RECOGNITION AND SEPARATION OF FRESH AND ROTTEN FRUITS USING YOLO ALGORITHM

Abstract

Fruit quality evaluation is crucial in today's food processing and distribution systems to assure consumer safety and minimize food waste. The fruits are often sorted manually using visual examination, which is time-consuming, labor-intensive, and prone to error. To address these issues, we can use the capabilities of computer vision and machine learning to build a powerful and real-time fruit quality evaluation system. This project presents an innovative approach for the automated detection and classification of fresh and rotten fruits through object detection. This project demonstrates a novel approach for the automated detection of fresh and rotten fruits on conveyor belts using the YOLO algorithm and Raspberry Pi. The YOLOv7 object detection model was used for deep learning. The trained ‘Model’ is capable of recognizing the color and texture of the fruit surface as features to say whether it is rotten or fresh. The map of our trained model is 0.986%, F1_score is 0.96, precision is 0.957 And recall is 0.966. The main focus of this project is automation of fruit sorting through conveyor belt by detecting and recognizing rotten and fresh fruits.