浏览器内 OCR
OCR (Optical Character Recognition) turns pixels in an image into selectable text. Drop a screenshot, scan or photo and Tesseract.js reads it in a Web Worker on your device; the first run downloads the engine and language data (cached afterwards), and the image is never uploaded.
工具结果以英文生成。
文字密集的扫描页面耗时更长。不会上传任何内容；引擎与语言数据来自 CDN。