Partly-hidden Markov model and its application to gesture recognition

Author

Kobayashi, Tetsunori ; Haruyama, Satoshi

Author_Institution

Dept. of Electr. Eng., Waseda Univ., Tokyo, Japan

Volume

4

fYear

1997

fDate

21-24 Apr 1997

Firstpage

3081

Abstract

A new pattern matching method, the partly-hidden Markov model, is proposed for gesture recognition. The hidden Markov model, which is widely used for the time series pattern recognition, can deal with only piecewise stationary stochastic 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 shown by the results of 6 sign-language recognition test, the error rate was improved by 73% compared with normal HMM

Keywords

feature extraction; hidden Markov models; image recognition; motion estimation; pattern matching; time series; HMM; error rate; gesture recognition; hidden Markov model; modified second order Markov model; partly hidden Markov model; pattern matching method; piecewise stationary stochastic process; sign-language recognition test; time series pattern recognition; Error analysis; Hidden Markov models; Image processing; Image recognition; Pattern matching; Pattern recognition; Read only memory; Speech recognition; Stochastic processes; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.595443

Filename

595443