Improved RT-DETR Network for High-Quality Defect Detection on Digital Printing Fabric

Digital printing technology has been successfully implemented in actual production within factories. However, issues with various digital printing heads can still lead to defects in printed fabrics, reducing the pass rate of digital printing textiles. To promptly detect these printing defects, we have constructed a dataset of fabric defects caused by digital printing head malfunctions and propose a high-quality digital printing defect detection model tailored to our self-built dataset. Our model is built upon the Real-Time Detection Transformer (RT-DETR) framework, with an added detection head designed for detailed processing in complex backgrounds. We also incorporated an inverted residual mobile block (iRMB) to integrate attention mechanisms into the network’s feature extraction process, and improved the bounding box loss function to enhance the model’s detection accuracy. Experimental results demonstrate that our model achieves state-of-the-art accuracy on the COCO metrics, with a detection accuracy of 0.588 on the AP index, compared to other advanced detection models. This method effectively identifies fabric defects caused by nozzle failures in digital printing equipment, offering a novel solution for fabric defect detection.