Text recognition of FU languages

[Johanna Laakso]

From: Jorma Luutonen <luutonen at utu.fi>

Dear Ura-list readers,

I want to inform you that the language list of the scanned text recognition
program FineReader 5.0 includes the following Uralic languages: Estonian,
Finnish, Hungarian, Khanty, Mansi, Mari, Mordvin, Nenets, Selkup and
Udmurt. This means that if you have a PC computer, a scanner and the
program you can transform printed pages to text files in a text editor
(e.g. MS Word). Such text files can then be used as material for computer
corpora. For information about FineReader see

http://www.trantor.fi/text_recognition_(ocr).htm
or
http://www.abbyy.ru/products/fine/index.htm

Jorma Luutonen
Research Unit for Volgaic Languages
University of Turku