Fabric Image Research Articles

A novel retrieval strategy for colored spun yarn fabrics based on hand-crafted features and support vector machine

The traditional retrieval methods of colored spun yarn fabrics are low in efficiency and accuracy. To solve this problem, this paper proposed a novel retrieval strategy for colored spun yarn fabrics based on hand-crafted features and support vector machine (SVM). First, the SVM classifier was built to automatically classify fabric images. Second, different texture and color features were extracted for solid-color fabrics and stylized fabrics based on hand-crafted feature extraction methods. Third, the retrieval strategy was formulated to realize image retrieval of colored spun yarn fabrics based on the output probability of the predicted sample category. The image database which contains over 6000 images was built to verify the proposed method. Experiments show that the mAP of the proposed method reaches 0.837 and the elapsed time is 0.171 s. Results indicate that the proposed method is feasible and effective, being superior to other methods for image retrieval of colored spun yarn fabrics. The proposed method can provide references for the production crew in the factory to shorten the production cycle and reduce manual labor.

ADDRESSING CLASS IMBALANCE FOR TRAINING A MULTI-TASK CLASSIFIER IN THE CONTEXT OF SILK HERITAGE

Abstract. Collecting knowledge in the form of databases consisting of images and descriptive texts that represent objects from past centuries is a fundamental part of preserving cultural heritage. In this context, images with known information about depicted artifacts can serve as a source of information for automated methods to complete existing collections. For instance, image classifiers can provide predictions for different object properties (tasks) to semantically enrich collections. A challenge in this context is to train such classifiers given the nature of existing data: Many images do not come along with a class label for all tasks (incomplete samples) and class distributions are commonly imbalanced. In this paper, these challenges are addressed by a multi-task training strategy for a classifier based on a convolutional neural network (SilkNet) that requires images with class labels for the tasks to be learned. The proposed approach can deal with incomplete training examples, while implicitly taking interdependencies between tasks into account. Extensions of the training approach with a focus on hard examples during training as well as the use of an auxiliary feature clustering are developed to counteract problems with class imbalance. Evaluation is conducted based on a dataset consisting of images of historical silk fabrics with labels for five tasks, i.e. silk properties. A comparison of different variants of the classifier shows that the extensions of the training approach significantly improve the classifier’s performance; the average F1-score is up to 5.0% larger, where the largest improvements occur with underrepresented classes of a task (up to +14.3%).

Automated Density Measurement of Weft Knitted Fabrics Using Backlight Imaging

This paper proposes a new density measurement algorithm to address the issues of poor applicability and inaccurate results associated with the automatic density measurement algorithm for weft-knitted fabrics. The algorithm involves collecting the transmitted light image of the knitted fabric, calculating the tilt angle using the skewing correction algorithm, and rotating the image to correct the weft skew present therein. The pre-rotated and post-rotated images are then projected vertically and horizontally in grayscale, and the obtained projection curves are used to represent the distribution of loops in vertical and horizontal rows. This study proposed a wave peak coordinate verification algorithm that calculates the coursewise densities and walewise densities of the knitted fabric. In experiments, the proposed density measurement method is found to exhibit an accuracy above 98% when compared with the manual mode.

The Role of Colour and Texture on Fabric Image Preference

The Role of Colour and Texture on Fabric Image Preference

Novel MobileNet based Multipath Convolutional Neural Network for defect detection in fabrics

Automatic fabric defect detection and classification is the most important process in the textile industry to ensure the fabric quality. In the existing systems, a learning based method is used for detecting defects in plain weave fabrics. In this paper, a novel MobileNet based Multipath Convolutional Neural Network (MMPCNN) architecture is proposed for detection and classification of simple and complex patterned fabric defects. In the proposed MMPCNN architecture, MobileNet model is used in the first path. In this, Gabor filter bank is used instead of conventional filters in the first convolution layer. A simple convolutional neural network architecture with Gray Level Co-occurrence Matrix (GLCM) features as an input is used in the second path of the MMPCNN architecture. Gabor filters are more useful for analyzing the texture with different orientations and scales. Each Gabor filter parameter has its own impact on analyzing the texture and extracting the information from the texture. Therefore, in this paper, the use of Gabor filter parameters in MMPCNN architecture is analyzed. The proposed model is experimented on the TILDA textile image database and it is able to achieve 100% accuracy with reduced trainable parameters for fabric defect detection and classification.

