DMCA
Visual Recognition of American Sign Language Using Hidden Markov Models (1995)
| Citations: | 347 - 14 self |
BibTeX
@MISC{Starner95visualrecognition,
author = {Thad E. Starner and Alex Pentland},
title = {Visual Recognition of American Sign Language Using Hidden Markov Models},
year = {1995}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Using hidden Markov models (HMM's), an unobstrusive single view camera system is developed that can recognize hand gestures, namely, a subset of American Sign Language (ASL). Previous systems have concentrated on finger spelling or isolated word recognition, often using tethered electronic gloves for input. We achieve high recognition rates for full sentence ASL using only visual cues. A forty word lexicon consisting of personal pronouns, verbs, nouns, and adjectives is used to create 494 randomly constructed five word sentences that are signed by the subject to the computer. The data is separated into a 395 sentence training set and an independent 99 sentence test set. While signing, the 2D position, orientation, and eccentricity of bounding ellipses of the hands are tracked in real time with the assistance of solidly colored gloves. Simultaneous recognition and segmentation of the resultant stream of feature vectors occurs five times faster than real time on an HP 735. With a strong ...
Keyphrases
visual recognition real time electronic glove word sentence full sentence asl word recognition simultaneous recognition feature vector hand gesture sentence test unobstrusive single view camera system forty word lexicon consisting american sign language personal pronoun resultant stream hidden markov model previous system sentence training set visual cue high recognition rate
