Fabric Defect Detection Research Articles

QA-USTNet: Yarn-dyed fabric defect detection via U-shaped Swin Transformer Network based on Quadtree Attention

The detection and location of yarn-dyed fabric defects is a crucial and challenging problem in actual production scenarios. Recently, unsupervised fabric defect detection methods based on convolutional neural networks have attracted more attention. However, the convolutional neural networks often neglect to model the global receptive field of images, which further influence the defect detection ability of the model. In this article, we propose a U-shaped Swin Transformer network based on Quadtree attention framework for unsupervised yarn-dyed fabric defect detection. The method via U-shaped network based on Swin Transformer, the Swin Transformer adopts local attention to effectively learn features, and the U-shaped network realizes pixel-level reconstruction of images. The Quadtree attention is used to effectively capture the global features of the image, and model the global receptive field, and then better reconstruct the yarn-dyed fabric image. The improved Euclidean residual enhances the detection ability of unobvious defects, and obtains the final defect detection results. The proposed method effectively avoids the difficulty of collecting a large number of defective samples and manual labeling. Our method obtains 51.34% F1 and 38.30% intersection over union on the YDFID-1 dataset. Experimental results show that the proposed method can achieve higher accuracy of fabric defect detection and location compared with other methods.

Attention-Gate-based U-shaped Reconstruction Network (AGUR-Net) for color-patterned fabric defect detection

Color-patterned fabrics possess changeable patterns, low probability of defective samples, and various forms of defects. Therefore, the unsupervised inspection of color-patterned fabrics has gradually become a research hotspot in the field of fabric defect detection. However, due to the redundant information of skip connections in the network and the limitation of post-processing, the current reconstruction-based unsupervised fabric defect detection methods have difficulty in detecting some defects of color-patterned fabrics. In this article, we propose an Attention-Gate-based U-shaped Reconstruction Network (AGUR-Net) and a dual-threshold segmentation post-processing method. AGUR-Net consists of an encoder, an Atrous Spatial Pyramid Pooling module and an attention gate weighted fusion residual decoder. The encoder is used to obtain more representative features of the input image via EfficientNet-B2. The Atrous Spatial Pyramid Pooling module is used to enlarge the receptive field of the network and introduce multi-scale information into the decoder. The attention-gate-weighted residual fusion decoder is used to fuse the features of the encoder with the features of the decoder to obtain the reconstructed image. The dual-threshold segmentation post-processing is used to obtain the final defect detection results. Our method achieves a precision of 59.38%, a recall of 59.1%, an F1 of 54.31%, and an intersection-over-union ratio of 41.18% on the public dataset YDFID-1. The experimental results show that the proposed method can better detect and locate the defects of color-patterned fabrics compared with several other state-of-the-art unsupervised fabric defect detection methods.

Fabric defect detection based on low-rank decomposition with factor group-sparse regularizer

Recently, many low-rank-based methods in terms of detecting defects in fabric images have been proposed. However, there are two disadvantages of these methods. First, current low-rank based methods use the nuclear norm as the surrogate of rank, which causes inefficient optimization process and sub-optimal performance. Second, low-rank defective regions cannot be detected by low-rank based models. Thus, we propose a factor group-sparse regularized low-rank decomposition model (FGSRLRD) to solve these problems. This method takes the factor group-sparse regularizer as the surrogate of rank, which is more efficient as singular value decomposition (SVD) is not applied in the optimization process. Better performance is achieved as the factor group-sparse regularizer is a more accurate approximation of the rank. In addition, the weight matrix generated by the lightweight autoencoder is incorporated into the object function of FGSRLRD to guide locating defective regions. Besides, as low-rank defective regions cannot be segmented by low-rank models, this method constructs a fusion image of the prior image and the sparse image to highlight the defective regions. The performance of the proposed method is evaluated on two standard datasets, and the results indicate that the suggested method outperforms the existing state-of-the-art methods in locating the defective regions on fabric images.

