1Jožef Stefan International Postgraduate School,Ljubljana,Slovenia.
3Institute of Food,Nutrition and Health (IFNH),ETH Zürich,Zürich,Switzerland.
Public Health Nutr. 2019 May;22(7):1193-1202. doi: 10.1017/S1368980018000708. Epub 2018 Apr 6.
The present study tested the combination of an established and a validated food-choice research method (the 'fake food buffet') with a new food-matching technology to automate the data collection and analysis.
The methodology combines fake-food image recognition using deep learning and food matching and standardization based on natural language processing. The former is specific because it uses a single deep learning network to perform both the segmentation and the classification at the pixel level of the image. To assess its performance, measures based on the standard pixel accuracy and Intersection over Union were applied. Food matching firstly describes each of the recognized food items in the image and then matches the food items with their compositional data, considering both their food names and their descriptors.
The final accuracy of the deep learning model trained on fake-food images acquired by 124 study participants and providing fifty-five food classes was 92·18 %, while the food matching was performed with a classification accuracy of 93 %.
The present findings are a step towards automating dietary assessment and food-choice research. The methodology outperforms other approaches in pixel accuracy, and since it is the first automatic solution for recognizing the images of fake foods, the results could be used as a baseline for possible future studies. As the approach enables a semi-automatic description of recognized food items (e.g. with respect to FoodEx2), these can be linked to any food composition database that applies the same classification and description system.
本研究测试了一种已建立和经过验证的食物选择研究方法（“假食物自助餐”）与一种新的食物匹配技术的结合，以实现数据采集和分析的自动化。
该方法结合了使用深度学习的假食物图像识别和基于自然语言处理的食物匹配和标准化。前者是特定的，因为它使用单个深度学习网络在图像的像素级别执行分割和分类。为了评估其性能，应用了基于标准像素精度和交并比的度量。食物匹配首先描述图像中识别出的每一种食物，然后将食物与它们的成分数据相匹配，同时考虑食物名称和描述。
在由 124 名研究参与者采集的、提供 55 种食物类别的假食物图像上训练的深度学习模型的最终准确率为 92.18%，而食物匹配的分类准确率为 93%。
本研究结果朝着饮食评估和食物选择研究的自动化迈出了一步。该方法在像素精度方面优于其他方法，并且由于它是识别假食物图像的首个自动解决方案，因此其结果可以作为未来可能进行的研究的基准。由于该方法能够对识别出的食物项目进行半自动描述（例如，就 FoodEx2 而言），这些描述可以与应用相同分类和描述系统的任何食物成分数据库相关联。
