Automated Food Recognition and Volume Estimation for Dietary Assessment and Nutritional Monitoring

This research explores the integration of computer vision and artificial intelligence (AI) for food detection and volume estimation to enhance nutritional analysis. As chronic diseases like obesity, diabetes, and cardiovascular conditions rise, accurate monitoring of food intake becomes critical. Traditional methods such as self-reported food diaries have limitations in precision and reliability. By using deep learning models, particularly Convolutional Neural Networks (CNNs) and object detection algorithms like YOLOv11, food items can be detected and segmented from images, followed by volume estimation to determine portion sizes. This approach allows for automated, real-time analysis of food consumption, reducing biases from self-reported data and offering more accurate assessments of nutritional content. The research highlights the potential of combining food recognition, volume estimation, and nutritional databases to calculate calorie and macronutrient information. By addressing challenges such as food shape variation and dataset diversity, these AI-powered systems can be further refined to improve accuracy and generalization across different food types and cultural cuisines. This methodology has the potential to revolutionize dietary tracking, offering real-time, personalized nutrition management, benefiting individuals, healthcare professionals, and large- scale studies. The findings suggest that with continued advancements, food detection and volume estimation systems could play a crucial role in public health strategies for better dietary management.