Personalised Food Classifier and Nutrition Interpreter Multimedia Tool Using Deep Learning

摘要

Food plays a vital role in our day-to-day life to get all the required nutrients for a healthy lifestyle. In recent years, obesity has become one of the major concerns among humans. Therefore, it is necessary for each individual to keep track of the nutrition intake in order to have a balanced diet. This has scaled up the implementation of automatic food analysis and semantic food detection using different image classification approaches, among which Deep Learning has brought a series of breakthroughs in this field. We have proposed the Food Classifier and Nutrition Interpreter (FCNI), a user-friendly tool that classifies various food types with a different graphical representation of food nutrients values in terms of calorie estimation along with a multimedia audio response. FCNI improves state-of-the-art food detection by a considerable margin on achieving about 96.81% accuracy.