The textile industry relies heavily on quality control to ensure product consistency and customer satisfaction. Traditional manual inspection methods are timeconsuming, prone to human error, and often lack consistency. To address these challenges, this research proposes an automated fabric defect detection system using the YOLOv8-m model. The proposed system utilizes a camera interfaced with a Raspberry Pi to capture high-resolution images of woven fabrics. The YOLOv8-m model is employed to accurately identify and classify defects such as holes and cuts. The model achieves impressive performance metrics, including an accuracy of 95%, precision of 94%, and recall of 93%, with an average processing time of 0.2 seconds per image. By automating the defect detection process, this system offers several benefits, including improved efficiency, reduced labor costs, and enhanced product quality. It can be easily integrated into textile manufacturing processes, enabling real-time monitoring and quality control. This research contributes to the advancement of automated quality control systems in the textile industry.
Fabric Defect Detection System for Textile Webmaterial using YOLOv8 on Raspberry Pi
06.11.2024
1053573 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Defect detection in textile fabric images using subband domain subspace analysis
British Library Online Contents | 2007
|British Library Online Contents | 2006
|Traffic Sign Detection Using YOLOv8
IEEE | 2024
|