Fabric Image Research Articles

Anchor selection based deep learning two stage fabric defect localization

<span lang="EN-US">Localizing and classifying fabric defects is a crucial step in the quality control process used in the production of textiles. Recently, fabric defect classification and detection have made use of deep learning approaches based on anchor selection. But due to in effectiveness in anchor selection, the computational overhead and localization error are higher in these solutions. As a solution to this problem, this work proposes a two-stage improvised anchor selection deep learning technique. In first stage, quaternion fourier transform frequency domain analysis along with super pixel segmentation is done over the fabric image to select probable defect regions. In the second stage deep learning based regression along with super pixel segment comparison is done over the probable defect regions localize and categorize the defect. Due to effectiveness in selection of probable defect regions and categorization of regions, the defect localization accuracy is increased at a comparative low computational overhead in the proposed two stage improvise anchor selection deep learning technique. Testing against the irish longitudinal study on ageing (TILDA) fabric defect detection dataset, the proposed solution is found to provide 1.2% higher fabric defect localization accuracy at a 3% lower computation overhead compared to most recent existing works.</span>

Development of a method for evaluating fabric surface contamination by particulate matter using fluorescent particles

Functional clothing products are being developed to prevent the attachment of particulate matter (PM). However, currently, PM-blocking performance of such products cannot be quantitatively evaluated. This study developed a method for measuring fabric surface contamination by PM by contaminating textile fabrics with PM and using an image processing technique. Silicate particles exhibiting fluorescence characteristics with a suitable size distribution were selected as PM simulants. The fabric surface contamination was calculated by contaminating textile fabrics under wind speed and PM concentration conditions similar to actual atmospheric environment. The number of pixels was obtained in the black and white binary images converted from the images of the textile fabrics captured under an ultraviolet (UV) light source. Experiments were performed using finished nylon fabric with PM-blocking performance and raw nylon fabric without PM-blocking performance. Comparison of the fabric surface contamination shows that it is possible to evaluate the PM-blocking performance of fabrics.

Study evaluating the curling property of weft knitted fabrics based on pixel analysis

Curling is a common phenomenon observed in knitted fabrics. Curling poses many problems for fabric and clothing production, especially for digital devices, where it can affect the production quality and efficiency, while there is still no accurate method for evaluating it. This study established an evaluation method for the curling properties of knitted fabrics based on pixel statistics. Weft knitted fabric samples were created using a fabric cutter and a piece of paper was placed underneath the fabric. The fabric sample curls, whereas the paper represents a non-curling state. Subsequently, a scanner was used to scan the projections of the circular samples and paper to obtain digital images. The pixel amounts of the curled fabric and paper digital images were measured using the Photoshop 2020 software. The ratio between the fabric and paper projection pixels can be calculated by subtracting from 100% and converting the curling area ratio to the curling distance ratio. This can be used to represent the curling properties of knitted fabrics. The error between the theoretical and measured values is <0.1%, indicating a high level of accuracy. Ten knitted fabrics were validated for analysis. The sample with the maximum deviation between the left, middle, and right positions was 5.9%, whereas that with the minimum deviation was 0.3%. Subsequently, the fabrics were retested on the 7th and 14th days to assess reproducibility. The maximum deviation for each fabric on the 1st, 7th, and 14th days was 4.1%, and the minimum deviation was 0%. Therefore, it can be concluded that the method described in this study can accurately quantify the curling properties of knitted fabrics.

