Presentation 1998/1/22
Partly-Hidden Markov Model and Its Application to Gesture Recognition
Ken Masumitsu, Tetunori Kobayashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A new pattern matching method, Partly-Hidden Markov model, is proposed for gesture recognition. HMM, which has been used for time series pattern matting, can deal with only piecewise stationary process. We solved this problem by introducing the modified second order Markov Model, in which the first state is hidden and the second one is observable. As the result of 6 hand sign language recognition, the error rate iwas improved by 43% compared with HMM. And as for the simple feature parameter condition, PHMM achived 60% less error rate than HMM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) HMM / gesture recognition / sign language
Paper # PRMU97-203
Date of Issue

Conference Information
Committee PRMU
Conference Date 1998/1/22(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) Partly-Hidden Markov Model and Its Application to Gesture Recognition
Sub Title (in English)
Keyword(1) HMM
Keyword(2) gesture recognition
Keyword(3) sign language
1st Author's Name Ken Masumitsu
1st Author's Affiliation Department of Electrical, Electronics & Computer Engineering Waseda University()
2nd Author's Name Tetunori Kobayashi
2nd Author's Affiliation Department of Electrical, Electronics & Computer Engineering Waseda University
Date 1998/1/22
Paper # PRMU97-203
Volume (vol) vol.97
Number (no) 500
Page pp.pp.-
#Pages 8
Date of Issue