IoTCaloTrack: An IoT-Enabled Real-Time Calorie Tracking System

Abstract: In today’s health-conscious world and simultaneously the world of unhealthy and processed foods, managing what a person eats, how much a person eats and most of all how much it affects their body is getting harder as time goes on. In this paper, IoTCaloTrack, a novel Internet-of-Things framework for real-time calorie monitoring using a web frontend and Python FastAPI backend is introduced. This system integrates a microcontroller with a camera and load- cell sensor, a FastAPI server, and the Google Gemini AI for food recognition. In a typical workflow, a user triggers meal capture via the web interface; the IoT device then captures a photo of the food and measures its weight. The backend then uploads the image to the Gemini API, which identifies the dish. Knowing the food type and its measured weight, IoTCaloTrack computes caloric content by multiplying weight (in grams) by a nutrient database value. The result is stored and returned to the web client. Gemini’s high accuracy (20% improved recognition over prior methods) ensures reliable identification. Experiments show that Gemini 2.5 processes images very quickly (≈1 second faster than earlier AI models), enabling near-instant calorie estimates. It is a comprehensive calorie management and tracking system where each user can independently store their nutritional data and access it conveniently.

Keywords: IoT, FastAPI, Web Frontend, Calorie Tracking, Food Recognition, Gemini API, Python.