🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: comp.text
Article #6641

OCR for Non-Latin texts?

#6641
From: Robin C. LaPasha
Date: Thu, 04 Jan 1990 19:49
32 lines
1896 bytes
Can someone give me any pointers - or better yet, words of experience -
for trying to scan non-Latin character sets?
	1.  I want to scan Cyrillic (usually Russian,) from typeset
text (or xerox thereof.)  Dual capabilities for Cyrillic and Latin would
be okay too, but not absolutely mandatory.
	2.  It would be nice if it ran with a micro and some normally
available scanner (that can get a full page in.)  PC or Mac or whatever
on the micro.  But if it's on something else, tell me anyway.

So - it'll probably need one of those "teachable" OCR programs, so we can
tell it about Cyrillic letters, right?  Somebody at a national Slavic
conference said they tried a Kurzweil optical scanner, but that it crashed
frequently.  (This was a few years ago, and they didn't know about the
software for it.)

The setup would be for frequent and/or heavy use, so if the "training"
could be saved in a file, then loaded whenever the Cyrillic needs doing,
that'd be optimal.  

It'd also be nice if I could convert the text to some nice PostScript fonts
in a word processor...  

I don't read all these groups, so  - 
Just email to me, and if I get useful info I'll summarize.  Let me know
if there's a particularly appropriate group to followup to, as well.

Thanks in advance.
-- 
=-=-=-=-=-=-=-
Robin LaPasha               |Deep-Six your
ruslan@ecsvax.uncecs.edu    |files with VI! ;^) ;^) ;^)
Technical Details
Message-ID: <1990Jan4.194956.2896@uncecs.edu>
Path: arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!aplcen!uakari.primate.wisc.edu!uflorida!mephisto!mcnc!ecsvax.uncecs.edu!ruslan

Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!aplcen!uakari.primate.wisc.edu!uflorida!mephisto!mcnc!ecsvax.uncecs.edu!ruslan
From: ruslan@uncecs.edu (Robin C. LaPasha)
Newsgroups: comp.text,comp.fonts,comp.periphs,comp.misc
Subject: OCR for Non-Latin texts?
Keywords: Cyrillic, scanners, OCR
Message-ID: <1990Jan4.194956.2896@uncecs.edu>
Date: 4 Jan 90 19:49:56 GMT
Followup-To: poster
Organization: UNC Educational Computing Service
Lines: 32