From: growf@ucscl.ucsc.edu (Purple Dragons!  EVERYWHERE!!!)
Subject: Recognizing sign language
Date: 30 Apr 91 21:47:13 GMT
Organization: University of California, Santa Cruz




In article <> kovach@rtc.atk.com (Pete Kovach) writes:

[N.B. I don't really know what I'm talking about here, but the little
 lights in my head lit up when I read about this application, so
 I got wild and posted a reply.]

>The sifficult area is recognizing sign language as a whole.

Hm.  Given that I'm not an expert on sign language, it seems to me
the two things you'd be looking to recognize would be a) hand positioning
and b) arm positioning.  Part A has been accomplished (or mostly
accomplished) already, in the finger spelling.  The arm motion would
be more difficult, but falls under the general category of recognizing
body motion, so a patient researcher could find that problem solved
by someone else.  The big problem would be the s/n ratio - would be
kind of a bummer if such a system crashed if you scratched your elbow.

>Recognizing
>finger spelling is fairly useless. Can you imagine talking to someone who
>verbally SPELLED everything - "H-I H-O-W A-R-E Y-O-U". Geeez - a slow 
>conversation to say the least. Also, no one thinks that way and it would
>be a difficult task just to make yourself finger spell everything rather 
>than sign.

Oh?  And I suppose sitting down at your keyboard, typing out that message,
was a chore?  Doesn't seem to me sign-spelling stuff would be much
tougher than typing, just more tedious.

>It will be interesting to see how people approach the recognition task. I
>think it will be a great "contest" to see who does the best. I know I hope
>to be first, but I am sure I will not be. Of well, maybe the best or most 
>affordable. Whatever.

Realistic optimism, I like it :)  I'd like to be the first, too,
but since I'm still an undergrad that ain't too likely...

>-- 
>Peter Kovach

Tom Wylie