A multi-scale dynamic convolution-based visual inspection network for nondestructive detection of fabric surface defects

Fabric surface defects can significantly affect the appearance and performance of textile products, often resulting in reduced product quality and economic loss. As a key step in non-destructive quality control, fabric defect detection requires both high accuracy and real-time performance under complex industrial environments. In this study, we present a visual inspection framework based on an improved YOLOv11 architecture for the non-destructive detection of fabric surface defects. A custom image acquisition system, integrating a high-resolution industrial camera and ring-shaped LED lighting, is designed to enhance defect edge contrast and provide high-quality input data. The proposed network incorporates a C3k2-DSConv module with dynamic snake convolution to better capture irregular defect geometries at multiple scales, and introduces a lightweight Slim-Neck structure with GSConv and VoV-GSCSP for efficient feature fusion. Additionally, the WIoU loss function is adopted to stabilise training and improve localisation accuracy. Experimental results on the Cloth_dataset demonstrate a mAP of 96.1%, outperforming existing detectors in both speed and accuracy. This approach provides a practical and efficient solution for real-time, non-destructive defect detection in textile manufacturing lines.