Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition

Vesa-Matti Mäntylä

Research output: Book/ReportBook (author)Scientificpeer-review

Abstract

The development of computers and the theory of doubly stochastic processes, have led to a wide variety of applications of the hidden Markov models (HMMs). Due to their computational efficiency, discrete HMMs are often favoured. HMMs offer a flexible way of presenting events with temporal and dynamical variations. Both of these matters are present in hand gestures, which are of increasing interest in the research of human-computer interaction (HCI) technologies. The exploitation of human-to-human communication modalities has become actual in HCI applications. It is even expected, that the existing HCI techniques become a bottleneck in the effective utilization of the available information flow. In this work it is given mathematically uniform presentation of the theory of discrete hidden Markov models. Especially, three basic problems, scoring, decoding and estimation, are considered. To solve these problems it is presented forward and backward algorithms, Viterbi algorithm, and Baum-Welch algorithms, respectively. The second purpose of this work is to present an application of discrete HMMs to recognize a collection of hand gestures from measured acceleration signals. In pattern recognition terms, it is created an isolated user-dependent recognition system. In the light of recognition results, the effect of several matters to the optimality of the recognizer is analyzed.
Original languageEnglish
Place of PublicationEspoo
PublisherVTT Technical Research Centre of Finland
Number of pages107
ISBN (Electronic)951-38-5876-6
ISBN (Print)951-38-5875-8
Publication statusPublished - 2001
MoE publication typeC1 Separate scientific books

Publication series

NameVTT Publications
PublisherVTT
No.449
ISSN (Print)1235-0621
ISSN (Electronic)1455-0849

Fingerprint

Gesture recognition
Hidden Markov models
Human computer interaction
Viterbi algorithm
Computational efficiency
Random processes
Pattern recognition
Decoding
Communication

Keywords

  • discrete hidden Markov models
  • hand gesture recognition
  • stochastic processes
  • discrete Markov chains
  • Bayes classification

Cite this

Mäntylä, V-M. (2001). Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. Espoo: VTT Technical Research Centre of Finland. VTT Publications, No. 449
Mäntylä, Vesa-Matti. / Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. Espoo : VTT Technical Research Centre of Finland, 2001. 107 p. (VTT Publications; No. 449).
@book{3bfa00db2e434c9fb8a4a35a04f93f41,
title = "Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition",
abstract = "The development of computers and the theory of doubly stochastic processes, have led to a wide variety of applications of the hidden Markov models (HMMs). Due to their computational efficiency, discrete HMMs are often favoured. HMMs offer a flexible way of presenting events with temporal and dynamical variations. Both of these matters are present in hand gestures, which are of increasing interest in the research of human-computer interaction (HCI) technologies. The exploitation of human-to-human communication modalities has become actual in HCI applications. It is even expected, that the existing HCI techniques become a bottleneck in the effective utilization of the available information flow. In this work it is given mathematically uniform presentation of the theory of discrete hidden Markov models. Especially, three basic problems, scoring, decoding and estimation, are considered. To solve these problems it is presented forward and backward algorithms, Viterbi algorithm, and Baum-Welch algorithms, respectively. The second purpose of this work is to present an application of discrete HMMs to recognize a collection of hand gestures from measured acceleration signals. In pattern recognition terms, it is created an isolated user-dependent recognition system. In the light of recognition results, the effect of several matters to the optimality of the recognizer is analyzed.",
keywords = "discrete hidden Markov models, hand gesture recognition, stochastic processes, discrete Markov chains, Bayes classification",
author = "Vesa-Matti M{\"a}ntyl{\"a}",
note = "Project code: E6SU00081",
year = "2001",
language = "English",
isbn = "951-38-5875-8",
series = "VTT Publications",
publisher = "VTT Technical Research Centre of Finland",
number = "449",
address = "Finland",

}

Mäntylä, V-M 2001, Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. VTT Publications, no. 449, VTT Technical Research Centre of Finland, Espoo.

Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. / Mäntylä, Vesa-Matti.

Espoo : VTT Technical Research Centre of Finland, 2001. 107 p. (VTT Publications; No. 449).

Research output: Book/ReportBook (author)Scientificpeer-review

TY - BOOK

T1 - Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition

AU - Mäntylä, Vesa-Matti

N1 - Project code: E6SU00081

PY - 2001

Y1 - 2001

N2 - The development of computers and the theory of doubly stochastic processes, have led to a wide variety of applications of the hidden Markov models (HMMs). Due to their computational efficiency, discrete HMMs are often favoured. HMMs offer a flexible way of presenting events with temporal and dynamical variations. Both of these matters are present in hand gestures, which are of increasing interest in the research of human-computer interaction (HCI) technologies. The exploitation of human-to-human communication modalities has become actual in HCI applications. It is even expected, that the existing HCI techniques become a bottleneck in the effective utilization of the available information flow. In this work it is given mathematically uniform presentation of the theory of discrete hidden Markov models. Especially, three basic problems, scoring, decoding and estimation, are considered. To solve these problems it is presented forward and backward algorithms, Viterbi algorithm, and Baum-Welch algorithms, respectively. The second purpose of this work is to present an application of discrete HMMs to recognize a collection of hand gestures from measured acceleration signals. In pattern recognition terms, it is created an isolated user-dependent recognition system. In the light of recognition results, the effect of several matters to the optimality of the recognizer is analyzed.

AB - The development of computers and the theory of doubly stochastic processes, have led to a wide variety of applications of the hidden Markov models (HMMs). Due to their computational efficiency, discrete HMMs are often favoured. HMMs offer a flexible way of presenting events with temporal and dynamical variations. Both of these matters are present in hand gestures, which are of increasing interest in the research of human-computer interaction (HCI) technologies. The exploitation of human-to-human communication modalities has become actual in HCI applications. It is even expected, that the existing HCI techniques become a bottleneck in the effective utilization of the available information flow. In this work it is given mathematically uniform presentation of the theory of discrete hidden Markov models. Especially, three basic problems, scoring, decoding and estimation, are considered. To solve these problems it is presented forward and backward algorithms, Viterbi algorithm, and Baum-Welch algorithms, respectively. The second purpose of this work is to present an application of discrete HMMs to recognize a collection of hand gestures from measured acceleration signals. In pattern recognition terms, it is created an isolated user-dependent recognition system. In the light of recognition results, the effect of several matters to the optimality of the recognizer is analyzed.

KW - discrete hidden Markov models

KW - hand gesture recognition

KW - stochastic processes

KW - discrete Markov chains

KW - Bayes classification

M3 - Book (author)

SN - 951-38-5875-8

T3 - VTT Publications

BT - Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition

PB - VTT Technical Research Centre of Finland

CY - Espoo

ER -

Mäntylä V-M. Discrete hidden Markov models with application to isolated user-dependent hand gesture recognition. Espoo: VTT Technical Research Centre of Finland, 2001. 107 p. (VTT Publications; No. 449).