Path: utzoo!utgpu!news-server.csri.toronto.edu!bonnie.concordia.ca!ccu.umanitoba.ca!herald.usask.ca!alberta!ubc-cs!uw-beaver!milton!hlab
From: kovach@rtc.atk.com (Pete Kovach)
Newsgroups: sci.virtual-worlds
Subject: Re: Chris' Ethics Paper: Report from Cybercon 2
Message-ID: <1991Apr30.183717.29270@milton.u.washington.edu>
Date: 30 Apr 91 13:35:15 GMT
References: <1991Apr29.200959.17885@milton.u.washington.edu> <1991Apr30.051111.1
Sender: hlab@milton.u.washington.edu (Human Int. Technology Lab)
Organization: Alliant Techsystems, Inc., Mpls, MN
Lines: 30
Approved: cyberoid@milton.u.washington.edu



Peter Vamplew writes -

>Doubt no more. Work is already being done in this area.  My recently
>commenced PhD thesis is on Machine Recognition of Sign Language, and I know
>others are also working in the area including Jim Kramer from Stanford who
>has already developed a system which converts fingerspelling to speech.
>Expanding this research to full-blown sign language is obviously a
>long-term goal but at

Most certainly it is a popular area. Finger spelling recognition is quite
simple and it amazed me that he applied for a patent on it. I know I, and
a few others, had developed systems to recognize finger spelling. 

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

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.
-- 
Peter Kovach

Sig - We don't need no stinking sig!