A working prototype for capturing frames off of a live MJPEG video stream, identifying objects in near real-time using deep learning, and triggering actions based on an objects watch list.
-
Updated
Feb 23, 2021 - JavaScript
A working prototype for capturing frames off of a live MJPEG video stream, identifying objects in near real-time using deep learning, and triggering actions based on an objects watch list.
GammaCV is a WebGL accelerated Computer Vision library for browser
一个可以帮你快速反推出网页上图片的提示词,并快速生图测试提示词效果的插件。A Chrome extension to reverse-engineer prompts from web images and instantly validate them via live generation.
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
Interactive Visualization Interface for Multidimensional Datasets
The Engagement Meter calculates and shows engagement levels of an audience participating in a meeting
OHIF Plugin for The Visualization Toolkit (VTK)
A React component for grabbing the color palette from an image(一个提取图片主要颜色的React组件)
This sample project integrates OpenAI's GPT-4 Vision, with advanced image recognition capabilities, and DALL·E 3, the state-of-the-art image generation model, with the Chat completions API. This powerful combination allows for simultaneous image creation and analysis.
Generate the object-position value to capture an image's focal point given a custom aspect-ratio.
AI-powered photo geolocation tool — upload any photo and AI analyzes visual clues to pinpoint the exact location on an interactive map. Built with Node.js, Gemini Vision AI, and Leaflet.js.
Provides image optimisation information within the browser
Binary classification to filter and block unsolicited NSFW content from annoying coworkers... --- ...
Un proyecto sobre metadatos del guild de ciberseguridad
A demo of Google's latest vision based AI model, gemini-pro-vision.
(🚧) Analyze images of MTG cards
Stop misinformation in its tracks - three clicks, instant truth for anything you see on the web
Image analysis and visual understanding tools for AI agents — describe, detect, extract from any image.
Image Recognition as a Service is a scalable #AWS-powered web app that exposes a deep learning model via REST API, using EC2 auto-scaling and load balancing to handle image input and return predictions efficiently.
To associate your repository with the image-analysis topic, visit your repo's landing page and select "manage topics."