Gesture interaction for small handheld devices to support multimedia applications

Jani Mäntyjärvi, Sanna Kallio, Panu Korpipää, Juha Kela, Johan Plomp

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Accelerometer-based gesture control is proposed as a complementary interaction modality for small handheld devices to enable a variety of multimedia applications. The motivation for experimenting with gesture interaction is justified by the personal and public domain prototype applications developed. The challenges related to developing user-dependent and independent gesture control are presented. In this article, we experiment with methods for user-dependent gesture recognition with a low number of training repetitions, and for feasible user-independent gesture recognition from a moderately large set of gestures. The user-dependent gesture recognition performance of the continuous Hidden Markov Model (HMM) is better when compared to discrete HMM with three gesture repetitions in a training set. With continuous HMM, a recognition accuracy level of 95% is obtained with or without tilt normalization, while for discrete HMM a best recognition accuracy of 90% is obtained. The user-independent gesture recognition performance with continuous HMM of 89% is considerably better compared to tests with discrete HMM, when both are obtained with cross-validation from 2,520 gestures. An important result is that the effect of using tilt normalization notably increases the user-independent gesture recognition performance by 10- 15% depending on the method used. The chosen methods show great potential for gesture-based interaction in multimedia applications.
Original languageEnglish
Pages (from-to)92 - 112
Number of pages21
JournalJournal of Mobile Multimedia
Volume1
Issue number2
Publication statusPublished - 2005
MoE publication typeA1 Journal article-refereed

Fingerprint

Gesture recognition
Hidden Markov models
multimedia
interaction
normalization
Accelerometers
performance
Experiments

Cite this

Mäntyjärvi, Jani ; Kallio, Sanna ; Korpipää, Panu ; Kela, Juha ; Plomp, Johan. / Gesture interaction for small handheld devices to support multimedia applications. In: Journal of Mobile Multimedia. 2005 ; Vol. 1, No. 2. pp. 92 - 112.
@article{7876f9080f684b898ad93d383772012c,
title = "Gesture interaction for small handheld devices to support multimedia applications",
abstract = "Accelerometer-based gesture control is proposed as a complementary interaction modality for small handheld devices to enable a variety of multimedia applications. The motivation for experimenting with gesture interaction is justified by the personal and public domain prototype applications developed. The challenges related to developing user-dependent and independent gesture control are presented. In this article, we experiment with methods for user-dependent gesture recognition with a low number of training repetitions, and for feasible user-independent gesture recognition from a moderately large set of gestures. The user-dependent gesture recognition performance of the continuous Hidden Markov Model (HMM) is better when compared to discrete HMM with three gesture repetitions in a training set. With continuous HMM, a recognition accuracy level of 95{\%} is obtained with or without tilt normalization, while for discrete HMM a best recognition accuracy of 90{\%} is obtained. The user-independent gesture recognition performance with continuous HMM of 89{\%} is considerably better compared to tests with discrete HMM, when both are obtained with cross-validation from 2,520 gestures. An important result is that the effect of using tilt normalization notably increases the user-independent gesture recognition performance by 10- 15{\%} depending on the method used. The chosen methods show great potential for gesture-based interaction in multimedia applications.",
author = "Jani M{\"a}ntyj{\"a}rvi and Sanna Kallio and Panu Korpip{\"a}{\"a} and Juha Kela and Johan Plomp",
year = "2005",
language = "English",
volume = "1",
pages = "92 -- 112",
journal = "Journal of Mobile Multimedia",
issn = "1550-4646",
publisher = "Rinton Press Inc.",
number = "2",

}

Gesture interaction for small handheld devices to support multimedia applications. / Mäntyjärvi, Jani; Kallio, Sanna; Korpipää, Panu; Kela, Juha; Plomp, Johan.

In: Journal of Mobile Multimedia, Vol. 1, No. 2, 2005, p. 92 - 112.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Gesture interaction for small handheld devices to support multimedia applications

AU - Mäntyjärvi, Jani

AU - Kallio, Sanna

AU - Korpipää, Panu

AU - Kela, Juha

AU - Plomp, Johan

PY - 2005

Y1 - 2005

N2 - Accelerometer-based gesture control is proposed as a complementary interaction modality for small handheld devices to enable a variety of multimedia applications. The motivation for experimenting with gesture interaction is justified by the personal and public domain prototype applications developed. The challenges related to developing user-dependent and independent gesture control are presented. In this article, we experiment with methods for user-dependent gesture recognition with a low number of training repetitions, and for feasible user-independent gesture recognition from a moderately large set of gestures. The user-dependent gesture recognition performance of the continuous Hidden Markov Model (HMM) is better when compared to discrete HMM with three gesture repetitions in a training set. With continuous HMM, a recognition accuracy level of 95% is obtained with or without tilt normalization, while for discrete HMM a best recognition accuracy of 90% is obtained. The user-independent gesture recognition performance with continuous HMM of 89% is considerably better compared to tests with discrete HMM, when both are obtained with cross-validation from 2,520 gestures. An important result is that the effect of using tilt normalization notably increases the user-independent gesture recognition performance by 10- 15% depending on the method used. The chosen methods show great potential for gesture-based interaction in multimedia applications.

AB - Accelerometer-based gesture control is proposed as a complementary interaction modality for small handheld devices to enable a variety of multimedia applications. The motivation for experimenting with gesture interaction is justified by the personal and public domain prototype applications developed. The challenges related to developing user-dependent and independent gesture control are presented. In this article, we experiment with methods for user-dependent gesture recognition with a low number of training repetitions, and for feasible user-independent gesture recognition from a moderately large set of gestures. The user-dependent gesture recognition performance of the continuous Hidden Markov Model (HMM) is better when compared to discrete HMM with three gesture repetitions in a training set. With continuous HMM, a recognition accuracy level of 95% is obtained with or without tilt normalization, while for discrete HMM a best recognition accuracy of 90% is obtained. The user-independent gesture recognition performance with continuous HMM of 89% is considerably better compared to tests with discrete HMM, when both are obtained with cross-validation from 2,520 gestures. An important result is that the effect of using tilt normalization notably increases the user-independent gesture recognition performance by 10- 15% depending on the method used. The chosen methods show great potential for gesture-based interaction in multimedia applications.

M3 - Article

VL - 1

SP - 92

EP - 112

JO - Journal of Mobile Multimedia

JF - Journal of Mobile Multimedia

SN - 1550-4646

IS - 2

ER -