This paper proposes a robust fabric defect detection method, based on the improved RefineDet. This is done using the strong object localization ability and good generalization of the object detection model. Firstly, the method uses RefineDet as the base model, inheriting the advantages of the two-stage and one-stage detectors and can efficiently and quickly detect defect objects. Secondly, we design an improved head structure based on the Full Convolutional Channel Attention (FCCA) block and the Bottom-up Path Augmentation Transfer Connection Block (BA-TCB), which can improve the defect localization accuracy of the method. Finally, the proposed method applies many general optimization methods, such as attention mechanism, DIoU-NMS, and cosine annealing scheduler, and verifies the effectiveness of these optimization methods in the fabric defect localization task. Experimental results show that the proposed method is suitable for the defect detection of fabric images with unpattern background, regular patterns, and irregular patterns.
Focusing on the fabric defect detection with periodic-pattern and pure-color texture, an algorithm based on Direction Template and Image Pyramid is proposed. The detection process is divided into two stages: model training and defect localization. During the model training stage, we construct an Image Pyramid for each fabric image that does not contain any defects. Then, Stacked De-noising Convolutional Auto-Encoder (SDCAE) is used for image reconstruction, its training sets are created by randomly extracting image blocks from image pyramid, which makes the feature information of the image block more abundant and the reconstruction effect of the model more remarkable. During the defect localization stage, the image to be detected is divided into a number of blocks, and is reconstructed by using the trained SDCAE model. Then, the candidate defective image blocks are roughly located by using the Structural Similarity Index Measurement after the image reconstruction. Subsequently, direction template is introduced to solve the problem of fabric deformation caused by factors such as fabric production environment and photographic angle. We select the direction template of the images to be detected, filter the candidate defective blocks, and further reduce false detection rate of the proposed algorithm. Furthermore, there is no need to calculate size of periodic-pattern during detection for periodic textured fabric. The algorithm is also suitable for defect detection for pure-color fabrics. The experimental results show that the proposed algorithm can achieve better defect localization accuracy, and receive better results in detection of pure-color fabrics, compared with traditional methods. INDEX TERMS Fabric defect detection, direction template, image pyramid, stack de-noising convolutional auto-encoder, similarity measure.
The fabric defect detection algorithm based on object detection has become a research hotspot. The method based on the Single Shot MultiBox Detector (SSD) model has a fast detection speed, but the detection accuracy is insufficient. To balance the detection speed and accuracy of the model and meet the actual needs of the industry, an improved fabric defect detection algorithm based on SSD is proposed in this study. The Fully Convolutional Squeeze-and-Excitation (FCSE) block is added into the traditional SSD to improve the detection accuracy of the model. The number of default boxes was adjusted to accommodate the detection of long strip defects on fabric surface. Experimental results on the TILDA and Xuelang dataset confirm that our detection method based on SSD efficiently detected various fabric defects.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.