Home

Human Library

AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition,
Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis,
Age & Gender & Emotion Prediction, Gesture Recognition

JavaScript module using TensorFlow/JS Machine Learning library

• Browser:
  Compatible with both desktop and mobile platforms
  Compatible with CPU, WebGL, WASM backends
  Compatible with WebWorker execution
• NodeJS:
  Compatible with both software tfjs-node and
  GPU accelerated backends tfjs-node-gpu using CUDA libraries

Check out Live Demo for processing of live WebCam video or static images

Demos

• Main Application
• Face Extraction, Description, Identification and Matching
• Face Extraction and 3D Rendering
• Details on Demo Applications

Project pages

• Code Repository
• NPM Package
• Issues Tracker
• API Specification: Human
• API Specification: Root
• Change Log

Wiki pages

• Home
• Installation
• Usage & Functions
• Configuration Details
• Output Details
• Face Recognition & Face Description
• Gesture Recognition
• Common Issues

Additional notes

• Notes on Backends
• Development Server
• Build Process
• Performance Notes
• Performance Profiling
• Platform Support
• List of Models & Credits

See issues and discussions for list of known limitations and planned enhancements

Suggestions are welcome!

---

Inputs

Human library can process all known input types:

• Image, ImageData, ImageBitmap, Canvas, OffscreenCanvas, Tensor,
• HTMLImageElement, HTMLCanvasElement, HTMLVideoElement, HTMLMediaElement

Additionally, HTMLVideoElement, HTMLMediaElement can be a standard <video> tag that links to:

• WebCam on user's system
• Any supported video type
  For example: .mp4, .avi, etc.
• Additional video types supported via HTML5 Media Source Extensions
  Live streaming examples:
  • HLS (HTTP Live Streaming) using hls.js
  • DASH (Dynamic Adaptive Streaming over HTTP) using dash.js
• WebRTC media track

---

Default models

Default models in Human library are:

• Face Detection: MediaPipe BlazeFace-Back
• Face Mesh: MediaPipe FaceMesh
• Face Description: HSE FaceRes
• Face Iris Analysis: MediaPipe Iris
• Emotion Detection: Oarriaga Emotion
• Body Analysis: PoseNet

Note that alternative models are provided and can be enabled via configuration
For example, PoseNet model can be switched for BlazePose model depending on the use case

For more info, see Configuration Details and List of Models

---

Human library is written in TypeScript 4.2
Conforming to JavaScript ECMAScript version 2020 standard
Build target is JavaScript EMCAScript version 2018

For details see Wiki Pages
and API Specification