Alignment of 3D woven textile composites towards their ideal configurations

The objective of the present study is to create a parametric model of an ideal 3D woven textile from a computed tomography at mesoscale without prior knowledge of the fabric architecture. The model is constructed by identifying a minimal number of parameters from the tomography and includes further assumptions about the textile properties (e.g., equally-spaced vertical yarn columns). A novel registration procedure called Model-based Digital Image Correlation (MDIC) is introduced for mapping the whole textile image onto its own model. It leads to a realignment of the yarn columns after deforming the textile image, from which the model is updated. Model extraction and registration steps are iterated up to a stationary solution. The final result is a perfect textile geometry with straight and orthogonal yarn columns and its mapping onto the original tomography image. The proposed procedure is applied successfully to a 3D woven textile and a 3D-injected woven composite. This novel technique is useful as a pre-processing step to image segmentation procedures or to ease the visual inspection performed by operators in correcting the yarn paths and yarn column deformations occurring during composite material manufacturing. Additionally, this alignment procedure could be used to deform a numerical ideal model to better fit the geometry of a real weave.

ResNet50: Automated Fabric Defect Detection and Classification based on a Deep Learning Approach

"The demand for an intelligent computer-based system for visual inspection is on the rise in the textile business, especially among those who place a premium on textile quality. In this research, we present a fully automated AI-driven algorithm for defect detection in fabric, one that makes use of deep neural network models that have already been pre-trained. In order to train the networks, the fabric images go through a series of pre-processing steps where typical image processing techniques are applied. In order to train and categorize various fabric flaws, we use Deep Convolutional Neural Networks (DCNNs) and the pre-trained ResNeT network. The system obtains a best classification accuracy of 96.40% in simulations utilizing preexisting textile datasets. This model's detection and classification system can help human operators spot flaws in the fabric manufacturing process with this degree of precision."

FabricNET: A Microscopic Image Dataset of Woven Fabrics for Predicting Texture and Weaving Parameters through Machine Learning

This research presents an approach aimed at enhancing texture recognition and weaving parameter estimation in the textile industry to align with sustainability goals and improve product quality. By utilizing low-cost handheld microscopy and machine learning, this method offers the potential for more precise production outcomes. In this study, textile images were manually labeled for texture, specific mass, weft, and warp parameters, followed by the extraction of various texture features, resulting in a comprehensive dataset comprising four hundred and fifty-eight inputs and four outputs. Prominent machine learning algorithms, including XGBoost, RF, and MLP, were applied, resulting in noteworthy achievements. Specifically, XGBoost demonstrated an impressive texture classification accuracy of 0.987, while RF yielded the lowest MAE (5.121 g/cm) in specific mass prediction. Additionally, weft and warp estimations displayed superior accuracy compared to manual measurements. This research emphasizes the crucial role of AI in improving efficiency and sustainability within the textile industry, potentially reducing resource wastage, enhancing worker safety, and increasing productivity. These advancements hold the promise of significant positive environmental and social impacts, marking a substantial step forward in the industry’s pursuit of its objectives.

Research on fabric image registration and color difference detection based on cyclic elements

In order to realize online color difference detection of printed fabrics, a color difference detection method of printed fabrics based on image segmentation and image registration was proposed to detect the color difference of simple printed fabrics. The acquired standard fabric images are segmented using the combination of a Canny edge detector and uniform grid partitioning. The color information of each sub image is extracted based on the segmentation results and saved. We use the speeded-up robust features algorithm that incorporates the position information of the cyclic element where the feature points are located. The segmentation path of the standard image is registered onto the fabric image to be detected. The color information of each sub image of the image to be detected is extracted according to the registered segmentation path. The color difference value between the sub image of the image to be detected and the sub image of the standard sample is calculated using the CIEDE2000 color difference formula. The experimental results show that when fabric images with duplicate patterns are registered, the image registration methods mentioned in this paper significantly improve the accuracy of registration. The accuracy of the detection method in this paper on the printed fabric dataset can reach 95% compared to the manual calibration results.

Visual similarity simulation of slub denim based on image processing

The slub denim has various appearance styles that attract consumers due to the irregular distribution and long cycle of the slubs in the slub yarn. This characteristic of the slub yarn makes the slub denim proofing that relies on artificial visual contrast time-consuming with a long design cycle. A visual similarity simulation method was proposed for slub denim based on slub yarn images to solve this problem. At first, the yarn images were pre-processed by grey-level transformation, image threshold segmentation, and morphological operations to obtain the yarn core images. Secondly, according to the elastic change of yarn in fabric structure, the elliptic and sine curve models were established to treat the string to obtain the actual yarn shape in the fabric. Then, a light intensity curve function, which consists of a radial curve model and an interlacing point curve model, was established to simulate the light intensity distribution on the yarn surface. Finally, the cover relation of warp and weft yarns was controlled by Boolean matrix, and mean filtering was used to adjust the fuzzy denim fabric images. The experimental results show that the slub denims simulated by the method proposed in this article have a high visual similarity with the actual slub denims. Meanwhile, multiple parameters of the simulation model established in this article can be adjusted to enhance the adaptability of the model and the accuracy of the simulation results.

