From: doug_at_ispinn.com
Date: Thu May 06 2004 - 11:32:54 PDT
Oooh, oooh, I'm psyched. I've been thinking about this for a year or more.
Larry Yaeger and I exachanged emails briefly on this a while ago. I've
been thinking about a way to decompose the handwriting to start the
process, and with the documentation that Larry has provided, plus the
ideas I have in mind already, I'm wondering how close we could get to the
recognition stats the 2100 currently has. It wouldn't be a quick
time-to-market metric by any means, but I'm wondering how well it could be
done.
Here are some critical pieces of the puzzle, compliments of Larry Yaeger:
http://homepage.mac.com/larryy/larryy/ANHR.html
Doug Parker
> The handwriting recognition part will be difficult
> unless there are some good and public algorithms
> for bitmap -> to text recognition
Steve
-- This is the NewtonTalk list - http://www.newtontalk.net/ for all inquiries Official Newton FAQ: http://www.chuma.org/newton/faq/ WikiWikiNewt for all kinds of articles: http://tools.unna.org/wikiwikinewt/
This archive was generated by hypermail 2.1.5 : Thu May 06 2004 - 13:39:32 PDT