Design and application of an intelligent generation model for fashion clothing images based on improved generative adversarial networks

Design and application of an intelligent generation model for fashion clothing images based on improved generative adversarial networks

Design and 3D simulation of weft-knitted jacquard plush fabrics

Abstract Weft-knitted jacquard plush fabrics are widely used and have a wide variety of varieties, but the design and production process is complicated, time-consuming, and labor-intensive. To reduce the time and cost of fabric sampling and production, a method for designing and simulating these fabrics is proposed based on an analysis of their structural characteristics. Following the design principles of weft-knitted jacquard plush fabrics, mathematical models for pattern design and structural design were established sequentially, leading to the generation of a mathematical model for the knitting diagram. Arrays for raw material editing and threading editing were created to set various parameters. Second, loop models were established based on plush loop shapes, including a forming loop model, a U-shaped loop model, a Henkel plush loop model, a “8”-shaped plush loop model, and a O-shaped plush loop model. Finally, the effects of lighting and number of segments were investigated in THREE.Tube Geometry on the simulation’s effectiveness and speed. By comparing actual fabric images with simulation images, the feasibility of the design and simulation method was verified. This resulted in a computer-aided design process for weft-knitted jacquard plush fabrics, providing an effective method for their design and simulation. The proposed method holds significant theoretical and practical values.

Limonene biosolvent-based non-aqueous dyeing medium for salt-free and alkali-free rhamnolipid (RL) biosurfactant reverse micellar dyeing of cotton fabric with reactive dyes

The feasibility of using different forms of limonene biosolvents as dyeing medium in rhamnolipid (RL) biosurfactant-based reverse micellar dyeing system for cotton fabrics is investigated, with different dyeing profiles. Experimental results reveal that limonene-dyed fabrics can achieve generally higher colour yield than water-dyed fabrics while samples dyed by one-step dyeing method could obtain higher colour yield, but poorer relative unlevelness index (RUI) values when compared with samples dyed by two-step method. The CIE L*a*b* value and reflectance of water-dyed and limonene-dyed samples were examined. The pH value of aqueous and non-aqueous dye liquor was measured. SEM images of limonene-dyed cotton fabrics and TEM images of reverse micelle morphology were evaluated. Washing and crocking fastness of the dyed samples were also assessed. The resulting evidence validate that limonene is feasible for reverse micellar reactive dyeing of cotton fabric with the use of RL biosurfactant and it can be one of the alternative solvents, making the dyeing process more natural, more biodegradable and environmentally more sustainable.

Fabric Defect Detection Using Transfer Learning

Transfer learning in fabric defect detection involves utilizing pre-trained deep learning models on a large dataset, typically from a different domain, and fine-tuning them on a smaller dataset that is specific to fabric defects. By leveraging transfer learning, the limitations of limited annotated data for fabric defect detection can be overcome by utilizing the knowledge gained from a more extensive and diverse dataset. The pre-trained model's learned features are adjusted to recognize specific fabric defect patterns, resulting in more accurate and efficient defect detection. This approach reduces the reliance on a massive labelled dataset for training, which is particularly beneficial in industrial applications where obtaining a vast amount of annotated fabric defect images may be challenging. Ultimately, transfer learning enhances the model's ability to generalize and detect fabric defects with higher precision, thereby contributing to improved quality control in textile manufacturing processes.

Reconstructing hyperspectral images of textiles from a single RGB image utilizing the multihead self-attention mechanism

Hyperspectral images possess abundant information and play a pivotal role in enhancing the accuracy of color difference detection in textiles. However, traditional hyperspectral imaging methods necessitate costly equipment and intricate operational procedures. A novel deep learning model based on a multihead attention mechanism was proposed in this article to facilitate the extensive application of hyperspectral imaging technology in textile quality inspection. This model enabled the reconstruction of the hyperspectral information of plain weave textiles from a single RGB image. In this model, encoder-decoder architecture and pyramid pooling convolutional operations were employed to integrate multiscale features of plain weave cotton-linen textiles. This could capture details and contextual information in textile images more precisely, enhancing the accuracy of hyperspectral image reconstruction. Simultaneously, an attention mechanism was introduced to increase the model’s receptive field and improve its focus on key regions in the input image and feature maps. This resulted in a reduced weighting of redundant information during network learning, leading to an improved feature extraction capability of the network. Through these methods, successful reconstructions of plain weave textiles hyperspectral information from a single RGB image was achieved. Quantitative and qualitative tests were conducted on two datasets, namely, the NTIRE 2020 dataset and a self-made textile dataset, to evaluate the performance of the proposed method. The approach proposed in this article exhibited promising results on both datasets. Specifically, the reconstructed textile hyperspectral images achieved a root mean square error of 0.0344, a peak signal-to-noise ratio of 29.945, a spectral angle mapper of 3.753, and a structural similarity index measure of 0.955 on the textile dataset. In the reconstructed hyperspectral colorimetric experiment, the maximum value of average color difference was 2.641. These results demonstrate that the method can meet the requirements for textile color measurement applications.

