Development of Mechanical and Geometrical Texture Sensing System Based on Mastication Pressure Distribution Analysis
Project/Area Number |
17K06263
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Intelligent mechanics/Mechanical systems
|
Research Institution | Osaka University |
Principal Investigator |
|
Project Period (FY) |
2017-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
Keywords | 咀嚼ロボット / 食品テクスチャー / 圧力分布解析 / 深層学習 / 食塊形成マニピュレーション / CNN / テクスチャー推定 / CNN / ロボティクス / 食品センシング / テクスチャー解析 |
Outline of Final Research Achievements |
This work proposed a new food texture estimation method by using a robot system. By imitating human's oral mechanism, a robotic mastication simulator was developed. Biting and tongue pressure distribution measured during mastication was processed as a series of image frames. Using a convolutional neural network, the value of human sensory evaluation of texture was estimated. Through experimental validation, it was shown that the proposed method has a potential ability of estimating texture with higher accuracy than that of human.
|
Academic Significance and Societal Importance of the Research Achievements |
本研究では,柔軟対象物の変形から破壊までの一連の物理現象を取り扱うマニピュレーション・センシング問題について取り扱い,人工咀嚼過程の咬合力と舌圧を画像情報として処理し,深層学習を利用することで多様なテクスチャー(食感)の推定が可能なことを明らかにした.本研究の成果は,新しい食品評価技術の確立およびヒトの官能評価処理メカニズムの解明に貢献するものである.
|
Report
(5 results)
Research Products
(25 results)