FABRIC IDENTIFICATION AND FABRIC DEFECT DETECTION

Fabric defect detection and fabric identification are crucial tasks in the textile industry. In this research, we propose an integrated system that combines YOLOv5, a state-of-the-art object detection algorithm, with Generative Adversarial Networks (GANs) and convolutional neural networks (CNNs) for fabric defect detection and identification. Our system achieves high precision and recall rates in detecting various fabric defects, such as stains, holes, and pattern irregularities, using YOLOv5. Additionally, GANs and CNNs automate the fabric identification process by generating realistic fabric images and extracting discriminative features. Experimental results demonstrate the effectiveness and superiority of our integrated approach, providing a comprehensive and automated solution for quality control in the textile industry.