- Getting started
- Checking out the source code
- Trying samples (C++, C#, Java and Python)
- Getting help
- Online web demo at https://www.doubango.org/webapps/face-liveness/
- Full documentation for the SDK at https://www.doubango.org/SDKs/face-liveness/docs/
- Supported languages (API): C++, C#, Java and Python
- Open source Computer Vision Library: https://github.com/DoubangoTelecom/compv
To our knowledge we’re the only company in the world that can perform face recognition, 3D liveness check, deepfake detection, identity concealment check and stream injection (virtual camera) detection from a single image. Our implementation is Passive/Frictionless and takes less than 20 milliseconds.
The stream injection module checks whether the image or video is from a local file or delivered using a virtual camera (OBS Studio, ManyCam, Unity Virtual Camera…). It works on all platforms (Android, iOS, Windows, Linux…). It also detects when a real stream (from real camera) is altered to modify the face (e.g. deepfake).
Deepfake check module detects whether the face is generated ex-nihilo (synthetic, AI-generated) or injected via virtual camera and superimposed.
Identity concealment module detects when a user tries to partially hide his/her face (e.g. 3D realistic mask, dark glasses…) or alter the facial features (e.g. heavy makeup, fake nose, fake beard…) to impersonate another user.
The 3D liveness module supports multiple form of spoofing attacks: Paper Print, Screen, Video Replay, 3D (silicone, paper, tissue…) realistic face mask, 2D paper mask…
| 3D Liveness detection | Deepfake detection | Injection detection |
|---|---|---|
 |
 |
 |
A facial recognition system without a robust liveness detector is a playground for fraudsters.
This version supports both Windows and Linux x86_64.
The deep learning models are on a private repository for obvious reasons. To get access to the private repository you'll need to:
- 1/ Opt-out from all Doubango's private repositories. You cannot be beta tester on more than 1 repo at the same time.
- 2/ Send us a mail with your company name and Github user name (to be added to the private repo). The mail must come from @YourCompanyName, mails from other domains (e.g. @Gmail) will be ignored. The terms of use do not allow you to decompile or reverse engineer the models.
- 3/ You must include the reason for your request: R&D test, educational, commercial...
To checkout the source code: git clone --recurse-submodules -j8 https://github.com/DoubangoTelecom/ultimateFace-SDK
If you already have the code and want to update to the latest version: git pull --recurse-submodules
Go to the samples folder and choose your prefered language.
Please check our discussion group or twitter account