Hacker News Reader

tesseract is a cli OCR program. In the Archlinux community repo there is also, ocrad, cuneiform and gocr. I have not used these.

View on HN

Open source OCR programs have not yet reached the level of what is commercially available and none of this stuff is packaged together in an easy to use manner for OCRing scanned documents.

Reply on news.ycombinator.com