Fabric Defect Research Articles

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.

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.

Textile defect recognition network based on label embedding

Textile defect recognition network based on label embedding

A Novel Industrial Application of CNN Approach: Real Time Fabric Inspection and Defect Classification on Circular Knitting Machine

Fabric Automatic Visual Inspection (FAVI) system provides reliable performance on fabric defects inspection. This study presents a machine vision system developed to adapt in circular knitting machines where fabric defects can be automatically controlled and detected defects can be classified. The knitted fabric surface are detected during real-time manufacturing. For the classification process, three different transfer learning architectures (ResNet-50, AlexNet, GoogLeNet) have been applied. The five common knitted fabric defects were recognized with the artificial intelligence-based software and classified with an average success rate of 98% using ResNet-50 architecture. The success rates of the trained networks were compared.

딥러닝을 이용한 직물의 결함 검출에 관한 연구

Identifying defects in textiles is a key procedure for quality control. This study attempted to create a model that detects defects by analyzing the images of the fabrics. The models used in the study were deep learning-based VGGNet and ResNet, and the defect detection performance of the two models was compared and evaluated. The accuracy of the VGGNet and the ResNet model was 0.859 and 0.893, respectively, which showed the higher accuracy of the ResNet. In addition, the region of attention of the model was derived by using the Grad-CAM algorithm, an eXplainable Artificial Intelligence (XAI) technique, to find out the location of the region that the deep learning model recognized as a defect in the fabric image. As a result, it was confirmed that the region recognized by the deep learning model as a defect in the fabric was actually defective even with the naked eyes. The results of this study are expected to reduce the time and cost incurred in the fabric production process by utilizing deep learning-based artificial intelligence in the defect detection of the textile industry.

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

Multi-scale modeling and experimental study on electrosprayed multicore microcapsule-based self-healing polymers

In this study, we promote a multi-scale modeling to predict the healing efficiencies (HEs) of incorporated polymers with self-healing microcapsules. The Python scripts were employed to generate three representative volume elements (RVEs) with randomly dispersed 5, 7.5, and 10% volume fraction (VF) of alginate microcapsules. Three VUSDFLD subroutines were codded and supplemented with ABAQUS/Explicit solver to obtain the maximum tensile stresses (Sut) of virgin, damaged, and healed samples followed by calculating HF of self-healing polymers. Based on the simulation results, more incorporation of self-healing microcapsules increased the tensile after impact HF, so that HFs were increased from 46.31% for RVEs containing 5% VF up to 65.41% and 84.84% for 7.5% and 10% VF, respectively. The presence of more self-healing microcapsules could improve the chance of rupturing more filled microcapsules with healing agents after crack propagation due to impact damages in the matrix. Thus, more damaged elements would be healed by spread healing agents. To evaluate the reliability of simulation results, the specimens containing electrosprayed multicore self-healing microcapsules were fabricated, and experimental HFs were calculated. The same trend was obtained for experimental results, as acquired in the simulation of RVEs. The error of healing efficiencies were only 6.82%, 2.81%, and 7.74 for incorporated specimens with 5, 7.5, and 10% VF of electrosprayed multicore microcapsules, respectively, indicating the accuracy of introduced multi-scale finite element modeling. The fabrication defects of experimental specimens can be the reason of simulation errors.

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.

LSTM based texture classification and defect detection in a fabric

Texture classification through deep learning is a science of detecting assumptions from various data through different tools of statistics, machine learning, signal processing and algorithm design. The ultimate aim of textile industries is to produce high quality and defect free fabric to the customers. Traditional methodologies involve manual inspection of every fabric produced which in turn seems to be tedious and time consuming. When Long Short Term Memory (LSTM) is applied to the defect detection and texture classification of a fabric the process leads to high efficiency. Industry can maintain the database which consists of pattern as well as the history of defects present in the fabric. The proposed deep learning technique on LSTM infers the details about the fabric through digital images. The defects in fabric are identified using LSTM method. The defects can be identified irrespective of complex patterns. The obtained images are converted to RGB images and compared with threshold levels for pattern recognition. The obtained factors from proposed technique is pattern of the fabric and location of the defects which include scratches, perforations etc. An unsupervised learning algorithm is proposed to classify the defect percentage present in the fabric and classifying the pattern in the fabric. Here multi-scale curvelet image decomposition and sub band decomposition is used to identify pattern and defects in the fabric. The defect detection involves two different phases. The first phase involves in analyzing defect free images. The second phase incorporated LSTM techniques to identify the defects by using logistic regression. The trained images are decomposed as blocks and the algorithm proposed has the capability to achieve defect detection and pattern recognition in a less computational time.

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%.

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.

