TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece

Takuma Hashimoto; Suzanne Low; Koji Fujita; Risa Usumi; Hiroshi Yanagihara; Chihiro Takahashi; Maki Sugimoto; Yuta Sugiura

doi:10.23919/SICE.2018.8492690

TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece

Takuma Hashimoto, Suzanne Low, Koji Fujita, Risa Usumi, Hiroshi Yanagihara, Chihiro Takahashi, Maki Sugimoto, Yuta Sugiura

Department of Information and Computer Science

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

5 Citations (Scopus)

Abstract

We proposed a system to recognize tongue gestures by mounting a mouthpiece embedded with an array of photo-reflective sensors, to measure the changes in distance between the tongue surface and the back of the upper teeth when the tongue moves. The system utilizes grayscale images of the sensor values to calculate the HOG feature descriptor and to use SVM to recognize the gesture. We conducted two experiments to evaluate the accuracy of the system to estimate 4 tongue positions and 4 tongue gestures, where we obtained a recognition rate of 85.67% for positions and 77.5% for gestures. However, we observed that we can improve the rate by improving the issues we discovered.

Original language	English
Title of host publication	2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1219-1224
Number of pages	6
ISBN (Electronic)	9784907764609
DOIs	https://doi.org/10.23919/SICE.2018.8492690
Publication status	Published - 2018 Oct 15
Event	57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018 - Nara, Japan Duration: 2018 Sept 11 → 2018 Sept 14

Publication series

Name	2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018

Other

Other	57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018
Country/Territory	Japan
City	Nara
Period	18/9/11 → 18/9/14

Keywords

Photo-Reflective Sensors
Tongue Gestures

ASJC Scopus subject areas

Control and Systems Engineering
Control and Optimization
Instrumentation

Access to Document

10.23919/SICE.2018.8492690

Cite this

Hashimoto, T., Low, S., Fujita, K., Usumi, R., Yanagihara, H., Takahashi, C., Sugimoto, M., & Sugiura, Y. (2018). TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece. In 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018 (pp. 1219-1224). [8492690] (2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/SICE.2018.8492690

TongueInput : Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece. / Hashimoto, Takuma; Low, Suzanne; Fujita, Koji et al.

2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1219-1224 8492690 (2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018).

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

Hashimoto, T, Low, S, Fujita, K, Usumi, R, Yanagihara, H, Takahashi, C, Sugimoto, M & Sugiura, Y 2018, TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece. in 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018., 8492690, 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1219-1224, 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018, Nara, Japan, 18/9/11. https://doi.org/10.23919/SICE.2018.8492690

Hashimoto T, Low S, Fujita K, Usumi R, Yanagihara H, Takahashi C et al. TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece. In 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1219-1224. 8492690. (2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018). doi: 10.23919/SICE.2018.8492690

Hashimoto, Takuma ; Low, Suzanne ; Fujita, Koji et al. / TongueInput : Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece. 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1219-1224 (2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018).

@inproceedings{565af858048f4632927c62792781c322,

title = "TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece",

abstract = "We proposed a system to recognize tongue gestures by mounting a mouthpiece embedded with an array of photo-reflective sensors, to measure the changes in distance between the tongue surface and the back of the upper teeth when the tongue moves. The system utilizes grayscale images of the sensor values to calculate the HOG feature descriptor and to use SVM to recognize the gesture. We conducted two experiments to evaluate the accuracy of the system to estimate 4 tongue positions and 4 tongue gestures, where we obtained a recognition rate of 85.67% for positions and 77.5% for gestures. However, we observed that we can improve the rate by improving the issues we discovered.",

keywords = "Photo-Reflective Sensors, Tongue Gestures",

author = "Takuma Hashimoto and Suzanne Low and Koji Fujita and Risa Usumi and Hiroshi Yanagihara and Chihiro Takahashi and Maki Sugimoto and Yuta Sugiura",

note = "Funding Information: This work was supported by JSPS KAKENHI Grant Numbers JP16H01741. Publisher Copyright: {\textcopyright} 2018 The Society of Instrument and Control Enginners - SICE.; 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018 ; Conference date: 11-09-2018 Through 14-09-2018",

year = "2018",

month = oct,

day = "15",

doi = "10.23919/SICE.2018.8492690",

language = "English",

series = "2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1219--1224",

booktitle = "2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018",

}

TY - GEN

T1 - TongueInput

T2 - 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018

AU - Hashimoto, Takuma

AU - Low, Suzanne

AU - Fujita, Koji

AU - Usumi, Risa

AU - Yanagihara, Hiroshi

AU - Takahashi, Chihiro

AU - Sugimoto, Maki

AU - Sugiura, Yuta

PY - 2018/10/15

Y1 - 2018/10/15

N2 - We proposed a system to recognize tongue gestures by mounting a mouthpiece embedded with an array of photo-reflective sensors, to measure the changes in distance between the tongue surface and the back of the upper teeth when the tongue moves. The system utilizes grayscale images of the sensor values to calculate the HOG feature descriptor and to use SVM to recognize the gesture. We conducted two experiments to evaluate the accuracy of the system to estimate 4 tongue positions and 4 tongue gestures, where we obtained a recognition rate of 85.67% for positions and 77.5% for gestures. However, we observed that we can improve the rate by improving the issues we discovered.

AB - We proposed a system to recognize tongue gestures by mounting a mouthpiece embedded with an array of photo-reflective sensors, to measure the changes in distance between the tongue surface and the back of the upper teeth when the tongue moves. The system utilizes grayscale images of the sensor values to calculate the HOG feature descriptor and to use SVM to recognize the gesture. We conducted two experiments to evaluate the accuracy of the system to estimate 4 tongue positions and 4 tongue gestures, where we obtained a recognition rate of 85.67% for positions and 77.5% for gestures. However, we observed that we can improve the rate by improving the issues we discovered.

KW - Photo-Reflective Sensors

KW - Tongue Gestures

UR - http://www.scopus.com/inward/record.url?scp=85056696696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056696696&partnerID=8YFLogxK

U2 - 10.23919/SICE.2018.8492690

DO - 10.23919/SICE.2018.8492690

M3 - Conference contribution

AN - SCOPUS:85056696696

T3 - 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018

SP - 1219

EP - 1224

BT - 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2018

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 11 September 2018 through 14 September 2018

ER -

TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this