Getting started with the SDK library

Are you a developer that is excited about the opportunity of accessing the DeepAffex engine but unsure how to begin this process? Outlined here you will find a brief step-by-step description to assist you to immediately get started on this rewarding journey!

DFX "Software Development Kit" (SDK) Overview

The primary purpose of the SDK is to convert an incoming stream of face-tracked image data into resultant blood-flow. This procedure is referred to as the blood-flow extraction and is an important stage in the TOI “front-end” pipeline functionality required for DeepAffex processing. Through configuration, the SDK is used to generate measurement data (binary payloads) sequences that are then forwarded to DeepAffex for analysis and processing.

As noted elsewhere the SDK provides extraction of the subjects facial blood-flow information from the incoming video frames. The client application is responsible for supplying video frames with accurate timestamps (e.g. from a digital camera or video file), detecting faces in the video frames and annotating them with "MPEG-4 facial animation points" (a standard naming convention for face point labeling provided by many 3rd party off-the-shelf face-detection libraries e.g. dlib, Visage etc.).


Windows (VS2015 or higher)
macOS (High Sierra 10.13 or higher) dfxsdk-macos-v4.0.4.tar.gz
Linux (Ubuntu 18.04 LTS) dfxsdk-linux-v4.0.4.tar.gz
Docs (Windows/Linux/macOS) libdfxcpp-v4.0.4.pdf
Samples (Windows/Linux/macOS) Example Data
Windows (Python 3.4+ 64bit) v4.0.4.3
macOS (High Sierra 10.13 or higher, Python 3.4+ 64bit) v4.0.4.3
Linux (Ubuntu 18.04 LTS, Python 3.4+, 64bit) v4.0.4.3
Example (Windows/Linux/macOS) Example Python Code
Samples (Windows/Linux/macOS) Example Data
Coming Soon!

Check back later for updates

Coming Soon!

Check back later for updates

DeepAffex SDK

The DeepAffex SDK exists as proprietary source-code and is written in C. NuraLogix distributes SDK binaries that are compatible with Ubuntu, macOS and Windows operating platforms. We also provide the source files for a C++ wrapper in the SDK. All client applications using the C++ binding will require linking against OpenCV cv::Mat structures. The underlying C library headers have no external dependencies.

DeepAffex™ SDK Python wrappers for Windows, Linux and macOS are now available to download as wheels. A JavaScript binding (based on webasm) is currently under construction. Other language bindings and operating systems are possible on request.

Anura core

iOS (iOS 12.2 or higher)
Coming Soon!

Check back later for updates

Anura™ core

The mobile Anura™ app published by Nuralogix performs live/interactive, facial-blood-flow (FBF) extraction and displays health related results under discrete (single/finite) measurement conditions. By making the Anura™ core package available (i.e. measurement UI + SDK binaries with skeleton source files) from this website, our intention is to assist your development process. The sample code and libraries supplied within this package will greatly accelerate the app development cycle by providing a minimal working example/reference for how an app with similar functionality could be quickly developed by utilizing the Anura™ core.

This Anura™ core package takes control (opens) the platform camera device to execute a calibration procedure that is required for optimal and reliable blood-flow extraction as well as configurable runtime constraint monitoring which helps to ensure that the measurement conditions remain valid and stable for the duration of the measurement. The target audience for this Anura™ core package are able to create custom apps incorporating corporate branding, additional UI/UX flow, user admin, location-tracking and other measurement enhancement features. Our full Anura app development roadmap is quite active and we will continue to update and maintain this Anura™ core package for both iOS and Android platforms.

Having access to this extensible Anura core package can bootstrap your development cycle if you are able to construct your use case application/scenario to incorporate the Anura measurement cycle. However if you application workflow is vastly different or cannot be easily derived from the Anura app, then you will have to implement natively using our other available platform SDK binaries.