Multi-Food Items Detection and Localization in Images

Description:

Keeping track of dietary habits traditionally requires a written diary of the foods consumed in every meal. Mobile apps have added some convenience to the process, but the consumer must still spend time logging each and every meal. To simplify this process, we imagine an automated food camera detection system that would save people time and convenience by autonomously logging meals. Moreover, dietary information would be stored in the cloud, offering easy access to nutritionists and other software platforms. In this project, we lay the foundation for this vision. We prepare a dataset of food images designed for machine learning, then implement an AI model to recognize multiple foods in a given picture. Our research creates a baseline for future work that we hope can be used to track nutritional intake in schools and hospitals, helping decrease malnutrition in vulnerable populations.