[1331] in cryptography@c2.net mail archive
Re: text formatting .....
daemon@ATHENA.MIT.EDU (Ulf =?iso-8859-1?Q?M=F6ller?=)
Thu Aug 14 10:12:16 1997
To: ant@notatla.demon.co.uk (Antonomasia)
Date: Thu, 14 Aug 1997 12:57:24 +0200 (DFT)
Cc: coderpunks@toad.com, cryptography@c2.net
In-Reply-To: <199708132027.VAA00701@notatla.demon.co.uk> from "Antonomasia" at Aug 13, 97 09:27:06 pm
From: ulf@fitug.de (Ulf =?iso-8859-1?Q?M=F6ller?=)
> I know nothing about how likely different OCR programs, or re-runs
> of the same one, are to get the same errors. Would these be based
> on the same scan from paper to bitmap ?
I used to do a fairly lot of OCR while working for a blind people's
organization four years ago, but obviously not on this kind of text.
Running one program on the same bitmap will produce identical results
(though sanning again with a different contrast / brightness may
improve it), but running different programs on the same bitmap will
give substantially different results. Given the relatively low error
rate of the PGP5 recognition, I think this approach will be very
useful.