Automatic fabric defect detection using optimal Gabor filter based on hybrid beetle antennae search–gravitational search algorithm

Automatic fabric defect detection using optimal Gabor filter based on hybrid beetle antennae search–gravitational search algorithm

CACFNet: Fabric defect detection via context-aware attention cascaded feedback network

Fabric defect detection plays an irreplaceable role in the quality control of the textile manufacturing industry, but it is still a challenging task due to the diversity and complexity of defects and environmental factors. Visual saliency models imitating the human vision system can quickly determine the defect regions from the complex texture background. However, most visual saliency-based methods still suffer from incomplete predictions owing to the variability of fabric defects and low contrast with the background. In this paper, we develop a context-aware attention cascaded feedback network for fabric defect detection to achieve more accurate predictions, in which a parallel context extractor is designed to characterize the multi-scale contextual information. Moreover, a top-down attention cascaded feedback module was devised adaptively to select the important multi-scale complementary information and then transmit it to an adjacent shallower layer to compensate for the inconsistency of information among layers for accurate location. Finally, a multi-level loss function is applied to guide our model for generating more accurate prediction results via optimizing multiple side-output predictions. Experimental results on the two fabric datasets built under six widely used evaluation metrics demonstrate that our proposed framework outperforms state-of-the-art models remarkably.

Adaptively Fused Attention Module for the Fabric Defect Detection

In the fabric manufacturing industry, fabric defect detection is a practical yet challenging task, due to the problem of defects with small sizes or unremarkable appearances distributed in fabric images with high resolution. Some deep‐learning‐based solutions try to tackle the aforementioned problem but with limited achievements. Herein, a brand new module called adaptively fused attention module (AFAM) is proposed to improve the detection performance by enabling the network to concentrate more on the small or unremarkable defects in terms of 1) enhancing the feature maps both spatial‐wise and channel‐wise, 2) enhancing the attention information flow between the channel‐attention feature map and the spatial‐attention feature map, and 3) enriching background information. Experiments on the MS‐COCO dataset show that AFAM reaches higher AP than other state‐of‐the‐art (SOTA) attention modules (e.g., squeeze‐and‐excitation network [SE], efficient channel attention [ECA], convolutional block attention module [CBAM]). Meanwhile, on the Smart Diagnosis of Cloth Flaw Dataset (CloF), the Cascade R‐CNN (Resnext101) + AFAM outperforms the SOTA in the official leaderboard of the CloF dataset. Speed‐wisely, the solution achieves a 12.19‐FPS on RTX 3090, thus making it practical to be applied in the industry of fabric defect detection.

A context-aware progressive attention aggregation network for fabric defect detection

Fabric defect detection plays a critical role for measuring quality control in the textile manufacturing industry. Deep learning-based saliency models can quickly spot the most interesting regions that attract human attention from the complex background, which have been successfully applied in fabric defect detection. However, most of the previous methods mainly adopted multi-level feature aggregation yet ignored the complementary relationship among different features, and thus resulted in poor representation capability for the tiny and slender defects. To remedy these issues, we propose a novel saliency-based fabric defect detection network, which can exploit the complementary information between different layers to enhance the representation features ability and discrimination of defects. Specifically, a multi-scale feature aggregation unit (MFAU) is proposed to effectively characterize the multi-scale contextual features. Besides, a feature fusion refinement module (FFR) composed of an attention fusion unit (AFU) and an auxiliary refinement unit (ARU) is designed to exploit complementary important information and further refine the input features for enhancing the discriminative ability of defect features. Finally, a multi-level deep supervision (MDS) is adopted to guide the model to generate more accurate saliency maps. Under different evaluation metrics, our proposed method outperforms most state-of-the-art methods on our developed fabric datasets.

MobileNetV2-based Transfer Learning Model with Edge Computing for Automatic Fabric Defect Detection

In textile manufacturing, fabric defect detection is an essential quality control step and a challenging task. Earlier, manual efforts were applied to detect defects in fabric production. Human exhaustion, time consumption, and lack of concentration are the main problems in the manual defect detection process. Machine vision systems based on deep learning play a vital role in the Industrial Internet of things (IIoT) and fully automated production processes. Deep learning centered on Convolution Neural Network (CNN) models have been commonly used in fabric defect detection, but most of these models require high computing resources. This work presents a lightweight MobileNetV2-based Transfer Learning model to assist defect detection with low power consumption, low latency, easy upgrade, more efficiency, and an automatic visual inspection system with edge computing. Firstly, different image transformation techniques were performed as data augmentation on four fabric datasets for the model's adaptability in various fabrics. Secondly, fine-tuning hyperparameters of the MobileNetV2 with transfer learning gives a lightweight, adaptable and scalable model that suits the resource-constrained edge device. Finally, deploy the trained model to the NVIDIA Jetson Nano-kit edge device to make its detection faster. We assessed the model based on its accuracy, sensitivity rate, specificity rate, and F1 measure. The numerical simulation reveals that the model accuracy is 96.52%, precision is 96.52%, recall is 96.75%, and F1-Score is 96.52%.

