| Project/Area Number |
26560051
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Eating habits
|
|---|
| Research Institution | National Agriculture and Food Research Organization |
|---|
Principal Investigator |
WADA Yuji 国立研究開発法人農業・食品産業技術総合研究機構, 食品研究部門 食品健康機能研究領域, 上級研究員 (30366546)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
本田 秀仁 東京大学, 大学院総合文化研究科, 特任研究員 (60452017)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 鮮度 / 生鮮食品 / 機械学習 / 画像統計量 / 輝度分布 / 弁当 / 光沢 / 画像解析 / デジタルカメラ |
|---|
| Outline of Final Research Achievements |
In order to reduce errors due to optical environments, we took digital images of food (tomato) with varying freshness under many illumination conditions. We extracted image statistics such as the standard deviation and the skewness of the luminance distribution, which may provide cues for how fresh the food in such images is perceived to be. We used the image statistics as input signals and the elapsed time as supervisory signal for a neural network model in order to predict freshness based on the image statistics. Results reveal that prediction accuracy improved as illumination conditions increased. Furthermore, we conducted a survey using crowdsourcing to identify the relationship between image statistics and visual subjective evaluation.
|