Optimized Gabor Filter Banks and Autoencoder Models for Enhanced Knitted Fabric Defect Detection

There is a high need for an automated system to detect fabric defects, as the current manual methods used in the garment industries in Nepal are unreliable and costly. Previous research has focused on specific fabric defects rather than overall fabric defects efficiently. This research employs two autoencoder models to identify different defects across different types of knitted fabrics, utilizing two datasets: the SFDG dataset and a custom dataset prepared from Butwal’s garment industries. The models benefit from a carefully designed Gabor filter bank to examine fabric compositions. This filter bank is fine-tuned by modifying parameters, wavelength, and orientation to detect varieties of defects in knitted fabrics. These models get feature representations from the Gabor filter bank’s outputs and help the system adapt to different types of defect patterns, making defect detection more reliable and accurate. The nearest neighbor density estimator finds possible defects and marks on the fabric images. The model's effectiveness and strength are shown by validating it on different types of knitted fabrics, including plain and patterned fabrics, using evaluation metrices like cTPR and ROC AUC. The first model achieves a cTPR of 0.879 and an AUC score of 0.947, while the second model achieves a cTPR of 0.899 and an AUC score of 0.958.

A deformation procedure using position-based dynamics to optimize the geometric model of woven fabrics

Generating realistic three-dimensional (3D) yarn-level models for fabrics has become a significant research topic due to the complexity of fabric structures and the requirement for high-quality models with no interpenetration between yarns. The generation process of idealized geometric models leads to inaccurate descriptions of yarn contact, specifically the interpenetrations and spurious voids between yarns. A geometric optimization procedure was developed to address the defects in the idealized models, involving a series of geometry-driven operations, such as the shrinking and expansion of yarn volume and the straightening of the yarn centerline, to obtain accurate and consistent fabric models for Finite Element Analysis. During the geometric optimization, a method for yarn deformation based on position-based dynamics (PBD) was applied to simulate the real deformation during yarn interweaving, ensuring no interpenetrations between yarns while preserving yarn volume. The accuracy of the model is validated by comparison with the real fabric images. Although the methods involved in the procedure are all geometric, their deformation results have realistic physical effects. In addition, the procedure can be applied to various woven fabric structures.

Wearable damaged clothing fabric image recognition system based on image restoration algorithm

With the improvement of people's living standards and the rapid growth of national technological strength, wearable devices have gradually integrated into people's daily lives, making them convenient for people's work and lives. Traditional fabric detection methods often rely on manual visual inspection, which has low efficiency and accuracy that does not meet the requirements. In view of this, the research has innovatively integrated GAN, CNN, field Programmable gate array (FPGA), multi-stage image recovery algorithm based on graph neural network, for high frequency and low frequency fusion, and combined it with wearable devices to develop a new wearable fabric recovery and recognition system. The results showed that in the COCO dataset, after 250 iterations, the WFR2S algorithm achieved a damage identification accuracy of 95.5 %, a mean absolute error of 0.011, a real-time processing speed of 30 fps, and a resource consumption of 2.4 W. These data demonstrate the significant performance advantages of WFR2S in image recovery and damage detection. The newly developed image recovery algorithm improves the accuracy, availability and stability of damage recognition in garment fabrics. This study not only has theoretical value but also has broad application prospects in practical application. The aim is to contribute to the intelligent development of the garment industry.

