ENHANCING PERSONAL WELLNESS THROUGH AI: OBJECT IQ'S IMAGE-BASED DIETARY MONITORING AND PERSONALIZED RECOMMENDATIONS

Abstract

In recent years, the intersection of artificial intelligence (AI) and health technology has yielded powerful tools for enhancing personal wellness and disease prevention. One such application is dietary monitoring via image-based food recognition, which offers a convenient alternative to manual logging of meals and nutrition. This research introduces ObjectIQ, an AI-powered mobile application that utilizes multimodal large language models (LLMs) and advanced computer vision techniques to analyze food images and provide real-time nutritional insights. Unlike traditional diet apps that rely on text-based inputs and fixed databases, ObjectIQ incorporates GPT 4o in a ReAct (Reason + Act) agent framework to interpret images, identify food items, estimate caloric content, and generate recipe suggestions with minimal user input.The system architecture is designed with modularity and scalability in mind. It uses Flutter for cross-platform frontend development, FastAPI for backend API orchestration, Supabase for cloud storage and authentication, and SQLite for offline data persistence. At its core, the AI model processes the input image using GPT 4o's vision capabilities, performs reasoning through chain-of-thought prompting, and interacts with external tools and APIs to retrieve nutritional data. The application offers features such as automated food recognition, real-time calorie estimation, personalized recipe generation, history logging, PDF export, and a user-friendly interface optimized for both fitness and general users. Performance evaluations demonstrate high levels of accuracy, with Top-1 accuracy of 89.3%, Top-3 accuracy of 94.7%, and a mean inference time of approximately 2.1 seconds per image. User testing involving 25 participants revealed high satisfaction in usability, clarity, and practical benefit, with average usability ratings exceeding 4.6/5 across various metrics.