A Lightweight Detector Based on Attention Mechanism for Fabric Defect Detection

Defects on fabric surfaces are difficult to identify owing to unsuitable computing devices, highly complex algorithms, small size, and high degree of integration with the fabric. To this end, this study proposes a lightweight fabric defect-detection network, YOLO-SCD, based on attention mechanism. The introduction of depth-wise separable convolution and the attention mechanism enhanced the capacity of the neck network to extract the defective features and increased the detection speed of the overall network. The extensive experimental results revealed that YOLO-SCD achieved an average accuracy of 82.92%, effective improvement of 8.49% in mAP, and an improvement of 37 fps compared to the original YOLOv4 on a standard fabric defect dataset. By leveraging its swift detection speed and high efficiency, YOLO-SCD excels in both the general fabric defect category and the difficult-to-detect fabric. Overall, it exhibited strong performance in detecting both minor flaws and flaws with high fabric integration. Furthermore, the proposed model was extended to steel datasets with similar characteristics.

FA-YOLO: A High-Precision and Efficient Method for Fabric Defect Detection in Textile Industry

FA-YOLO: A High-Precision and Efficient Method for Fabric Defect Detection in Textile Industry

HookNet: Efficient Multiscale Context Aggregation for High-Accuracy Detection of Fabric Defects

Automatic defect detection is a critical stage of quality control in the textile industry. Because defects vary in texture structure, size, and spatial distribution, existing defect detection methods have difficulty in achieving a perfect trade-off between detection efficiency, accuracy, and generalizability. This paper presents an advanced fabric defect detection model based on a deep learning algorithm. A novel parallel dilated attention module was designed: this is nested in the deep layers of the neural network backbone to establish global channel dependencies and capture multiscale contextual information. Further, a hook-shaped feature pyramid network was developed for multiscale context aggregation: this directs the network to focus on lower-level features and is helpful for further improving detection efficiency without sacrificing detection accuracy. In addition, the Alpha-GIoU loss is used to improve the accuracy of bounding box regression because of its modulated power parameter α. The advantages and effectiveness of the proposed method were statistically analyzed using data from several public datasets. The code is available at https://github.com/aabb605/HookNet.

A lightweight model for digital printing fabric defect detection based on YOLOX

Online detection of digital printing defects is a necessary but challenging topic. The performance of the current detection methods is still not ideal for the diversified patterns of digital printing fabric defects and the realtime requirements of online detection. In this paper, we proposed a lightweight model of digital printing fabric defect detection based on YOLOX. Firstly, according to the characteristics of many types of defects and complex background of digitally printed fabrics, a defect detection network structure based on YOLOX is constructed. Then, the SE attention module is introduced to enhance important features and weaken unimportant features, which make the extracted features more directional. And it can further solve the influence of small feature size on the detection accuracy of small targets. The experimental results show that the proposed model has a detection accuracy of 66.2 mAP on our self-built dataset, which is 2.7 percentage points higher than YOLOX. This method can effectively solve the problem that low detection accuracy of small defects. The proposed model can meet the real-time requirements and improve the detection accuracy of small target defects.

An Inventive Method to Fabric Part Structural Defect Detection Using Frame Harmonizing

Using a frame harmonizing based approach, this paper examines paper defects. In the textiles industry, the quick cutting and sewing of fabric has resulted in a lot of small mistakes, making this task extremely difficult. Especially these deformities won't be quickly recognized by specialists as well as programming. A novel frame harmonizing method is used in our system to find flaws in the fabric production process. Transformation and filtering techniques are used for the inputted fabric image frame. The conventional outline extraction method Berkeley edge detector is used to extract the edge map. Contour-based features are extracted and classified by K-Nearest Neighbour (KNN) classifier. The experimentation with real-time data set produced the outstanding performance results when compared with state of the art methods.

