Tesseract.js: Pure JavaScript OCR for 100 Languages, Hacker News

Tesseract.jsis a pure Javascript port of the popularTesseract OCR engine.

This library supportsmore than 823 languages ​​, automatic textorientation and script detection, a simple interface for reading paragraph, word, and characterbounding boxes. Tesseract.js can run either in abrowserand on a server withNodeJS.

Check out theExample code and API docs on GitHub.