Research on textile Defect detection Algorithm for Deep Learning

Textile defect detection is a crucial aspect of the textile industry. H owever, the detection accuracy is often low due to the small size of textile de fects and the influence of fabric texture background. To address these issues, we propose a textile defect detection algorithm based on YOLOv8.The reparameter ized structure was introduced to the original YOLOv8 to achieve hardware effici ency with the RepGhost module. The head section incorporates a new GD Mechanism and includes the Wasserstein Distance loss function.This method accurately ide ntifies the location and type of defects in textiles with high precision under complex backgrounds, meeting the needs of industrial textile production. We con ducted training and comparison experiments on different models using the AITEX public dataset and Roboflow open source dataset. We also designed ablation expe riments to verify the considerable improvement of each enhancement on the evalu ation index. The experimental results indicate that the detection accuracy of t he enhanced YOLOv8 model in the task of detecting textile defects has increased by 18.9% to 93.8% on the public dataset. The number of parameters has increase d by 10.94MB, and the FLOPs have increased from 8.2G to 11.3G. The improved alg orithm has significantly enhanced the accuracy. It can effectively handle large amounts of data and recognize defects even under complex backgrounds, meeting the fast, complex, and high-precision requirements of the textile industry.