Published Paper Details:

Dietary management is essential for maintaining a healthy lifestyle, yet traditional food tracking methods such as manual calorie counting and handwritten food diaries are often inaccurate and inconvenient. To address these challenges, this research presents NutriSnap: An Advanced Food Detection and Dietary Management System, which leverages deep learning models for real-time food detection, classification, and AI-driven personalized recommendations. The system allows users to capture or upload food images, automatically identifying food items and providing real-time nutritional analysis, including calorie counts, macronutrient breakdowns, and allergen alerts. Additionally, NutriSnap offers customized meal recommendations based on user preferences, dietary restrictions, and fitness goals. The system has been evaluated for food detection accuracy and classification performance, demonstrating its effectiveness in automating dietary tracking. While challenges such as food presentation variations and portion size estimation remain, the system provides a more efficient and automated alternative to manual food logging. Future improvements, such as enhanced portion size estimation, integration with fitness applications, and mobile app development, will further enhance usability and accuracy. By bridging the gap between food recognition, nutritional analysis, and AI-driven dietary recommendations, NutriSnap aims to help users make informed food choices and adopt healthier eating habits.