Design of a low-false-positive gesture for awearable device

Ryo Kawahata, Atsushi Shimada, Takayoshi Yamashita, Hideaki Uchiyama, Rin Ichiro Taniguchi

研究成果: 著書/レポートタイプへの貢献会議での発言

5 引用 (Scopus)

抄録

As smartwatches are becoming more widely used in society, gesture recognition, as an important aspect of interaction with smartwatches, is attracting attention. An accelerometer that is incorporated in a device is often used to recognize gestures. However, a gesture is often detected falsely when a similar pattern of action occurs in daily life. In this paper, we present a novel method of designing a new gesture that reduces false detection. We refer to such a gesture as a low-false-positive (LFP) gesture. The proposed method enables a gesture design system to suggest LFP motion gestures automatically. The user of the system can design LFP gestures more easily and quickly than what has been possible in previous work. Our method combines primitive gestures to create an LFP gesture. The combination of primitive gestures is recognized quickly and accurately by a random forest algorithm using our method. We experimentally demonstrate the good recognition performance of our method for a designed gesture with a high recognition rate and without false detection.

元の言語英語
ホスト出版物のタイトルICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods
編集者Maria De Marsico, Ana Fred, Gabriella Sanniti di Baja
出版者SciTePress
ページ581-588
ページ数8
ISBN(電子版)9789897581731
出版物ステータス出版済み - 1 1 2016
イベント5th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2016 - Rome, イタリア
継続期間: 2 24 20162 26 2016

出版物シリーズ

名前ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods

その他

その他5th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2016
イタリア
Rome
期間2/24/162/26/16

Fingerprint

Gesture recognition
Accelerometers

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

これを引用

Kawahata, R., Shimada, A., Yamashita, T., Uchiyama, H., & Taniguchi, R. I. (2016). Design of a low-false-positive gesture for awearable device. : M. De Marsico, A. Fred, & G. S. di Baja (版), ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods (pp. 581-588). (ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods). SciTePress.

Design of a low-false-positive gesture for awearable device. / Kawahata, Ryo; Shimada, Atsushi; Yamashita, Takayoshi; Uchiyama, Hideaki; Taniguchi, Rin Ichiro.

ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods. 版 / Maria De Marsico; Ana Fred; Gabriella Sanniti di Baja. SciTePress, 2016. p. 581-588 (ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods).

研究成果: 著書/レポートタイプへの貢献会議での発言

Kawahata, R, Shimada, A, Yamashita, T, Uchiyama, H & Taniguchi, RI 2016, Design of a low-false-positive gesture for awearable device. : M De Marsico, A Fred & GS di Baja (版), ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods. ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods, SciTePress, pp. 581-588, 5th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2016, Rome, イタリア, 2/24/16.
Kawahata R, Shimada A, Yamashita T, Uchiyama H, Taniguchi RI. Design of a low-false-positive gesture for awearable device. : De Marsico M, Fred A, di Baja GS, 編集者, ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods. SciTePress. 2016. p. 581-588. (ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods).
Kawahata, Ryo ; Shimada, Atsushi ; Yamashita, Takayoshi ; Uchiyama, Hideaki ; Taniguchi, Rin Ichiro. / Design of a low-false-positive gesture for awearable device. ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods. 編集者 / Maria De Marsico ; Ana Fred ; Gabriella Sanniti di Baja. SciTePress, 2016. pp. 581-588 (ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods).
@inproceedings{ec6395040a6e453f960eac589d6178cd,
title = "Design of a low-false-positive gesture for awearable device",
abstract = "As smartwatches are becoming more widely used in society, gesture recognition, as an important aspect of interaction with smartwatches, is attracting attention. An accelerometer that is incorporated in a device is often used to recognize gestures. However, a gesture is often detected falsely when a similar pattern of action occurs in daily life. In this paper, we present a novel method of designing a new gesture that reduces false detection. We refer to such a gesture as a low-false-positive (LFP) gesture. The proposed method enables a gesture design system to suggest LFP motion gestures automatically. The user of the system can design LFP gestures more easily and quickly than what has been possible in previous work. Our method combines primitive gestures to create an LFP gesture. The combination of primitive gestures is recognized quickly and accurately by a random forest algorithm using our method. We experimentally demonstrate the good recognition performance of our method for a designed gesture with a high recognition rate and without false detection.",
author = "Ryo Kawahata and Atsushi Shimada and Takayoshi Yamashita and Hideaki Uchiyama and Taniguchi, {Rin Ichiro}",
year = "2016",
month = "1",
day = "1",
language = "English",
series = "ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods",
publisher = "SciTePress",
pages = "581--588",
editor = "{De Marsico}, Maria and Ana Fred and {di Baja}, {Gabriella Sanniti}",
booktitle = "ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods",

}

TY - GEN

T1 - Design of a low-false-positive gesture for awearable device

AU - Kawahata, Ryo

AU - Shimada, Atsushi

AU - Yamashita, Takayoshi

AU - Uchiyama, Hideaki

AU - Taniguchi, Rin Ichiro

PY - 2016/1/1

Y1 - 2016/1/1

N2 - As smartwatches are becoming more widely used in society, gesture recognition, as an important aspect of interaction with smartwatches, is attracting attention. An accelerometer that is incorporated in a device is often used to recognize gestures. However, a gesture is often detected falsely when a similar pattern of action occurs in daily life. In this paper, we present a novel method of designing a new gesture that reduces false detection. We refer to such a gesture as a low-false-positive (LFP) gesture. The proposed method enables a gesture design system to suggest LFP motion gestures automatically. The user of the system can design LFP gestures more easily and quickly than what has been possible in previous work. Our method combines primitive gestures to create an LFP gesture. The combination of primitive gestures is recognized quickly and accurately by a random forest algorithm using our method. We experimentally demonstrate the good recognition performance of our method for a designed gesture with a high recognition rate and without false detection.

AB - As smartwatches are becoming more widely used in society, gesture recognition, as an important aspect of interaction with smartwatches, is attracting attention. An accelerometer that is incorporated in a device is often used to recognize gestures. However, a gesture is often detected falsely when a similar pattern of action occurs in daily life. In this paper, we present a novel method of designing a new gesture that reduces false detection. We refer to such a gesture as a low-false-positive (LFP) gesture. The proposed method enables a gesture design system to suggest LFP motion gestures automatically. The user of the system can design LFP gestures more easily and quickly than what has been possible in previous work. Our method combines primitive gestures to create an LFP gesture. The combination of primitive gestures is recognized quickly and accurately by a random forest algorithm using our method. We experimentally demonstrate the good recognition performance of our method for a designed gesture with a high recognition rate and without false detection.

UR - http://www.scopus.com/inward/record.url?scp=84970021716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84970021716&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84970021716

T3 - ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods

SP - 581

EP - 588

BT - ICPRAM 2016 - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods

A2 - De Marsico, Maria

A2 - Fred, Ana

A2 - di Baja, Gabriella Sanniti

PB - SciTePress

ER -