Re: OCR [was: Bar codes]

Tripp Lilley (tlilley@perspex.com)
Mon, 8 Mar 1999 20:08:22 -0500 (EST)

Here are my links:

http://starship.python.net/crew/amk/ocr/
"An As-Yet-Unnamed OCR Project"

does have a number of good links to other projects of varyingly open
licenses. It also has a mailing list archive for the project, which has
some good random comments.

http://www-stud.enst.fr/~michon/quinefaut/index.html

This appears to be a relatively new effort, but only does 70% recognition
right now. It uses greyscale input in an attempt to better inform the
recognition engine.

http://www.serve.com/dstilwell/page5.html

I just found this, on the subject of Tibetan OCR :-). I'm not sure about
Tibetan specifically, but I believe the principles of OCR are broadly
applicable. The page also has a good links section, including a couple of
book reviews and a couple of pointers to open source OCR-related code and
projects.

Those are the links I've found so far that had some value to them. Hope
this helps someone...

--
   Tripp Lilley + Innovative Workflow Engineering, Inc. + (tripp@iweinc.com)
------------------------------------------------------------------------------
  "Stallman, after all, still has a point: greed, competition, and secrets
   really are, on some level, bad for us; they really do rob the industry of
   a certain amount of genius. The time and energy that is poured into the
   maintenance of proprietary frameworks could be much better spent elsewhere,
   like on real innovation."

-- 
   Thomas Scoville in http://opensource.oreilly.com/news/scoville_0399.html

--
Source code, list archive, and docs: http://www.mostang.com/sane/
To unsubscribe: echo unsubscribe sane-devel | mail majordomo@mostang.com