Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!cis.ohio-state.edu!tut.cis.ohio-state.edu!udecc.engr.udayton.edu!blackbird.afit.af.mil!kahuna.asd-yf.wpafb.af.mil!falcon.aamrl.wpafb.af.mil!nlonginow From: nlonginow@falcon.aamrl.wpafb.af.mil Newsgroups: comp.ai.neural-nets Subject: Re: Hand Shape recognition (Sign Language) Message-ID: <1991May30.160041.122@falcon.aamrl.wpafb.af.mil> Date: 30 May 91 21:00:41 GMT References: <54953@nigel.ee.udel.edu> Organization: USAF AL/HE, WPAFB, Dayton, OH Lines: 25 In article <54953@nigel.ee.udel.edu>, peters@ee.udel.edu (Shirley Peters) writes: > I'm looking for references and names of research done in the area of > Sign language recognition. This could be hand shape recognition using a > glove sensing device, or video image recognition, or anything else that > will ultimately end up dealing with sign language. > > Thanx in advance, > Shirley > -- > +------------------------------------------------------------------------+ > Shirley Peters peters@dewey.udel.edu > I'd rather be sleeping! > +------------------------------------------------------------------------+ A guy by the name of Sidney Fels did this using neural nets. He appears to have had a lot of success, too. The work goes by the name of 'Glove-talk', and is published and he is at a university in Canada (Alberta ?). Anyway, he takes the output from a Dataglove, and converts it to words using a net. There was a writeup on this (or another work) where this concept was actually made into a product, where the output of the net was used to drive a speech synthesizer. Supposedly worked quite well. Wish I could tell you more. Try the sci.virt-worlds newsgroup, someone there should know more. Nick