Presentation 2010-05-22
Sign Language Recognition Considering Signer and Motion Diversity Using HMM
Koki ARIGA, Shinji SAKO, Tadashi KITAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In sign language recognition, feature extraction and modeling is important, and we use hand transition and Hidden Markov Model as sign feature and model. On the image, the value of hand transition may vary because of difference of body-size and position. So feature normalization is employed to correct these differences. And, each sign motion may vary every time signer performs, even if these are same word. So we should use a model topology considering these aspect. In this report, we describe a method of constructing various transitional topology of word HMM by sharing common segment over some words sequence.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sign language recognition / HMM / subunit / transitional topology / normalization
Paper # WIT2010-11
Date of Issue

Conference Information
Committee WIT
Conference Date 2010/5/14(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) Sign Language Recognition Considering Signer and Motion Diversity Using HMM
Sub Title (in English)
Keyword(1) sign language recognition
Keyword(2) HMM
Keyword(3) subunit
Keyword(4) transitional topology
Keyword(5) normalization
1st Author's Name Koki ARIGA
1st Author's Affiliation Department of Computer Science and Engineering Graduate School of Engineering Nagoya Institute of Technology()
2nd Author's Name Shinji SAKO
2nd Author's Affiliation Department of Computer Science and Engineering Graduate School of Engineering Nagoya Institute of Technology
3rd Author's Name Tadashi KITAMURA
3rd Author's Affiliation Department of Computer Science and Engineering Graduate School of Engineering Nagoya Institute of Technology
Date 2010-05-22
Paper # WIT2010-11
Volume (vol) vol.110
Number (no) 53
Page pp.pp.-
#Pages 6
Date of Issue