txt with license 2 for machine code 2.

After that run docker again as follows:

sudo docker run -v ./license.txt:/root/kby-ai-idcard/license.txt -v ./license2.txt:/root/kby-ai-idcard/license2.txt -p 8082:8080 kby-ai-idcard

API can be tested through Postman

Testing with an image file: Send a POST request to http://{xx.xx.xx.xx}:8082/idcard_recognition.

Testing with a base64-encoded image: Send a POST request to http://{xx.xx.xx.xx}:8082/idcard_recognition_base64

In case of trying with real ID document, the SDK would return the following values:

Or in case of spoof attack, the SDK will return the values as follows:

Last updated