Online Fabric Defects Detection Using Convolutional Neural Networks with Two Frameworks

Due to the suboptimal efficiency, accuracy, and increasing costs of manual defect detection in the textile industry, online visual inspection for fabric defects has emerged as an essential and promising research area. However, challenges such as the lack of defective samples and issues with industrial deployment still persist. This paper presents a novel defect detection technique based on deep learning, which primarily comprises two frameworks. First, we design an improved generative adversarial network with an encoder–decoder architecture to address the paucity of requisite defective samples. We use defect-free samples as input to the generator, ensuring that the generated defect samples maintain a similar pattern. We mitigate the vanishing gradient problem using Wasserstein distance as the loss function. Second, we enhance the Single Shot MultiBox Detector network by introducing Inception modules and feature fusion to detect defects across different scales. The AdaBound optimizer is selected to update the model parameters. We compare the proposed approach with other methods on self-generated fabric data sets that are partially produced by our generative adversarial network model. An online defect detection system is proposed to capture fabric images and evaluation in a production environment. Experiments demonstrate the superior performance of the proposed approach, achieving 97.5% accuracy in real time, making it well-suited for application in the industry.

Recognition of fabric composition of clothing in an image in e-commerce using neural networks

Objectives. Development of new approach for recognizing the fabric composition of clothing in e-commerce images by using generative adversarial network(GAN) to generate synthetic images of clothing with known fabric composition, to be used to train the CNN to classify the fabric composition of real clothing images. Instead of a classic clothing image, a copy is generated with the material zoomed to fibers and fabric structure.Methods. The main methods to recognize the fabric composition of the clothing image in the e-commerce are the creation and annotation of a dataset for the neural network training, synthesis of the fabric of clothing, the choice of architecture and its modification, validation and testing, and interpretation of the results.Results. Experimental results with the constructed method show that it is effective for accurately recognizing the fabric composition of e-commerce clothing to be used to improve search and browsing on websites.Conclusion. In the course of the experiment, using a generative adversarial network, a data set of e-commerce products was synthesized and annotated, neural networks were built to recognize the composition of the fabric of clothing items. The results of the study showed that the new approach for recognizing the fabric of clothing provides higher accuracy in comparison with already known methods, in addition, the use of the attention model also gives good results to improve the metrics.

Collar recognition and matching of clothing style drawings based on complex networks

Seeking a fast and effective algorithm for describing and classifying clothing styles is currently a hot topic in the textile and clothing industry. The study first constructs a sample library of collar styles, preprocesses clothing images, and uses complex network models to describe and extract features; Implement clothing image classification based on support vector machines, and finally use image matching algorithms to match the image to be matched with the target object. It was indicated that the complex network model established by the research institute can effectively depict the characteristics of various collar styles, and the complex network model can effectively depict the characteristics of various collar styles. In 10 experiments, the overall average overall accuracy was 98%; Regarding different types of collars, the average accuracy of 10 experiments is above 96%, indicating that the collar classification accuracy based on support vector machine method is very high. The classifying results of the 10 categories obtained by the research method have little change and are relatively stable. For each category, the research method is higher than the other two methods. The results can indicate that the research method has effect and is more suitable for collar recognition and classification. Compared with traditional Hu invariant moments and HOG feature extraction algorithms, the research algorithm has stronger noise suppression ability, and using Euclidean distance as a similarity measure has great advantages.

In-situ monitoring of image texturing via random forests and clustering with applications to additive manufacturing

The amount of attention paid to in-situ monitoring in Additive Manufacturing (AM) has significantly increased over the last few years, paving the way to a paradigm shift for quality monitoring and control via big data analysis of signals, images, and videos. In-situ quality monitoring represents an opportunity for waste reduction and first-time-right production via inline detection of process flaws, which allows early identification of scraps and the possibility of correcting actions for first-time-right production. This article presents a solution for in-situ monitoring of images taken layerwise in material extrusion AM. Compared with the existing solutions, mainly focusing on monitoring the shape deviation observed at each layer with respect to the nominal shape, this article focuses on monitoring the internal surface texture with the aim of detecting over- and under-extrusion flaws. Inspired by an approach reported in the literature that was developed for textile image monitoring, we propose a solution for in-situ monitoring of textured surfaces which is based on combining Random Forests with clustering to automatically identify defective locations layerwise. A real case study based on Fused Filament Fabrication is used to compare the performance of the novel proposed solution with the original one and identify an appropriate direction for future research.

