Presentation 2002/2/28
Hand Shape Recognition Based on Chordal Axis Transform
Minami ASATANI, Jiro KATTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a novel method of hand shape recognition for masked images of arms. Firstly, the mask contours are smoothed by discrete Fourier transform with thresholds in order to add tolerance against noises. Secondly, chordal axis transform (CAT) is applied to the smoothed contours and fingers are recognized based on triangulation structure achieved by CAT. Finally, each finger is identified by applying probabilistic models that are prepared for each finger beforehand. Experimental results show that the proposed method achieves 93% recognition ratio that is much better than the conventional ones and 84% identification ratio.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) chordal axis transform / hand shape recognition / human interface
Paper # MVE2001-143
Date of Issue

Conference Information
Committee MVE
Conference Date 2002/2/28(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Hand Shape Recognition Based on Chordal Axis Transform
Sub Title (in English)
Keyword(1) chordal axis transform
Keyword(2) hand shape recognition
Keyword(3) human interface
1st Author's Name Minami ASATANI
1st Author's Affiliation Graduate School of Science and Engineering, Waseda University()
2nd Author's Name Jiro KATTO
2nd Author's Affiliation Graduate School of Science and Engineering, Waseda University
Date 2002/2/28
Paper # MVE2001-143
Volume (vol) vol.101
Number (no) 700
Page pp.pp.-
#Pages 6
Date of Issue