Automatic Textile Stain Detection Using Yolo Algorithm

Abstract

Automatic textile stain detection is essential for optimizing the quality control process within the textile industry. Traditional hands-on inspection methods are time-consuming, not immune to errors, and expensive. This research paper proposes a novel approach for automatic textile stain detection using the YOLO (You Only Look Once) algorithm, a state-of-the-art object detection model. The proposed system utilizes a YOLOv5 model trained on a diverse dataset of stained textile images to accurately identify and localize stains in real-time. The model's performance is evaluated based on standard metrics such as precision, recall, and mean average precision (mAP). Experimental results Showcase the impact of the YOLO-based approach in achieving high accuracy and efficiency in stain detection, significantly outperforming traditional methods. This research contributes to the advancement of automation in the textile industry, ultimately leading to improved quality control, reduced costs, and enhanced productivity.