Tuesday, February 12, 2008

Tesseract OCR How-To, by Dr Stupid; Scripts by Fred Smith

Groklaw - Tesseract OCR How-To, by Dr Stupid; Scripts by Fred Smith

I have recently discovered Tesseract, the OCR software used by Google for its books.google.com offerings. I have used a number of open source OCR packages in the past, but this exceeds them all. I believe Tesseract will become the main stream de facto Linux OCR program once some GUI interfaces are written for it. Perhaps the Kooka team will incorporate it.

0 comments: