awesome-repositories.com
Blog
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectAboutHow we rankPressMCP server
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
brownhci avatar

brownhci/WebGazer

0
View on GitHub↗
3,865 stars·582 forks·HTML·2 viewswebgazer.cs.brown.edu↗

WebGazer

WebGazer is a JavaScript eye tracking library and browser-based computer vision tool that predicts a user's gaze coordinates on a screen in real time using a standard webcam. It functions as a client-side biometric tracker and accessibility input framework, mapping eye gaze to screen interactions to enable hands-free navigation and user interaction research.

The system performs all video processing and gaze analysis locally within the web browser, removing the need for external servers. It employs regression-based mapping models to translate eye coordinates into screen pixels, utilizing a training process that records mouse movements and click events to refine prediction accuracy.

The library includes capabilities for managing the tracking lifecycle, validating face position via a visual feedback overlay, and persisting calibration data to local storage to maintain model accuracy across sessions.

Features

  • Gaze Predictors - A tool that predicts where a user is looking by analyzing webcam video through regression-based mapping models.
  • Eye Gaze Tracking - Determines a user's gaze position on a screen by analyzing eye orientation via webcam.
  • Client-Side Biometric Trackers - Performs all biometric gaze analysis and model training locally in the web browser without external servers.
  • Web-Based Computer Vision - Implements real-time image processing and pupil detection directly within the web browser.
  • Spatial Interaction Frameworks - Maps eye gaze and spatial interaction to screen coordinates to enable hands-free navigation.
  • Hands-Free User Interfaces - Enables full website interaction and navigation without the use of a mouse or keyboard.
  • Client-Side Media Processing - Analyzes webcam video frames locally in the browser to reduce latency and preserve privacy.
  • Gaze Feedback Overlays - Provides real-time visual feedback on gaze alignment and calibration status via a video feed.
  • Gaze Model Trainers - Collects interaction data from mouse clicks and cursor movements to improve gaze prediction models.
  • Positioning Guidance Overlays - Renders a dynamic UI layer over the video stream to guide user positioning and verify tracking.
  • User Research Platforms - Facilitates usability testing by analyzing visual attention and how users look at web pages.
  • Calibration Event Mappings - Refines gaze prediction accuracy by mapping real-time mouse click events to eye-tracking data.

Star history

Star history chart for brownhci/webgazerStar history chart for brownhci/webgazer

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does brownhci/webgazer do?

WebGazer is a JavaScript eye tracking library and browser-based computer vision tool that predicts a user's gaze coordinates on a screen in real time using a standard webcam. It functions as a client-side biometric tracker and accessibility input framework, mapping eye gaze to screen interactions to enable hands-free navigation and user interaction research.

What are the main features of brownhci/webgazer?

The main features of brownhci/webgazer are: Gaze Predictors, Eye Gaze Tracking, Client-Side Biometric Trackers, Web-Based Computer Vision, Spatial Interaction Frameworks, Hands-Free User Interfaces, Client-Side Media Processing, Gaze Feedback Overlays.

What are some open-source alternatives to brownhci/webgazer?

Open-source alternatives to brownhci/webgazer include: optikey/optikey — OptiKey is an assistive technology suite and gaze-based input system designed to provide computer access and… esimov/pigo — Pigo is a computer vision library written in Go for locating human faces in images and video streams. It provides… justadudewhohacks/face-api.js — face-api.js is a TensorFlow.js face recognition library and browser-based computer vision API. It provides tools for… eduardolundgren/tracking.js — tracking.js is a browser computer vision library written in JavaScript for performing real-time image analysis and… jeeliz/jeelizfacefilter — jeelizFaceFilter is a browser-based computer vision engine and WebGL face tracking library designed for AR filters and… steveseguin/vdo.ninja — VDO.Ninja is a low-latency peer-to-peer media routing service and video streaming platform designed to integrate…

Open-source alternatives to WebGazer

Similar open-source projects, ranked by how many features they share with WebGazer.
  • optikey/optikeyOptiKey avatar

    OptiKey/OptiKey

    4,396View on GitHub↗

    OptiKey is an assistive technology suite and gaze-based input system designed to provide computer access and communication tools. It functions as an eye-tracking virtual keyboard and augmentative and alternative communication software, allowing users to perform text entry and system control via gaze-tracking hardware or other pointer devices. The system differentiates itself through an input-agnostic selection layer that supports diverse sources, including eye trackers, game controllers, and head mice. It utilizes a dwell-time trigger mechanism and gaze fixation selection to translate eye mov

    C#aacaccessibilityaccessible
    View on GitHub↗4,396
  • esimov/pigoesimov avatar

    esimov/pigo

    4,710View on GitHub↗

    Pigo is a computer vision library written in Go for locating human faces in images and video streams. It provides tools for face detection, facial landmark identification, and pupil and eye localization. The project is implemented in pure Go to ensure portable execution without external dependencies. It supports compilation to WebAssembly, enabling face detection and image processing to run directly in web browsers without a backend. The library's capabilities include real-time face detection using classifier cascades and gaze tracking localization. It maps anatomical points on the face to a

    Gocomputer-visioneye-detectionface-detection
    View on GitHub↗4,710
  • justadudewhohacks/face-api.jsjustadudewhohacks avatar

    justadudewhohacks/face-api.js

    17,869View on GitHub↗

    face-api.js is a TensorFlow.js face recognition library and browser-based computer vision API. It provides tools for performing face detection, recognition, and landmark prediction within browsers and Node.js. The library includes a biometric identity descriptor generator that creates numerical vectors to compare identity and similarity between images. It features a facial landmark detection tool for mapping sixty-eight specific coordinate points on a face, as well as an age and gender estimation model. Its capabilities cover real-time facial analysis, including the recognition of facial exp

    TypeScriptage-estimationemotion-recognitionface-detection
    View on GitHub↗17,869
  • eduardolundgren/tracking.jseduardolundgren avatar

    eduardolundgren/tracking.js

    9,472View on GitHub↗

    tracking.js is a browser computer vision library written in JavaScript for performing real-time image analysis and object tracking directly within a web browser. It functions as a real-time object tracker, a color tracking tool, and a face detection utility. The library enables the detection and monitoring of specific color ranges, human faces, and known visual patterns across consecutive video frames. It extracts visual features and descriptors from images to identify distinct landmarks for matching and tracking. The project covers broad computer vision capabilities, including the ability t

    JavaScript
    View on GitHub↗9,472
    • See all 30 alternatives to WebGazer→