Presentation 2010-12-09
Hand Shape Recognition Using Particle Filter and Modified Projection Distance Method
Eri MORIYAMA, Toru WAKAHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new technique for recognizing hand shapes to realize direct manipulation of PC and large screen displays. First, a dynamic sequence of hand shape movements is captured via a Web camera connected with PC. Next, the hand region is extracted by using a particle filter technique based on a likelihood measure of skin-color. Finally, a modified projection distance method is utilized to classify hand shapes into five categories: five fingers, one finger, two fingers, no finger, and the others. Experimental results using a collection of 800 samples per hand shape for ten people demonstrate that the proposed method achieves high recognition rates of 99.0% for "five fingers", 96.98% for "one finger", 96.85% for "two fingers" and 98.16% for "no finger," respectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hand shape recognition / Particle filter / Modified projection distance method
Paper # PRMU2010-129
Date of Issue

Conference Information
Committee PRMU
Conference Date 2010/12/2(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Hand Shape Recognition Using Particle Filter and Modified Projection Distance Method
Sub Title (in English)
Keyword(1) Hand shape recognition
Keyword(2) Particle filter
Keyword(3) Modified projection distance method
1st Author's Name Eri MORIYAMA
1st Author's Affiliation Graduate School of Computer and Information Sciences, Hosei University()
2nd Author's Name Toru WAKAHARA
2nd Author's Affiliation Graduate School of Computer and Information Sciences, Hosei University
Date 2010-12-09
Paper # PRMU2010-129
Volume (vol) vol.110
Number (no) 330
Page pp.pp.-
#Pages 6
Date of Issue