In recent years, the number of people who use online recipe services in order to cook has increased. It is difficult to match food taste to user’s preference because an online recipe page shows a recipe to realize just one taste even though there are countless numbers of recipes in an online recipe service. Our preliminary experiment using convenience food to investigate the user’s preference showed that the preference of almost participants differed from the taste of food cooked following the recipe printed in the package. It has also been reported that 76.5% of housewives are interested in cooking activities. However, using measuring spoon is difficult to use in order to determine the exact amount of seasonings. When we conducted a preliminary experiment to confirm the error between the input amount based on a rough estimation and the specific amount, the average error for small spoon was 46.2%, and the average error for large spoon was 31.8% even though the participants cook frequently. Especially, for an elderly person requiring low salt or low sugar, if the error becomes too big than appropriate amount, leading to endangering his life or losing the pleasures of eating. However, since there is no device currently in use that can assist in putting seasonings, a device other than measuring spoon is needed to determine the amount of seasoning for cooking. In this research, we aim to bring the taste of food with an online recipe close to the user’s preferable taste without burdening the user. In this paper, we propose a cooking support system which analyzes user’s preference from user’s feedback according to the five grade evaluation for each meal, adjusts the amount of seasoning for a recipe depending on user’s preference, and supports to add the seasoning by Smart Cruet equipped with motion sensors, LED light, and BLE communication interface. We conducted an experiment for 14 days to confirm how many days are needed to bring the adjustment of the seasonings close to the preferable taste for the user. We were able to reach the desired adjustment in 7 days. Furthermore, we found Smart Cruet could measure the adding amount of seasoning with 5.56% average error.
[1]
Takashi Ijiri,et al.
CogKnife: Food recognition from their cutting sounds
,
2016,
2016 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).
[2]
Zhengxian Li,et al.
A Scalable Recipe Recommendation System for Mobile Application
,
2016,
2016 3rd International Conference on Information Science and Control Engineering (ICISCE).
[3]
Kiyoshi Toko,et al.
Advanced Taste Sensors Based on Artificial Lipids with Global Selectivity to Basic Taste Qualities and High Correlation to Sensory Scores
,
2010,
Sensors.
[4]
Samantha Kleinberg,et al.
Automated estimation of food type and amount consumed from body-worn audio and motion sensors
,
2016,
UbiComp.
[5]
Gregory D. Abowd,et al.
Leveraging Context to Support Automated Food Recognition in Restaurants
,
2015,
2015 IEEE Winter Conference on Applications of Computer Vision.
[6]
Noriko Kando,et al.
Continuous Recipe Selection Model Based on Cooking History
,
2016,
SocInfo.
[7]
N. Ryba,et al.
The receptors and cells for mammalian taste
,
2006,
Nature.
[8]
Keiji Yanai,et al.
FoodCam: A real-time food recognition system on a smartphone
,
2015,
Multimedia Tools and Applications.
[9]
Yoko Yamakata,et al.
Situation-based food recommendation for yielding good results
,
2015,
2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).