Recognition of local features for camera-based sign language recognition system

Kazuyuki Imagawa, Hideaki Matsuo, Rin-Ichiro Taniguchi, Daisaku Arita, Shan Lu, Seiji Igi

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

A sign language recognition system is required to use information from both global features, such as hand movement and location, and local features, such as hand shape and orientation. In this paper, we present an adequate local feature recognizer for a sign language recognition system. Our basic approach is to represent the hand images extracted from sign-language images as symbols which correspond to clusters by a clustering technique. The clusters are created from a training set of extracted hand images so that a similar appearance can be classified into the same cluster on an eigenspace. The experimental results indicate that our system can recognize a sign language word even in two-handed and hand-to-hand contact cases.

Original languageEnglish
Pages (from-to)849-853
Number of pages5
JournalProceedings - International Conference on Pattern Recognition
Volume15
Issue number4
Publication statusPublished - Dec 1 2000
Externally publishedYes

Fingerprint

Information use
Cameras

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Recognition of local features for camera-based sign language recognition system. / Imagawa, Kazuyuki; Matsuo, Hideaki; Taniguchi, Rin-Ichiro; Arita, Daisaku; Lu, Shan; Igi, Seiji.

In: Proceedings - International Conference on Pattern Recognition, Vol. 15, No. 4, 01.12.2000, p. 849-853.

Research output: Contribution to journalArticle

Imagawa, Kazuyuki ; Matsuo, Hideaki ; Taniguchi, Rin-Ichiro ; Arita, Daisaku ; Lu, Shan ; Igi, Seiji. / Recognition of local features for camera-based sign language recognition system. In: Proceedings - International Conference on Pattern Recognition. 2000 ; Vol. 15, No. 4. pp. 849-853.
@article{1604b725f70647fd8d429ac8ec4dcf24,
title = "Recognition of local features for camera-based sign language recognition system",
abstract = "A sign language recognition system is required to use information from both global features, such as hand movement and location, and local features, such as hand shape and orientation. In this paper, we present an adequate local feature recognizer for a sign language recognition system. Our basic approach is to represent the hand images extracted from sign-language images as symbols which correspond to clusters by a clustering technique. The clusters are created from a training set of extracted hand images so that a similar appearance can be classified into the same cluster on an eigenspace. The experimental results indicate that our system can recognize a sign language word even in two-handed and hand-to-hand contact cases.",
author = "Kazuyuki Imagawa and Hideaki Matsuo and Rin-Ichiro Taniguchi and Daisaku Arita and Shan Lu and Seiji Igi",
year = "2000",
month = "12",
day = "1",
language = "English",
volume = "15",
pages = "849--853",
journal = "Proceedings - International Conference on Pattern Recognition",
issn = "1051-4651",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Recognition of local features for camera-based sign language recognition system

AU - Imagawa, Kazuyuki

AU - Matsuo, Hideaki

AU - Taniguchi, Rin-Ichiro

AU - Arita, Daisaku

AU - Lu, Shan

AU - Igi, Seiji

PY - 2000/12/1

Y1 - 2000/12/1

N2 - A sign language recognition system is required to use information from both global features, such as hand movement and location, and local features, such as hand shape and orientation. In this paper, we present an adequate local feature recognizer for a sign language recognition system. Our basic approach is to represent the hand images extracted from sign-language images as symbols which correspond to clusters by a clustering technique. The clusters are created from a training set of extracted hand images so that a similar appearance can be classified into the same cluster on an eigenspace. The experimental results indicate that our system can recognize a sign language word even in two-handed and hand-to-hand contact cases.

AB - A sign language recognition system is required to use information from both global features, such as hand movement and location, and local features, such as hand shape and orientation. In this paper, we present an adequate local feature recognizer for a sign language recognition system. Our basic approach is to represent the hand images extracted from sign-language images as symbols which correspond to clusters by a clustering technique. The clusters are created from a training set of extracted hand images so that a similar appearance can be classified into the same cluster on an eigenspace. The experimental results indicate that our system can recognize a sign language word even in two-handed and hand-to-hand contact cases.

UR - http://www.scopus.com/inward/record.url?scp=33750921419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750921419&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33750921419

VL - 15

SP - 849

EP - 853

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

SN - 1051-4651

IS - 4

ER -