Presentation 2004/3/18
The Sign Language Word Classification Using the Motion Vector
Chang-Hung Li, Kaoru NAKAZONO, Yuji NAGASHIMA, Hong-De Chang,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Sign language recognition technique has two major methods. The one is image processing based on sign image video. And the other is wearing equipment based on the position sensor etc. While the method based on image processing does not restrain movement of a signer, it has some following problems, analysis takes much time etc. In this report, we discuss the movement classification of sign words on assumption of sign language recognition. Sign words classification method had used a motion vector to use by encoding. Then we have tried a classification of 100 sign words by using KOSIGN Ver.2, we report it about the result.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Motion Vector / Classification of sign word / Image processing
Paper # WIT2003-62
Date of Issue

Conference Information
Committee WIT
Conference Date 2004/3/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Sign Language Word Classification Using the Motion Vector
Sub Title (in English)
Keyword(1) Motion Vector
Keyword(2) Classification of sign word
Keyword(3) Image processing
1st Author's Name Chang-Hung Li
1st Author's Affiliation Southern Taiwan University of Technology()
2nd Author's Name Kaoru NAKAZONO
2nd Author's Affiliation NTT Network Innovation Laboratories
3rd Author's Name Yuji NAGASHIMA
3rd Author's Affiliation Kogakuin Univerisity
4th Author's Name Hong-De Chang
4th Author's Affiliation Southern Taiwan University of Technology
Date 2004/3/18
Paper # WIT2003-62
Volume (vol) vol.103
Number (no) 746
Page pp.pp.-
#Pages 6
Date of Issue