Performs optical character recognition on selected screen regions using an internal powerful engine.
Advertisement
OCR Image Reader is a powerful browser extension that enables users to extract text from any selected area within their active window. By simply clicking a toolbar button, users can select a region, which the extension then captures and processes using the Tesseract OCR engine. This engine supports over 100 languages, alongside automatic text orientation and script detection, making it highly versatile for various text recognition needs. It also integrates seamlessly with coding agents like OpenCode, leveraging its MCP Server capabilities for advanced automation.
주요 기능
01127 GitHub stars
02Browser toolbar button for OCR activation
03Internal Tesseract OCR engine
04Automatic text orientation and script detection
05Area selection tool for precise text extraction
06Support for over 100 languages
사용 사례
01Digitizing text from screenshots or other visual data
02Extracting text from images or non-selectable content on web pages
03Automating text recognition tasks with coding agents
