Annapurna: An automated smartwatch-based eating detection and food journaling system

Abstract

Maintaining a food journal can allow an individual to monitor eating habits, including unhealthy eating sessions, food items causing severe reactions, or portion size related information. However, manually maintaining a food journal can be burdensome. In this paper, we explore the vision of a pervasive, automated, completely unobtrusive, food journaling system using a commodity smartwatch. We present a prototype system — Annapurna— which is composed of three key components: (a) a smartwatch-based gesture recognizer that can robustly identify eating-specific gestures occurring anywhere, (b) a smartwatch-based image captor that obtains a small set of relevant images (containing views of the food being consumed) with a low energy overhead, and (c) a server-based image filtering engine that removes irrelevant uploaded images. Through lessons learnt from multiple user studies, we refine Annapurna progressively and show that our vision is indeed achievable: Annapurna can identify eating episodes and capture food images (involving a very wide diversity in food content, eating styles and environments) in over 95% of all free-living eating episodes.