Multi-stage unsupervised fabric defect detection based on DCGAN

Multi-stage unsupervised fabric defect detection based on DCGAN

An Efficient and Intelligent Detection Method for Fabric Defects based on Improved YOLOv5.

Limited by computing resources of embedded devices, there are problems in the field of fabric defect detection, including small defect size, extremely unbalanced aspect ratio of defect size, and slow detection speed. To address these problems, a sliding window multihead self-attention mechanism is proposed for the detection of small targets, and the Swin Transformer module is introduced to replace the main module in the original YOLOv5 algorithm. First, to reduce the distance between several scales, the weighted bidirectional feature network is employed on embedded devices. In addition, it is helpful to improve the perception of small-target faults by incorporating a detection layer to achieve four-scale detection. At last, to improve the learning of positive sample instances and lower the missed detection rate, the generalized focal loss function is finally implemented on YOLOv5. Experimental results show that the accuracy of the improved algorithm on the fabric dataset reaches 85.6%, and the mAP is increased by 4.2% to 76.5%, which meets the requirements for real-time detection on embedded devices.

Defect detection algorithm for fabric based on deformable convolutional network

The detection of fabric defects is an important aspect of textile quality management. This paper proposes an algorithm based on YOLOv3 and deformable convolutional network to solve the problems of low accuracy, high rate of missed and false detection, and high labor cost existing in traditional manual detection methods. First, data enhancement is adopted to address the problem of imbalanced categories of defective samples in the dataset. Then, the Resnet101 model is used to extract the features, and the original convolution operation is replaced by deformable convolution to balance the accuracy and speed of the model. Finally, the focal loss function is introduced to solve the insensitivity problem of the model to difficult defect samples. Experimental results show that this method can quickly and accurately detect defects on the surface of fabrics. In real-time detection, the average accuracy of this method is 8.3% higher than that of YOLOv3. The average accuracy of multiple categories of detection reaches more than 90%, and the detection effect of small defect targets, such as three silk, is also relatively better.

Image restoration fabric defect detection based on the dual generative adversarial network patch model

The training of supervised learning requires the use of ground truth, which is difficult to obtain in large quantities in production practice. Unsupervised learning requires only flawless and anomalous images of fabrics, but inevitably generates a great deal of background noise when performing result generation, which reduces the quality of results. To overcome these limitations, we propose a new approach: image restoration fabric defect detection based on the dual generative adversarial network patch model (DGPM). We train with a modified generative adversarial network using only flawless and anomalous images of the fabric. We propose the patch model to directly obtain specific information about fabric defects and add a self-attentive model to reduce the generation of background noise. The performance of the DGPM is evaluated on box-, star-, and dot-patterned fabric databases. The true positive rate (TPR) of the box type is 81.56% and the f-measure is 62.69%, the TPR of the dot type is 83.72% and the f-measure is 67.33%, and the TPR of the star type is 79.79% and the f-measure is 64.65%.

Fabric defect detection based on saliency map and keypoints

Fabric defect detection based on saliency map and keypoints

Context receptive field and adaptive feature fusion for fabric defect detection

Context receptive field and adaptive feature fusion for fabric defect detection

Semantic Segmentation Using DeepLabv3+ Model for Fabric Defect Detection

Currently, numerous automatic fabric defect detection algorithms have been proposed. Traditional machine vision algorithms that set separate parameters for different textures and defects rely on the manual design of corresponding features to complete the detection. To overcome the limitations of traditional algorithms, deep learning-based correlative algorithms can extract more complex image features and perform better in image classification and object detection. A pixel-level defect segmentation methodology using DeepLabv3+, a classical semantic segmentation network, is proposed in this paper. Based on ResNet-18, ResNet-50 and Mobilenetv2, three DeepLabv3+ networks are constructed, which are trained and tested from data sets produced by capturing or publicizing images. The experimental results show that the performance of three DeepLabv3+ networks is close to one another on the four indicators proposed (Precision, Recall, F1-score and Accuracy), proving them to achieve defect detection and semantic segmentation, which provide new ideas and technical support for fabric defect detection.