Antimicrobial coating of biologically synthesized silver nanoparticles on surgical fabric and surgical blade to prevent nosocomial infections

In this study, biologically synthesized AgNPs were found to be effective against six hospital prevalent bacterial species (Pseudomonas aeruginosa, Escherichia coli, Acinetobacter baumannii, Klebsiella pneumoniae, Methicillin-resistant Staphylococcus aureus and Enterococcus faecalis). AgNPs were deposited on the fabric and surgical blades using layer-by-layer and electrochemical deposition methods, respectively. The coated objects were characterized using scanning electron microscopy, X-ray diffraction and Fourier transform infrared spectroscopy and energy dispersive X-ray. Coated fabric samples and blades when tested against six above mentioned bacterial species were found to be effective for all of them. Antibiofilm activity of AgNPs coated blade and fabric was tested against P. aeruginosa and SEM images of post-treated fabrics and blades showed clear bacterial cell distortion and inhibition. Furthermore, washing durability test revealed that AgNPs were strongly attached to the surface of fabric even after 20 cycles of hospital laundering. This unlocks the way to several technologically relevant applications of AgNPs coated surfaces to reduce the risks of nosocomial infections and as a proof of concept; we demonstrated efficient antibacterial properties of AgNPs coated cotton fabric and surgical blades.

Conditional image-to-image translation generative adversarial network (cGAN) for fabric defect data augmentation

The availability of comprehensive datasets is a crucial challenge for developing artificial intelligence (AI) models in various applications and fields. The lack of large and diverse public fabric defect datasets forms a major obstacle to properly and accurately developing and training AI models for detecting and classifying fabric defects in real-life applications. Models trained on limited datasets struggle to identify underrepresented defects, reducing their practicality. To address these issues, this study suggests using a conditional generative adversarial network (cGAN) for fabric defect data augmentation. The proposed image-to-image translator GAN features a conditional U-Net generator and a 6-layered PatchGAN discriminator. The conditional U-Network (U-Net) generator can produce highly realistic synthetic defective samples and offers the ability to control various characteristics of the generated samples by taking two input images: a segmented defect mask and a clean fabric image. The segmented defect mask provides information about various aspects of the defects to be added to the clean fabric sample, including their type, shape, size, and location. By augmenting the training dataset with diverse and realistic synthetic samples, the AI models can learn to identify a broader range of defects more accurately. This technique helps overcome the limitations of small or unvaried datasets, leading to improved defect detection accuracy and generalizability. Moreover, this proposed augmentation method can find applications in other challenging fields, such as generating synthetic samples for medical imaging datasets related to brain and lung tumors.

Plaid Fabric Image Retrieval Based on Wavelet Transform and SIFT Features

Abstract This study presents a method for plaid fabric image retrieval that combines wavelet and SIFT features to address the challenges of accuracy and efficiency in fabric retrieval due to diverse fabric types. The process starts with cropping plaid fabric images and applying histogram equalization to improve brightness and contrast. Texture is enhanced using the Sobel operator, and the Haar wavelet transform extracts image high-frequency components in various directions. Wavelet features are then derived through histogram statistics. The SIFT algorithm is utilized to describe local features by capturing key points and directional information. A codebook aggregates these features from the fabric database, and VLAD encoding generates a vector for the image features, which is further reduced to 256 dimensions via PCA. A similarity-weighted fusion method combines the wavelet and SIFT features, achieving an mAP of 0.67 and an average retrieval time of 1.1 seconds per image. This method significantly enhances plaid fabric retrieval, aiding in fabric design and production.

Research on Clothing Image Retrieval Combining Topology Features with Color Texture Features

Research on Clothing Image Retrieval Combining Topology Features with Color Texture Features

Colour difference detection algorithm for warp‐knitted fabric based on image colour appearance model

