期刊
FOOD CHEMISTRY
卷 373, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.foodchem.2021.130994
关键词
Food nutrients; Chinese market food; Deep learning; Convolutional neural network; Food composition; Food image; Nutrients
资金
- Chinese Scholarship Council
- National Key R&D Program of China [2018YFC1603300]
- National Natural Science Foundation of China [71633005]
This study utilized deep learning techniques to establish a nutrition estimation database with high accuracy and practical value. The establishment and optimization of the first food image database in the Chinese market, ChinaMartFood-109, provides important support and inspiration for research in the field of food analysis.
With commercialization of deep learning (DL) models, daily precision dietary record based on images from smartphones becomes possible. This study took advantage of DL techniques on visual recognition tasks and proposed a suite of big-data-driven DL models regressing from food images to their nutrient estimation. We established and publicized the first food image database from the Chinese market, named ChinaMartFood-109. It contained 10,921 images with 23 nutrient contents, covering 18 main food groups. Inception V3 was optimized using other state-of-the-art deep convolutional neural networks, achieving up to 78 % and 94 % for top-1 and top-5 accuracy, respectively. Besides, this research compared three nutrient estimation algorithms and achieved the best regression coefficient (R-2) by normalization + AM compared with arithmetic mean and harmonic mean, validating applicability in practice as well as theory. These encouraging results provide further evidence supporting artificial intelligence in the field of food analysis.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据