Optical Character Recognition (OCR)
OCR (according to wikipedia) basically refers to computer software designed to translate images of typewritten text into machine-editable text.
Lately I’ve been working on a project that involves converting text in some images to normal text that’s editable, so instead of spending a lot of time on simply reading the text and then typing, I looked out for some good OCR programs and ended up getting two of them.
One is SimpleOCR – Its opensource and has a free version, and the other is Abbyy FineReader – a proprietory software.
Abbyy is definitely powerful, easy and is considered one of the best OCR programs, on the other hand SimpleOCR does its job being free.
As for me though, my images are far too low on resolution to make them recognisable to edit 
Nonetheless these programs are especially good if you want to edit the text from a scanned document.
Update: Let’s just say my project is going to be a breeze (or something like that), thanks to Abbyy.
More: Wikipedia on OCR
December 30, 2006 at 12:26 am
There is also Tesseract on Sourceforge (more of an engine for OCR than an actual implementation from what I understand) and the company I work for resells an OCR package from Scansoft. I’d be interested to know how you fare.
January 2, 2007 at 3:56 am
Hehe. Looks like I am sticking with Abbyy for now. I just converted the .gif file (not supported natively) into .tif rather than .jpg (i guess the compresion was not good earlier) and voila the results were superb and its so easy to use….
For fun, i even took photos with my digital camera and tried Abbyy, even though there were errors, I was impressed
SimpleOCR on the other hand has some ways to go.
hehe Abby was so good that i did not nother to check the programs you mentioned. Sorry about
Thanks for the info anyways.