) (05/01/91)
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
kovach@rtc.atk.com (Pete Kovach) (05/01/91)
I wrote - >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. Tom Wylie wrote - -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. Well, I do know how to finger spell, and can sign a bit and I know that most individuals that sign do not much care for reading finger spelled words any more than they have to. It really drags out a conversation. I'm not saying it is any more difficult than typing - I'd hate to carry on a conversation in a typed manner any more than I HAD to also. I do realize that some must type to converse, or blow into straws, or whatever. But if they are not forced to by a physical restriction, I do not want to restrict concersation because it is EASIER to recognize finger spelling. Hopefully we can blow todays technology/methods away and do full gesture/sign recognition. -- Peter Kovach Sig - We don't need no stinking sig!
billk@sco.COM (William K. Karwin) (05/02/91)
growf@ucscl.ucsc.edu (Purple Dragons! EVERYWHERE!!!) writes: > >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. There's also: c) Facial expression, eyebrow movement, facial tension. d) Body motion; leaning forward while raising eyebrows is a common way to indicate an interrogative. e) Exaggeration of signs for emphasis. f) Many signers perform specific signs the way they first learned them. Signs for "mommy" and "daddy" often appear clumsy and childlike, even for clear, adult signers. How do you program a computer to recognize signs even if they are "slurred" like this? Not to criticize you, growf (you did acknowledge that you weren't an expert on ASL), but signing is a full-body language. For this reason, I think true sign translation machines will be a long way off. There's a reason most work has been done in fingerspelling only. -- William Karwin ARPA: billk@sco.COM C code. C code run. Run, code, run! UUCP: ...!uunet!sco!billk