Revolutionizing Textile Quality Control: Real-Time Cloth Defect Detection Using YOLO Algorithm For Enhanced Manufacturing Efficiency

Textile quality checking is an essential production process offering blemish-free materials with low waste and cost of production. Hand inspection methods are slow, susceptible to human mistake, and inefficient. This article proposes a sophisticated real-time fabric defect inspection system founded on the YOLOv8 (You Only Look Once) algorithm, a recent deep learning object detection model. With the help of convolutional neural networks (CNNs), YOLOv8 effectively detects and classifies fabric defects like holes, stains, and weaving defects with a very high accuracy. The real-time feature of the system allows the detection of defects in real time, thus improving quality control as well as production efficiency. We test the performance of the system in terms of precision, recall, F1-score, and processing time. Our findings show a significant leap forward from the conventional inspection techniques, showing the potential of AI technologies in transforming textile quality inspection.