looking for good OCR software that will convert text in jpg to regular text

[jimdagys]

I am looking for good OCR software that will convert text in jpg to regular text. I don't want to use software that uses the Microsoft Net1/2 thingy. I would appreciate any ideas.

[RLT69]

You might to try PaperPort
http://www.nuance.com/paperport/professional/

Though I'm not sure it will import an JPG file. It does do an excellent of job of scanning an image and grabbing the text which then allows the text to be edited before being exported.

[Seeker47]

You might to try PaperPort
http://www.nuance.com/paperport/professional/

Though I'm not sure it will import an JPG file. It does do an excellent of job of scanning an image and grabbing the text which then allows the text to be edited before being exported.

Do you have any ideas on where one might obtain old versions of Paperport ? I had heard some strong recommendations of their program, but it was from before ScanSoft (the 1200 lb. gorilla in this category, which gobbled up almost every major OCR product out there) took over. I had rather bad experiences with other ScanSoft programs, and want nothing further to do with them.

[RLT69]

Do you have any ideas on where one might obtain old versions of Paperport ?

Sorry, I don't.

I have used Paperport 7 and 8 which were released after scansoft took over. It's been a good product for me.

Technically Visioneer acquired ScanSoft (1999) and changed their name to ScanSoft. Then later ScanSoft merged/acquired Nuance (2005) and changed their name to Nuance.
http://en.wikipedia.org/wiki/Nuance_Communications


They have a 15 day trial version
http://www.nuance.com/paperport/trial/

Cheers

[jimdagys]

Thank you for the advice. I ending up getting ABBYY FineReader. (http://www.abbyy.com/finereader8/?param=45596)
This version is under 50MB (some other OCR software can be as big as 500MB). It works amazingly well and the software wins the ungeek award (see screenshot). You input your jpeg picture of text, or pdf text in picture format, etc (either one page or a book), click "read all" which means OCR, and then click "save". It will convert the text in picture format to editable text (txt, doc, pdf, etc).

[rallynavvie]

I guess I just use Acrobat for OCR these days. I've used FineReader in the past when I had to dump things to Excel spreadsheets since it has a much easier time identifying tables and section breaks. Acrobat has been the fastest on my systems as it is SMP-aware. I'm curious if ABBYY has upgraded their software to take advantage of this because I know ScanSoft hasn't.

[ahhaa]

I could have sworn that there was an OCR plugin for Firefox (or was it GIMP?), but went looking and couldn't call it up...