[clug] OCR software
keith sayers
keiths at apex.net.au
Mon Feb 16 06:05:58 GMT 2009
On Saturday 14 February 2009 at 15:55:31 Brad Hards replied :
> I've only looked at ocropus (and its underlying recognition engine, which
> is tesseract). It isn't a finished product, but it does appear to work well
> for some cases. It is a pain to get to build though.
Hmmmm. Then it sounds like it would not be the best for me.
> Are you actually working off scanned pages, or off a PDF?
Scanned pages - they are in JPG format.
And at 23:00:17 Paul Warren added :
> 'gocr' is the one I've used. It was for scanning some PDF's, but it does
> seem to work well on images. It came from the ubuntu repositories with
> an 'apt-get install gocr'. Sourceforge page is:
>
> http://jocr.sourceforge.net/
>
> NOT
>
> http://gocr.sourceforge.net/
>
> as you'd expect.
This looks a bit more suitable for me - I will seek it out.
__________________________________________________________________
Keith Sayers keiths at apex.net.au
6 Clambe Place
CHARNWOOD, ACT 2615 http://www.apex.net.au/~keiths
__________________________________________________________________
More information about the linux
mailing list