What is a great OCR program
September 22, 2010 7:55 PM   Subscribe

Suggest to me a fantastic OCR program capable of preserving formatting.

I scanned a book and I'd like to take the PDF created by the scanner and OCR it so that I can apply HTML templating to the text.

The scans are all in english, are fairly high quality, and have minimal weird formatting, no tables.

Especially interested in comments from those who have successfully OCR'd books before! Thanks very much.
posted by maize to Computers & Internet (3 answers total) 6 users marked this as a favorite
ABBY Finereader is what you want. I've OCR'd books with it.
posted by dfriedman at 8:29 PM on September 22, 2010

Incidentally this may be of use: http://lifehacker.com/5623062/which-text-recognition-tool-is-best
posted by dfriedman at 8:35 PM on September 22, 2010 [1 favorite]

Best answer: Seconding ABBY Finereader.

I was tasked with OCRing a book written in Russian. I don't read/speak Russian. I used ABBYY and gave the first couple OCRed pages to the client, fully expecting to hear that it was loaded with mistakes. The accuracy was near perfect.

FWIW, I also used ABBYY to scan 30 pages of spreadsheets and it automatically recognized the grid and let me export to Excel. Huge time saver.
posted by rancidchickn at 9:38 PM on September 22, 2010

« Older I Don't Need Your War Machines, I Don't Need Your...   |   Any benefit to a new modem? Newer »
This thread is closed to new comments.