AbstractDetecting colour differences in warp‐knitting fabric is essential to ensure its quality. Machine vision algorithms are commonly used for automatic colour difference detection. However, the current algorithm directly extracts RGB (red, green, blue) colour stimulus values from the image without considering the image's colour attributes, leading to a significant error in colour difference detection. To solve this issue, a colour appearance model is introduced into the field of colour difference detection for warp‐knitted fabric. Initially, a colour appearance model based on CAM16 is established, and the critical parameters are calculated to obtain the colour appearance attribute of the fabric. The colour difference calculation formula is then constructed in the uniform colour space of CAM16‐UCS. A template selection algorithm based on principal component analysis was designed to select warp‐knitted cloth images with standard colours. Subsequently, a cloth colour difference detection algorithm was developed using the cloth colour profile model. The performance of the colour difference formula based on the colour profile model was evaluated using the PF/3 method. To compare the CIELab, CMC(2:1), and CIEDE2000 colour difference formulas, standardised residual sum of squares was used. The results indicated that the colour difference formula based on the colour‐appearance model is about 5.32% different from the visual colour difference perceived by the human eye. However, it can perform as well as the CMC(2:1) colour difference formula, which is widely used in the textile industry.

A fully automatic adjacent key-points localization framework for minimal repeated pattern detection in printed fabric images

The printed fabric images usually contain a large number of minimal repeated patterns (MRPs), which are of great value for the color separation, plate-making and other related applications in the textile industry. The key-points localization is a well established and effective manual method to detect the MRPs by finding a number of identical key-points. Recently, computer-aided automated key-points localization techniques have shown great potential and attracted considerable interest. Nevertheless, most of the available subtle and ad-hoc strategies are poorly generalized to complex situations due to a lack of systematic formulation. In this study, we endeavor to automate and theorize this manual detection method, aiming to enhance its accuracy, robustness, and efficiency. Specifically, we delineate related concepts and systematically formalize the minimal repeated pattern (MRP) detection problem, thereby establishing a theoretical groundwork for the manual method’s viability. Then, we present an effective and robust adjacent key-points localization (AKL) framework by automating manual detection method of MRP in printed fabric images. This framework is further developed into a comprehensive automated image retrieval system, complete with detailed implementation techniques. We also create a printed fabric dataset named PFI-10K containing approximately 10,000 images to test corresponding methods. The experimental results demonstrate the effectiveness and robustness of the proposed AKL framework.

Innovative Application of Traditional Chinese Opera Elements in Modern Dramatic Costume Design

In the field of drama, especially in clothing design, designers are actively exploring how to combine traditional opera elements with modern drama to create clothing images that are both rich in traditional charm and in line with contemporary audience aesthetics. This innovation not only inherits traditional culture, but also challenges and extends modern aesthetics. Traditional Chinese opera elements, as an important component of Chinese culture, provide rich inspiration and materials for modern drama costume design with their unique symbolic meanings and aesthetic characteristics. The article conducts research on the innovative application of traditional Chinese opera elements in modern theatrical costume design, in order to enrich theatrical images and provide new paths and possibilities for the dissemination and inheritance of traditional culture in contemporary society.

Convolutional neural network application for supply–demand matching in Zhuang ethnic clothing image classification

This study aims to design a classification technique suitable for Zhuang ethnic clothing images by integrating the concept of supply–demand matching and convolutional neural networks. Firstly, addressing the complex structure and unique visual style of Zhuang ethnic clothing, this study proposes an image resolution model based on supply–demand matching and convolutional networks. By integrating visual style and label constraints, this model accurately extracts local features. Secondly, the model’s effectiveness and resolution performance are analyzed through various performance metrics in experiments. The results indicate a significant improvement in detection accuracy at different annotation points. The model outperforms other comparative methods in pixel accuracy (90.5%), average precision (83.7%), average recall (80.1%), and average F1 score (81.2%). Next, this study introduces a clothing image classification algorithm based on key points and channel attention. Through key point detection and channel attention mechanisms, image features are optimized, enabling accurate classification and attribute prediction of Zhuang ethnic clothing. Experimental results demonstrate a notable enhancement in category classification and attribute prediction, with classification accuracy and recall exceeding 90% in top-k tasks, showcasing outstanding performance. In conclusion, this study provides innovative approaches and effective solutions for deep learning classification of Zhuang ethnic clothing images.

Fabric image recolorization by fuzzy pretrained neural network

Fabric image recolorization by fuzzy pretrained neural network