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

The origin of the P-type conductivity for Cu and Ag-doped NiO: Density functional theory study

NiO, as a promising transparent p-type semiconductor, was intensively studied in experiment. Due to the difference of fabrication methods and defects concentration, it is difficult to make meaningful comparisons. In this work, the performance for Cu and Ag-doped NiO is fully evaluated by using the density functional theory method. Electronic structures show Cu and Ag substituting Ni (labeled as Cu Ni and Ag Ni ) are deep acceptors, and the ionization energy ε(0/-) for Cu Ni and Ag Ni are much higher than 0.20 eV. Our studies show the p-type conductivity for Cu and Ag-doped NiO mainly stems from the coexistent Ni vacancies (labeled V Ni ). The ionization energy ε(0/-) for Cu Ni (Ag Ni ) plus V Ni are 0.086 (0.012) eV. Under O-rich condition, the compounds M 2 O 2 and M 2 O (M = Cu and Ag) are promising dopants sources. We expect this work could promote the fundamental understanding of the p-type conductivity for nonstoichiometric NiO as well as the Cu and Ag-doped NiO. The data that supports the findings of this study are available from the corresponding author upon reasonable request.

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.

Fabric surface defect recognition based on multibranch residual network

Aiming at the subtle differences between fabric defects and complex texture background and the problem of small size defects, we propose a fabric surface defect recognition method based on multibranch residual network. First, the convolution kernel is decomposed and the multibranch shared feature extraction module is constructed using the residual connection to mine the feature information at different scales. At the same time, squeeze-and-excitation network (SE-Net) with a reduction ratio of 16 is added to the module to suppress the interference of complex texture background. Second, the channel attention mechanism is embedded in the residual block of the network backbone to realize the compensation for the lost feature information. Finally, the swish activation function is used to enhance the accuracy and robustness of the deep network, and transfer learning is used to further improve the network accuracy. The experimental results show that the proposed model is superior to the existing model in terms of average recognition accuracy. The proposed model has the highest recognition accuracy of 96.17% for eight defect categories, which proves the effectiveness of fabric surface defect class recognition.

Weft-knitted fabric defect classification based on a Swin transformer deformable convolutional network

With the vigorousness of the knitting industry, defect detection and classification of weft-knitted fabrics have become the research fields with extensive application value. However, convolution neural network models suffer from the limitation of convolutional operation, which makes them unable to capture the global features of fabric images abundantly. Although the transformer can compensate for this deficiency, it still has shortcomings such as poor small target recognition and unsatisfactory local information extraction ability. In order sufficiently to actualize the mutual support of relative advantages between the convolution neural network and the transformer, a Swin transformer deformable convolutional network integrated model is proposed in this paper. The Swin transformer deformable convolutional network utilizes the self-attention mechanism with global perception to establish dependencies comprehensively between long-range elements. Meanwhile, the deformable convolution is introduced according to the shaped characteristics of defects to extract local features effectively. Furthermore, a dataset containing 5474 images of weft-knitted fabrics was designed due to the less adequate databases. Experimental results on our weft-knitted fabric dataset and the Irish Longitudinal Study on Ageing (TILDA) database demonstrated that the proposed Swin transformer deformable convolutional network is superior to current state-of-the-art methods and has immense potential in fabric defect detection and classification.

INVESTIGATION OF ANTI-PILLING PROPERTIES OF DIFFERENT FABRICS APPLIED WITH POLYVINYLCAPROLACTAM

Pilling is one of the most important problems in the textile industry still not confidently solved. The problem is a kind of mechanically caused fabric defect consisting by a series of roughly spherical masses of entangled fibers called pills. Many studies have been carried out to define this problem in detail, determine the pilling intensity by different methods and improve the pilling grades of fabrics. One of the most beneficial methods to improve values is chemical finishing by applying specific polymers. In this study, a specific synthesized anti-pilling polymer was used for chemical finishing by padding method. A specific polymer based on polyvinylcaprolactam (PVCL) was synthesized and applied on the fabrics. The polymer has been characterized with FT-IR, NMR, DSC, elemental analysis devices also to optimize application-parameters. Especially pilling grades of blended fabrics of natural and synthetic staple fibres are often worser then other non blended fabrics, PVCL polymer was applied on a selection of different polyester cotton blends or polyester viscose blend, which have pilling values between 2-3. PVCL-Polymer applications were carried out by using these 7 different fabrics. As a result, approximately 1.5-2 pilling degree improvement was achieved. Anti-pilling polymers applied on the fabrics used to improve pilling values often decrease hydrophilicity values of the fabrics and worsen touch. However, the specific PVCL-polymer does not lead to a loss of smooth hand neighter to a loss of smooth fabric touch. On the contrary, it improves both hydrophilicity and smooth touch not causing fabric yellowing. PCVL is distinguished from other products used for pilling improvement in the textile industry.

Development and Prospect of Automatic Inspection System for Fabric Defects

Summarize the development of automatic inspection system for fabric defects. The main problems existing in traditional manual cloth inspection are pointed out. The development of automatic cloth inspection technology at home and abroad is reviewed. The classification and detection requirements of fabric defects are introduced. This paper probes into the functions and related technologies of automatic cloth inspection system, and looks forward to the prospect of automatic cloth inspection technology. It is considered that the use of automatic cloth inspection machine can improve labor productivity; Automatic cloth inspection machine is an important measure to upgrade the textile industry and get rid of labor-intensive industries, and it is an inevitable trend of future development.