光センサ組込み型マウスピースデバイスによる舌のジェスチャ認識
Input Method by Tongue Gestures Using Optical Sensors Embedded in Mouthpiece
2018
橋本拓磨，ラウスザン，藤田浩二，臼見莉沙，柳原弘志，高橋千尋，杉本麻樹，杉浦裕太
Takuma Hashimoto, Suzanne Low, Koji Fujita, Risa Usumi, Hiroshi Yanagihara, Chihiro Takahashi, Maki Sugimoto and Yuta Sugiura
[Reference /引用はこちら]
Takuma Hashimoto, Suzanne Low, Koji Fujita, Risa Usumi, Hiroshi Yanagihara, Chihiro Takahashi, Maki Sugimoto, Yuta Sugiura, TongueInput: Input Method by Tongue Gestures Using Optical Sensors Embedded in Mousepiece, In Proceedings of the SICE Annual Conference 2018, IEEE, 6 pages, September 11-14, 2018, Nara, Japan. [DOI]
本研究では機構が口の中で完結し，装着が容易なものとして，複数のフォトリフレクタを歯に配置し，各センサのデータ配列によって舌の動きをセンシングするシステムを提案する．フォトリフレクタは赤外光を照射し，対面物質からの反射率によって対面物質との距離を測定できるものである．複数のフォトリフレクタのセンサ値の時系列データを画像化し，抽出された特徴量によってクラスタリングを行うことで，舌の動きを推定する．
We proposed a system to recognize tongue gestures by mounting a mouthpiece embedded with an array of photo-reflector sensors. A photo-reflector is a sensor that measures distance between itself and a facing material. We utilized this sensor to measure the changes in the distance between the tongue surface and the back of the upper teeth when the tongue moves, in order to recognize the type of tongue gesture. The system in this research 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 when estimating 4 tongue positions and 4 tongue gestures, where we obtained a high recognition rate for the positions, but not for the gestures. However, we observed that we can improve the rate by improving the issues we discovered.