Awesome GitHub RepositoriesWeb-Based Computer Vision

This project provides a deep learning architecture designed to identify and isolate distinct objects within images by generating precise pixel-level masks. It functions as a browser-based inference engine, enabling the execution of complex machine learning models directly within web environments without requiring server-side processing. The system distinguishes itself by utilizing hardware-accelerated execution and parallel processing to achieve real-time segmentation speeds. It supports prompt-based mask decoding, allowing users to generate spatial masks by providing specific points or boxes

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

Transformers.js is a JavaScript library and web machine learning framework designed to run pretrained transformer models directly in the browser. It serves as a client-side inference engine and a wrapper for the ONNX Runtime, enabling the execution of multimodal AI tasks on user devices without the need for a backend server. The library distinguishes itself by providing a unified toolkit for processing text, image, and audio data locally. This architecture supports privacy-preserving model inference and reduces latency by performing all computations on the client's hardware. Its capabilities

This project is a collection of pre-trained machine learning models and conversion pipelines designed for running inference directly in the browser using TensorFlow.js. It provides a library of ready-to-use models for computer vision, audio classification, and natural language processing tasks. The suite includes specialized tools for transforming Python-based Keras models into JSON formats compatible with web environments. It enables the deployment of these models by fetching architectures and weight shards via HTTP for client-side execution. The project covers a broad range of capabilities

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

axe-core is an automated accessibility testing engine and compliance auditor designed to scan web and mobile interfaces for violations of industry accessibility standards. It functions as a programmatic scanner and linter that analyzes HTML and source code to identify barriers and verify compliance with accessibility guidelines. The project distinguishes itself by combining a DOM-based rule engine with computer vision and machine learning to detect complex violations that evade traditional analysis, such as visual heading discrepancies and informative images. It provides specialized capabilit

Real-Time-Person-Removal ist eine webbasierte Computer-Vision-Anwendung, die darauf ausgelegt ist, menschliche Figuren aus Live-Videostreams zu identifizieren und zu entfernen. Unter Verwendung von TensorFlow.js fungiert das Tool als Echtzeit-Hintergrund-Subtraktionssystem, das die Szenenzusammensetzung analysiert, um statische Hintergründe von sich bewegenden Personen zu isolieren. Das Projekt ermöglicht browserbasierte Computer-Vision durch die Verarbeitung von Webcam-Videofeeds direkt im Client. Es nutzt Machine Learning, um zwischen dynamischen Szenenelementen und dem Hintergrund zu unterscheiden, was die Echtzeit-Entfernung von Personen aus dem Sichtfeld ermöglicht.

Pigo ist eine Computer-Vision-Bibliothek in Go zur Lokalisierung menschlicher Gesichter in Bildern und Videostreams. Sie bietet Tools für Gesichtserkennung, Identifizierung von Gesichtsmerkmalen sowie Pupillen- und Augenlokalisierung. Das Projekt ist in reinem Go implementiert, um eine portable Ausführung ohne externe Abhängigkeiten zu gewährleisten. Es unterstützt die Kompilierung zu WebAssembly, wodurch Gesichtserkennung und Bildverarbeitung direkt in Webbrowsern ohne Backend ausgeführt werden können. Die Funktionen der Bibliothek umfassen Echtzeit-Gesichtserkennung mittels Classifier-Cascades und Gaze-Tracking-Lokalisierung. Sie mappt anatomische Punkte auf dem Gesicht, um strukturelle Geometrie und Ausdrücke mittels Random Forest Ensembles zu analysieren.

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 tra

jeelizFaceFilter is a browser-based computer vision engine and WebGL face tracking library designed for AR filters and real-time facial movement tracking. It functions as a neural network face detector that identifies multiple faces and monitors mouth movements and rotation within a web browser. The system distinguishes itself through a model-swappable detection pipeline, allowing the exchange of neural network weights to balance accuracy and performance across different camera angles and devices. It features real-time lighting synchronization to match the illumination of 3D overlays with the