American Sign Language Word Recognition with a Sensory Glove Using Artificial Neural Networks
Abstract
An American Sign Language (ASL) recognition system is being developed using artificial neutral networks (ANN) to translate the ASL words into English. The system uses a sensory glove CybergloveTM and a flock of Bird 3-D motion tracker to extract the gesture features. The finger joint angle data obtained from strain gages in the sensory glove defines the handshape while the data from the tracker describes the trajectory of hand movement. The data from these devices is processed by two neural networks, a velocity network and a word recognition network. Our goal is to continuously recognize ASL gestures using these devices in real time. We trained and tested our ANN model for 50 ASL word for different number of samples. Our test results show that the accuracy of recognition is 94%.
Recommended Citation
C. Oz et al., "American Sign Language Word Recognition with a Sensory Glove Using Artificial Neural Networks," Intelligent Engineering Systems Through Artificial Neural Networks, (ANNIE '04), American Society of Mechanical Engineers (ASME), Jan 2004.
Department(s)
Mechanical and Aerospace Engineering
Sponsor(s)
Ford Foundation
National Science Foundation (U.S.)
University of Missouri--Rolla. Intelligent Systems Center
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2004 American Society of Mechanical Engineers (ASME), All rights reserved.
Publication Date
01 Jan 2004