Gesture recognition system using optical muscle deformation sensors

Satoshi Hosono, Shoji Nishimura, Ken Iwasaki, Emi Tamaki

研究成果: Conference contribution

抄録

Due to the spread of VR(Virtual Reality)/AR(Augmented Reality) applications, gesture input method will be required. In this research, a gesture recognition system is suggested using the optical muscle deformation sensors. Our gesture recognition system adapts machine learning with 8 channel optical muscle deformation sensors on the forearm which doesn’t disturb the movement of the hand. In our experiment, significant differences were found in t-test. It was found that SVM can recognize gesture with higher accuracy more than Logistic Regression. In addition, we conducted an experiment to distinguish the state of bending each finger joint. As a result, it was found that the open hand gesture is erroneously recognized as PIP bent gesture.

元の言語English
ホスト出版物のタイトルProceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019
出版者Association for Computing Machinery
ページ12-15
ページ数4
ISBN(電子版)9781450362634
DOI
出版物ステータスPublished - 2019 4 13
イベント2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019 - Phuket, Thailand
継続期間: 2019 4 132019 4 16

出版物シリーズ

名前ACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019
Thailand
Phuket
期間19/4/1319/4/16

Fingerprint

Gesture recognition
Optical systems
Muscle
Augmented reality
Sensors
Virtual reality
Learning systems
Logistics
Experiments

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

これを引用

Hosono, S., Nishimura, S., Iwasaki, K., & Tamaki, E. (2019). Gesture recognition system using optical muscle deformation sensors. : Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019 (pp. 12-15). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3324033.3324037

Gesture recognition system using optical muscle deformation sensors. / Hosono, Satoshi; Nishimura, Shoji; Iwasaki, Ken; Tamaki, Emi.

Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019. Association for Computing Machinery, 2019. p. 12-15 (ACM International Conference Proceeding Series).

研究成果: Conference contribution

Hosono, S, Nishimura, S, Iwasaki, K & Tamaki, E 2019, Gesture recognition system using optical muscle deformation sensors. : Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 12-15, 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019, Phuket, Thailand, 19/4/13. https://doi.org/10.1145/3324033.3324037
Hosono S, Nishimura S, Iwasaki K, Tamaki E. Gesture recognition system using optical muscle deformation sensors. : Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019. Association for Computing Machinery. 2019. p. 12-15. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3324033.3324037
Hosono, Satoshi ; Nishimura, Shoji ; Iwasaki, Ken ; Tamaki, Emi. / Gesture recognition system using optical muscle deformation sensors. Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019. Association for Computing Machinery, 2019. pp. 12-15 (ACM International Conference Proceeding Series).
@inproceedings{016e613753d444f48e0ee98377e50eb1,
title = "Gesture recognition system using optical muscle deformation sensors",
abstract = "Due to the spread of VR(Virtual Reality)/AR(Augmented Reality) applications, gesture input method will be required. In this research, a gesture recognition system is suggested using the optical muscle deformation sensors. Our gesture recognition system adapts machine learning with 8 channel optical muscle deformation sensors on the forearm which doesn’t disturb the movement of the hand. In our experiment, significant differences were found in t-test. It was found that SVM can recognize gesture with higher accuracy more than Logistic Regression. In addition, we conducted an experiment to distinguish the state of bending each finger joint. As a result, it was found that the open hand gesture is erroneously recognized as PIP bent gesture.",
keywords = "Hand gesture, Human activity recognition, Information interface",
author = "Satoshi Hosono and Shoji Nishimura and Ken Iwasaki and Emi Tamaki",
year = "2019",
month = "4",
day = "13",
doi = "10.1145/3324033.3324037",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "12--15",
booktitle = "Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019",

}

TY - GEN

T1 - Gesture recognition system using optical muscle deformation sensors

AU - Hosono, Satoshi

AU - Nishimura, Shoji

AU - Iwasaki, Ken

AU - Tamaki, Emi

PY - 2019/4/13

Y1 - 2019/4/13

N2 - Due to the spread of VR(Virtual Reality)/AR(Augmented Reality) applications, gesture input method will be required. In this research, a gesture recognition system is suggested using the optical muscle deformation sensors. Our gesture recognition system adapts machine learning with 8 channel optical muscle deformation sensors on the forearm which doesn’t disturb the movement of the hand. In our experiment, significant differences were found in t-test. It was found that SVM can recognize gesture with higher accuracy more than Logistic Regression. In addition, we conducted an experiment to distinguish the state of bending each finger joint. As a result, it was found that the open hand gesture is erroneously recognized as PIP bent gesture.

AB - Due to the spread of VR(Virtual Reality)/AR(Augmented Reality) applications, gesture input method will be required. In this research, a gesture recognition system is suggested using the optical muscle deformation sensors. Our gesture recognition system adapts machine learning with 8 channel optical muscle deformation sensors on the forearm which doesn’t disturb the movement of the hand. In our experiment, significant differences were found in t-test. It was found that SVM can recognize gesture with higher accuracy more than Logistic Regression. In addition, we conducted an experiment to distinguish the state of bending each finger joint. As a result, it was found that the open hand gesture is erroneously recognized as PIP bent gesture.

KW - Hand gesture

KW - Human activity recognition

KW - Information interface

UR - http://www.scopus.com/inward/record.url?scp=85067844626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067844626&partnerID=8YFLogxK

U2 - 10.1145/3324033.3324037

DO - 10.1145/3324033.3324037

M3 - Conference contribution

AN - SCOPUS:85067844626

T3 - ACM International Conference Proceeding Series

SP - 12

EP - 15

BT - Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019

PB - Association for Computing Machinery

ER -