Using Distance Estimation and Deep Learning to Simplify Calibration in Food Calorie Measurement
This work addresses the need for user-friendly and accurate calorie intake measurement tools, which is important for health and diet management, but it appears incremental as it builds on existing image-based food recognition systems.
The paper tackles the problem of automatically calibrating food portion sizes for calorie measurement by proposing a method that uses deep learning, mobile cloud computing, distance estimation, and size calibration on a mobile device, achieving an average accuracy improvement to 95% compared to previous work.
High calorie intake in the human body on the one hand, has proved harmful in numerous occasions leading to several diseases and on the other hand, a standard amount of calorie intake has been deemed essential by dieticians to maintain the right balance of calorie content in human body. As such, researchers have proposed a variety of automatic tools and systems to assist users measure their calorie in-take. In this paper, we consider the category of those tools that use image processing to recognize the food, and we propose a method for fully automatic and user-friendly calibration of the dimension of the food portion sizes, which is needed in order to measure food portion weight and its ensuing amount of calories. Experimental results show that our method, which uses deep learning, mobile cloud computing, distance estimation and size calibration inside a mobile device, leads to an accuracy improvement to 95% on average compared to previous work