Presentation 2007-03-16
An analysis of sign-language motion considering smoothness of movement and variability of movement duration
Tetsuya TAKAOKA, Naohiro FUKUMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The motion of sign-language sentence is composed of word movement and transitional movement. A segmentation method of a word movement depending on the smoothness of movement has been proposed. This method depends on a hypothesis that unsmooth movement parts are assumed to represent the word movement and smooth movement parts are assumed to represent the transitional movement. Then, a word translation method has been proposed that the word area shifts around the unsmooth movement to minimum the distance between the movement data of word area and dictionary data prepared beforehand. In this study, DP matching is introduced to computation of the distance to deal with variation of the movement duration. The distance of velocity vectors are used to evaluate the distance between sign word movement and dictionary data and the hand jerk is employed as a criterion of the smoothness of the movement. As a result, orders of some correct words improved significantly than the previous study.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sign-language translation / segmentation / recognition / DPmatching
Paper # NC2006-203
Date of Issue

Conference Information
Committee NC
Conference Date 2007/3/9(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An analysis of sign-language motion considering smoothness of movement and variability of movement duration
Sub Title (in English)
Keyword(1) sign-language translation
Keyword(2) segmentation
Keyword(3) recognition
Keyword(4) DPmatching
1st Author's Name Tetsuya TAKAOKA
1st Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology()
2nd Author's Name Naohiro FUKUMURA
2nd Author's Affiliation Department of Information and Computer Sciences, Toyohashi University of Technology:Intelligent Sensing System Research Center, Toyohashi University of Technology
Date 2007-03-16
Paper # NC2006-203
Volume (vol) vol.106
Number (no) 590
Page pp.pp.-
#Pages 6
Date of Issue