On Nov 4, 2011, at 11:37 AM, Michael Della Bitta wrote:
> Tesseract and ABYY Recognition Server,
I just used tesseract to ocr 450 tiffs and it did a pretty good job. We had a student compare the scans to those done by Abbey reader and while they differed some the results were very comparable. That said there is no formatting of the text which could be a problem. I don't know your environment but it was so easy to write a bash shell script get things rolling.
--Brian
|