SmartFace Embedded Toolkit (SFE Toolkit) is a modular, portable and easy-to-integrate SDK, that can be used in any facial recognition use case on various platforms.


SFE Toolkit supports the following features:

Platform support

SFE Toolkit supports the following platforms:

  • Windows x86_64,
  • Linux x86_64,
  • Android ARMv7 o and ARM64
  • Embedded Linux ARMv7 and ARM64 If you need to support another OS or architecture, please contact your sales representative at Innovatrics.

HW acceleration

The neural network models used in the libraries can be accelerated using one of the following neural network accelerators:

  • Ambarella CV2, CV22, CV25 (Ambarella SDK 3.0)
  • Rockchip RV1109 and RV1126 (RKNPU 1.6.0)
  • NVidia GPUs and NVidia Jetson platforms with NVIDIA CUDA or TensorRT support
  • NXP iMX8 (Tensorflow Lite -> VX delegate)

Download and install

SFE Toolkit packages for various platforms are available to download at Customer Portal.


Each of the SFE Toolkit packages consists of:

  • root directory includes:
    • this readme file,
    • changelog,
    • EULA,
  • doc directory includes documentation in HTML and PDF format,
  • lib directory includes shared libraries compiled for one target CPU,
  • solver directory includes a set of solvers compiled to be accelerated using a specific neural network accelerator,
  • include directory includes header files with documentation of the C API, -bin directory includes:
    • pre-built example applications demonstrating the usage and integration of the SFE Toolkit libraries,
    • License Manager application compiled for the target CPU,
  • assets directory includes images for example applications.


SFE Toolkit consists of the following libraries:

  • (sfe_core.dll on Windows)
    • solver loading
    • image operations
    • error handling
  • (sfe_face.dll on Windows)
    • face detection
    • face landmarks detection
    • face mask detection
    • face template extraction
    • 1:1 face template matching
    • 1:N face template identification
    • face liveness detection
    • face and image quality attributes


SFE Toolkit libraries provide C API. We can also provide a Java wrapper with an example application for Android platforms.


You will need a valid license file to use SFE Toolkit.

You can find more information on how to generate and deploy a license at this page

Example application

To run the pre-built example application run the following commands in the package root directory:

export LD_LIBRARY_PATH=lib

To display options run:

bin/example_face -h

If you want to build the application, please follow the instructions in example/


Please contact in case of any issues or questions.