Presentation 2013-03-12
Word Recognition :Method of Sign Language Movement from Multiple speakers Using Via-points Based on the Minimum Jerk Model
Shinpei IGARI, Naohiro FUKUMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Feature extraction from movements and a pattern matching methods are major challenges in the word recognition of sign language represented by human arm movements. We have proposed the method that via-points, which is extracted based on the minimum jerk model is used as the feature of the arm movements. In this study, we apply DP matching to pattern matching method for extracted discrete via-points in order to compare the dictionary data from other subjects' movements since the number of the via-points in the same word may be different. The proposed method adding the weight depending on the time information to the recurrence formula of DP matching scored high accuracy in the recognition experiment using the multiple speakers' sign word movements.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sign Language Recognition / Multi-speaker / Minimum Jerk Model / Via-Points / DP matching
Paper # IMQ2012-80,IE2012-184,MVE2012-141,WIT2012-90
Date of Issue

Conference Information
Committee IE
Conference Date 2013/3/4(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Word Recognition :Method of Sign Language Movement from Multiple speakers Using Via-points Based on the Minimum Jerk Model
Sub Title (in English)
Keyword(1) Sign Language Recognition
Keyword(2) Multi-speaker
Keyword(3) Minimum Jerk Model
Keyword(4) Via-Points
Keyword(5) DP matching
1st Author's Name Shinpei IGARI
1st Author's Affiliation Department of Computer Science and Engineering, Toyohashi University of Technology()
2nd Author's Name Naohiro FUKUMURA
2nd Author's Affiliation Department of Computer Science and Engineering, Toyohashi University of Technology
Date 2013-03-12
Paper # IMQ2012-80,IE2012-184,MVE2012-141,WIT2012-90
Volume (vol) vol.112
Number (no) 473
Page pp.pp.-
#Pages 6
Date of Issue