3DiVi Face SDK is a set of software components (code libraries) for building face recognition solutions of any complexity – from a simple app to portals like Azure Face API or AWS Rekognition.

Face SDK supports the following features:

• Face detection and tracking on images and videos
• Face recognition on images and videos
• Face estimation (gender, age, emotions, liveness) on images and videos
• Video stream processing – face detection, tracking and recognition in video streams

Currently, the following platforms and architectures are supported:

• Windows (x86 32-bit, x86 64-bit)
• Linux (x86 32-bit, x86 64-bit, ARM 32-bit, ARM 64-bit)
• Android (ARM 32-bit, ARM 64-bit)
• iOS (ARM 64-bit)

Face SDK provides the following APIs:

• C++ API (for Windows, Linux, Android, iOS)
• Java wrapper (for Windows, Linux, Android)
• C# wrapper (for Windows, Linux)
• Python wrapper (for Windows, Linux)

• Components – essential information about the components included in Face SDK
• Use Cases – diagrams that show possible use cases and connection between the components
• Samples – sample programs in C++/C#/Java/Python that show you the features of Face SDK
• Tutorials – step-by-step tutorials on face detection, recognition, and estimation of age, gender, and emotions
• Licenses – information about different types of licenses, activation and locking of a license
• Performance Parameters – CPU and memory usage, identification quality (FAR/FRR)

To get started with Face SDK, download free Face SDK Trial license.

Note: The Trial license is not supported on iOS. Please contact us to get the free trial for iOS._

To remove trial limitations, you need to purchase Face SDK license.

Contact us at [email protected] if you have any questions.

1. Get free Face SDK Trial license or purchase the Face SDK license.
2. Clone this repository or download the distribution package from http://download.3divi.com/facesdk/archives/latest.html (here you can find the complete distribution packages for the most popular operating systems). If you download the distribution package from http://download.3divi.com/facesdk/archives/latest.html, go to Step 5. If you clone the repository, run the commands below (please note that it's important to clone this repository instead of downloading it):

$ git clone https://github.com/3DiVi/face-sdk.git
$ cd face-sdk

3. Download the Face SDK runtime using Git LFS:

$ git lfs install
$ git lfs pull

4. Extract one of the archives with the runtime depending on your platform: windows_x86_64.zip, windows_x86_32.zip, linux_x86_64.tar.xz, linux_x86_32.tar.xz, linux_armhf_32.tar.xz, linux_aarch64.tar.xz, android_arm_32.tar.xz, android_arm_64.tar.xz, ios_arm_64.tar.xz.
   When extracting the archive, specify the path to the Face SDK root – the folders bin and lib should be located at the same level with the folders conf, docs, examples, include, and share.

Extraction path – root folder of the Face SDK distribution

5. Copy the Face SDK License (3divi_face_sdk.lic) to the license folder
6. To explore the features of Face SDK, check out our samples that will show you how to work with C++, Java, C#, and Python API.

• Connecting Face SDK to Your Project – learn how to add and use the libfacerec library in your project
• Video Stream Processing – face tracking, creation of templates, face recognition, estimation of age, gender, and emotions, short-time identification
• Face Capturing – custom face tracking, getting information about faces, anthropometric points, face cropping
• Face Estimation – custom estimation of age, gender, emotion, and liveness (2D/3D)
• Face Identification – custom face identification, identification methods
• GPU Usage – instructions on GPU usage for acceleration of Face SDK modules on Linux x86 64-bit and Android
• Error Handling – error handling in C++/C#/Java/Python
• Memory Management – memory management in C++/C#/Java/Python
• Guidelines for Cameras – camera positioning and shooting, recommended cameras
• Face SDK Cross-Platform API. Latest Doxygen Output

If you've noticed a bug in our software or you'd like to propose a new feature to Face SDK, you can create an issue and our developers will take a look at your request. To do this:

1. Go to the Issues tab and click New issue.
2. Name your issue and describe it in detail.
3. When you're finished, click Submit new issue.

We're always looking forward to your feedback!

Learn more about issues on GitHub.

1. Fork this repository by clicking Fork in the top right corner of the page.
2. In a forked repository, make changes to a file and click Commit changes.
3. After making all changes, you'll see the message "This branch is ... commits ahead of 3DiVi:master." at the top of the forked repository. Click Compare to view the changes (don't forget to select the repositories and branches).
4. If everything is correct and you're ready to propose changes, click Create pull request.
5. Name your pull request and describe your changes. Then, click Create Pull Request once again.

Learn more about pull requests on GitHub.

• OpenSSL (https://www.openssl.org)
• Crypto++ (https://www.cryptopp.com)
• Boost (http://www.boost.org)
• OpenCV (http://opencv.org)
• Tensorflow (https://www.tensorflow.org/)