Title :
A hybrid sign language recognition system
Author_Institution :
Electr. & Comput. Eng. Dept., Cordoba Univ., Spain
fDate :
31 Oct.-3 Nov. 2004
Abstract :
This work describes an isolated sign language recognition (SLR) system that combines features from a video camera and an instrumented glove. Various combinations of features were tested on American Sign Language (ASL) vocabularies ranging from 10 to 200 words. The most accurate feature vector set included all available camera and glove features.
Keywords :
feature extraction; handwriting recognition; image classification; natural languages; video cameras; vocabulary; American Sign Language; feature vector set; hybrid sign language recognition system; instrumented glove; video camera; vocabulary; Cameras; Data gloves; Data mining; Feature extraction; Handicapped aids; Hidden Markov models; Instruments; Performance gain; Testing; Vocabulary;
Conference_Titel :
Wearable Computers, 2004. ISWC 2004. Eighth International Symposium on
Print_ISBN :
0-7695-2186-X
DOI :
10.1109/ISWC.2004.2
