Design and implementation of food nutrition information system using SURF and FatSecret API

Abstract

People are constantly looking for ways to improve their health and one approach that could be taken in addition to exercising is managing daily nutrition intake. Even though to get fit and healthy we must manage our daily nutrition intake often we do not know what nutrients are present in food. Therefore, before eating we need to look for nutrition information of the food. The usual process of getting the food's nutrition information is by searching via the google or use some application such as Coach Noom, Calorie Counter, Lose It. In this paper we proposed to make this process smarter, faster, and more efficient by developing an android application that can shows the nutrition information by just taking the picture of the food. We develop an android augmented reality application to help users to get nutritional information in an easy and informative way. The information is displayed in the form of calorie, fat, carbohydrate, and protein per serving. Using this application, users can get the nutritional information simply by taking a picture of the food. From our experiments, the food recognition's accuracy level is 92%, while the average time required to identify the name and the nutrients is 9.295 seconds.