Presentation 2007/1/19
Sign Language Recognition based on Estimation of Transition Structure
Tadashi MATSUO, Yoshiaki SHIRAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this report, we describe a method using HMM to recognize sign language from an image sequence. Some methods using HMM have been already proposed, but the topology of their HMMs is fixed for all signs. We should use topology suitable for dynamics of each sign because some motions in a sign may be skipped or modified. Accordingly, we propose a method to extract and match motions from multiple image sequences for learning and a method to estimate suitable topology. By some experiments we show that the proposed method works well.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sign recognition / video processing / HMM / motion extraction / estimation of transitional topology
Paper # TL2006-71,SP2006-159,WIT2006-103
Date of Issue

Conference Information
Committee TL
Conference Date 2007/1/19(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 Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Sign Language Recognition based on Estimation of Transition Structure
Sub Title (in English)
Keyword(1) sign recognition
Keyword(2) video processing
Keyword(3) HMM
Keyword(4) motion extraction
Keyword(5) estimation of transitional topology
1st Author's Name Tadashi MATSUO
1st Author's Affiliation College of Information Science and Engineering, Ritsumeikan University()
2nd Author's Name Yoshiaki SHIRAI
2nd Author's Affiliation College of Information Science and Engineering, Ritsumeikan University
Date 2007/1/19
Paper # TL2006-71,SP2006-159,WIT2006-103
Volume (vol) vol.106
Number (no) 486
Page pp.pp.-
#Pages 5
Date of Issue