Calorie Tracker with Food Classification and Nutritional Analysis

Abstract

This paper presents a web-based application designed for efficient calorie tracking, food classification, and nutritional analysis. The system enables users to log their daily food intake and obtain detailed nutritional information, including macronutrients and selected micronutrients, through integration with the Spoonacular API. A machine learning model built using the Scikit-learn library is employed to classify food items into categories such as high-protein, low-carb, and high-fat, helping users make informed dietary decisions. To enhance personalization and usability, the application incorporates a secure user authentication system that allows individuals to maintain their dietary records and track progress over time. Additionally, a Body Mass Index (BMI) calculator is integrated to assess users’ health status based on their height and weight, enabling them to set appropriate fitness goals such as weight loss, gain, or maintenance. The system is developed using Flask and provides an interactive interface supported by real-time data visualization. Overall, the application serves as a comprehensive and user friendly platform for promoting healthier lifestyle choices through data-driven insights and personalized health monitoring.