Re: OCR

[Doug <dmcgarrett@optonline.net>]

On 12/01/2010 03:57 AM, Anthony Campbell wrote:
> On 30 Nov 2010, deloptes wrote:
> > Debian TR wrote:
> >
> > > Hi everyone,
> > >
> > > I am looking for a good ocr software. A quick internet search showed
> > > that there are several softwares such as OCRad, tesseract, etc.. and if
> > > I didn't get it wrong, tesseract is one of the best softwares (maybe the
> > > best one)
> > I'm off this topic for the past 2 years, but last time I have compiled
> > tesseract it was hard to run it (tune it) I don't remember exactly, but I
> > did not have any success with it. g/jocr is working somehow but I have
> > found out that only commercial ocrs are really usable in production.
> >
> > regards
> I've found that the Debian tesseract package (tesseract-ocr-eng) works
> very well, with extremely few errors.
I found it on my PCLOS Synaptic file loader.  I haven't tested it as yet,
and it's likely to be a while, since I am not networked into my scanner,
which is on the Windows machine.  Anyway, here's the description it
offered:

"Raw OCR Engine
A commercial quality OCR engine originally developed at HP between 1985 and
1995. In 1995, this engine was among the top 3 evaluated by UNLV. It was
open-sourced by HP and UNLV in 2005."

On the Win 7 machine I have Nuance OmniPage 17, which works very well.
It's not free, and I don't know if they sell a Linux version. Nuance can 
be pesty
about trying to get you to upgrade.  I had another program from them
that I finally removed from the machine!

--doug

--
Blessed are the peacemakers...for they shall be shot at from both sides. --A. M. Greeley