The concerns for a healthier diet are increasing day by day, especially in diabetics wherein the aim of healthier diet can only be achieved by keeping a track of daily food intake and glucose-level. As a consequence, there is an ever-increasing need for automatic tools able to help diabetics to manage their diet and also help physicians to better analyse the effects of various types of food on the glucose-level of diabetics. In this paper, we propose an intelligent food recognition and tracking system for diabetics, which is potentially an essential part of a mobile application that we propose to couple food intake with the blood glucose-level using glucose measuring sensors. For food recognition, we rely on several feature extraction and classification techniques individually and jointly using an early and three different late fusion techniques, namely (i) Particle Swarm Optimisation (PSO), (ii) Genetic Algorithms (GA) based fusion and (iii) simple averaging. Moreover, we also evaluate the performance of several handcrafted and deep features and compare the results against state-of-the-art. In addition, we collect a large-scale dataset containing images from several types of local Middle-Eastern food, which is intended to become a powerful support tool for future research in the domain.

中文翻译：

---

中东美食自动识别系统

对健康饮食的关注日益增加，特别是在糖尿病患者中，只有通过跟踪每日食物摄入量和葡萄糖水平才能实现健康饮食的目的。结果，对能够帮助糖尿病患者管理饮食并帮助医师更好地分析各种食物对糖尿病患者葡萄糖水平的影响的自动工具的需求日益增长。在本文中，我们提出了一种针对糖尿病患者的智能食品识别和跟踪系统，这可能是移动应用程序的重要组成部分，我们建议使用葡萄糖测量传感器将食物摄入量与血糖水平相结合。为了识别食物，我们分别依靠几种特征提取和分类技术，并结合使用早期和三种不同的后期融合技术，即（i）粒子群优化（PSO），（ii）基于遗传算法（GA）的融合和（iii）简单平均。此外，我们还评估了一些手工制作的深层功能的性能，并将结果与​​最新技术进行了比较。此外，我们收集了包含来自几种当地中东食物的图像的大规模数据集，目的是成为该领域未来研究的有力支持工具。