Kogias K, Andreadis I, Dalakleidi K, Nikita K S
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:2603-2606. doi: 10.1109/EMBC.2018.8512839.
Accurate estimation of food's macronutrient content for people with Diabetes Mellitus (DM) is of great importance, as it determines postprandial insulin dosage. This paper introduces a classification system for food images that is adjusted to the nutritional needs of people with DM. A two-level image classification scheme, exploiting Convolutional Neural Networks (CNNs), is proposed, in order to classify an image in one of eight broad food categories with similar macronutrient content and then assign it to a specific food within that category. To this end, a visual dataset, namely NTUA-Food 2017, has been designed, consisting of 3248 images organized in eight broad food categories of totally 82 different foods. Moreover, a novel evaluation metric is proposed, which penalizes classification errors proportionally to the discrepancy in postprandial blood sugar levels between the actual and predicted class. The proposed system achieves 84.18% and 85.94% classification accuracy at the first and second level of classification, respectively, on the NTUA-Food 2017 dataset. The algorithm developed for the first level of classification on the NTUA-Food 2017 dataset improves classification accuracy on the benchmark Food Image Dataset (FID) to 97.08% outperforming previous approaches. The algorithm's mean error in terms of carbohydrate content estimation on the NTUA-Food 2017 dataset is less than 2 g per food serving.
准确估算糖尿病患者食物中的宏量营养素含量非常重要，因为这决定了餐后胰岛素剂量。本文介绍了一种针对食物图像的分类系统，该系统根据糖尿病患者的营养需求进行了调整。提出了一种利用卷积神经网络（CNN）的两级图像分类方案，以便将图像分类到八个宏量营养素含量相似的宽泛食物类别之一，然后将其分配到该类别中的特定食物。为此，设计了一个视觉数据集，即NTUA - Food 2017，它由3248张图像组成，这些图像被组织成八个宽泛的食物类别，总共82种不同的食物。此外，还提出了一种新颖的评估指标，该指标根据实际类别和预测类别之间餐后血糖水平的差异按比例惩罚分类错误。在NTUA - Food 2017数据集上，所提出的系统在第一级和第二级分类中的分类准确率分别达到了84.18%和85.94%。在NTUA - Food 2017数据集上为第一级分类开发的算法将基准食物图像数据集（FID）上的分类准确率提高到了97.08%，优于先前的方法。该算法在NTUA - Food 2017数据集上碳水化合物含量估计方面的平均误差小于每份食物2克。
