Gesture recognition system using optical muscle deformation sensors

Satoshi Hosono; Shoji Nishimura; Ken Iwasaki; Emi Tamaki

doi:10.1145/3324033.3324037

Gesture recognition system using optical muscle deformation sensors

Satoshi Hosono, Shoji Nishimura, Ken Iwasaki, Emi Tamaki

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

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.

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019
Publisher	Association for Computing Machinery
Pages	12-15
Number of pages	4
ISBN (Electronic)	9781450362634
DOIs	https://doi.org/10.1145/3324033.3324037
Publication status	Published - 2019 Apr 13
Event	2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019 - Phuket, Thailand Duration: 2019 Apr 13 → 2019 Apr 16

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019
Country/Territory	Thailand
City	Phuket
Period	19/4/13 → 19/4/16

Keywords

Hand gesture
Human activity recognition
Information interface

ASJC Scopus subject areas

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

Access to Document

10.1145/3324033.3324037

Cite this

Hosono, S., Nishimura, S., Iwasaki, K., & Tamaki, E. (2019). Gesture recognition system using optical muscle deformation sensors. In 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 et al.
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).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hosono, S, Nishimura, S, Iwasaki, K & Tamaki, E 2019, Gesture recognition system using optical muscle deformation sensors. in 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

@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{\textquoteright}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",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019 ; Conference date: 13-04-2019 Through 16-04-2019",

year = "2019",

month = apr,

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

T2 - 2nd International Conference on Electronics, Communications and Control Engineering, ICECC 2019

Y2 - 13 April 2019 through 16 April 2019

ER -

Gesture recognition system using optical muscle deformation sensors

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this