Nutrient Value Estimator via Fruit Detection using YOLOv8

In the contemporary health-conscious era, understanding the nutritional content of consumed foods is paramount. This paper presents a robust system employing the YOLOv8 architecture to facilitate real-time detection and recognition of fruits from images, subsequently estimating their nutritional values. By assembling a diverse dataset of fruit images and corresponding nutrient information, the system undergoes a meticulous process of data preprocessing, feature extraction, and classification using Convolutional Neural Networks (CNNs). The integration of a user-friendly interface developed with Flask allows users to upload images and instantly receive detailed nutritional insights. Experimental results demonstrate a commendable accuracy rate of 92% in fruit detection and recognition, underscoring the efficacy of the YOLOv8 model in this application. Future enhancements aim to incorporate quantity-dependent nutritional assessments and broaden the range of recognizable food items. This system not only streamlines the process of nutritional information retrieval but also empowers individuals to make informed dietary decisions.