Collocated Clothing Synthesis with GANs Aided by Textual Information: A Multi-Modal Framework

Synthesizing realistic images of fashion items which are compatible with given clothing images, as well as conditioning on multiple modalities, brings novel and exciting applications together with enormous economic potential. In this work, we propose a multi-modal collocation framework based on generative adversarial network (GAN) for synthesizing compatible clothing images. Given an input clothing item that consists of an image and a text description, our model works on synthesizing a clothing image which is compatible with the input clothing, as well as being guided by a given text description from the target domain. Specifically, a generator aims to synthesize realistic and collocated clothing images relying on image- and text-based latent representations learned from the source domain. An auxiliary text representation from the target domain is added for supervising the generation results. In addition, a multi-discriminator framework is carried out to determine compatibility between the generated clothing images and the input clothing images, as well as visual-semantic matching between the generated clothing images and the targeted textual information. Extensive quantitative and qualitative results demonstrate that our model substantially outperforms state-of-the-art methods in terms of authenticity, diversity, and visual-semantic similarity between image and text.

Incorporating convolutions into transformers for textile fiber identification from fabric images

Simple, fast and effective fiber identification can help consumers purchase their desired apparel and help the industry conduct large-scale textile testing. This paper presents a transformer architecture incorporating convolutions to recognize fibers in textile surface images, which meets the above requirements. Firstly, a convolution operation is performed on textile images to pick up overlapping patches as tokens and the linear projections in transformer encoders are replaced by depth-wise separable convolutions to extract the fiber representations. Secondly, the multi-head cross-attention module enables each label embedding to be compared with features at each spatial location to locate and pool the corresponding fiber characteristics. Finally, a simplified asymmetric loss is introduced to further purify the extracted fiber features. Experiments demonstrate that the proposed approach provides a significant improvement in fiber identification accuracy over both state-of-the-art multi-label classification frameworks and fiber identification architectures.

Progressive mask‐oriented unsupervised fabric defect detection under background repair

AbstractDetection of defects is an essential quality control method in fabric production. Unsupervised deep learning‐based reconstruction algorithms have recently been deeply concerned owing to scarce fabric defect samples, high annotation cost, and deficient prior knowledge. Most unsupervised reconstruction models are prone to overfitting and poor generalisation performance, resulting in blurred images, residual defects, and uneven textures in the reconstruction results. On this account, an unsupervised fabric surface defect detection method using the Progressive Mask Repair Model (PMRM) has been developed. Specifically, PMRM with transformer architecture gathers detailed feature information. In order to pay closer attention to the textural properties of fabrics, the model incorporates structural similarity as a constraint in the training stage. In the detection stage, we designate the non‐defective area of the fabric image as the background and the defective area as the foreground. Next, a progressive mask is applied to repair the background of the defective area, which avoids defect false detection resulting from the poor reconstruction effect of the traditional reconstruction model in the non‐defective area. Finally, image processing methods such as image difference, frequency‐tuned salient detection, and threshold binarisation are used to segment the defects. Relative to the other six unsupervised defect detection methods, the proposed scheme increases the F1 score and intersection over union (IoU) by at least 9.34% and 8.49%, respectively. According to the earlier results, PMRM is effective and exhibits superiority.

An efficient network based on double constrained loss for fabric image retrieval

An efficient network based on double constrained loss for fabric image retrieval

A neural-network-based machine-learning model for fabric defect detection and classification using fused global features

ABSTRACT Detecting defects and classifying them is a primary requirement for textile industries. Manual methods of defect identification and classification happens in most cases for which the accuracy could not exceed more than 70%. A real time, fast and automated system for defect detection and classification is required for textile industries. This paper addresses this challenge and explores the use of different machine-learning models for the global features such as GLCM and Tamura extracted from checked pattern fabrics. In the training phase, machine-learning models produce an accuracy of > 90% and testing with new fabric images provides a maximum accuracy of 65%. To improve the accuracy of the classification system, an artificial neural network-based machine-learning model with features fusing has been proposed. Using the proposed approach, a testing accuracy of 80% is observed, and an accuracy of 96.1% is achieved in the training phase.

Self-supervised feature matched virtual try-on

Abstract Virtual try-on is a technology that enables users to preview the effect of wearing a target garment without wearing the actual garment. However, existing image-based virtual try-on methods often require additional human parsing or segmentation operations to generate intermediate representations required for garment deformation and texture fusion. These operations not only increase the computational complexity and memory consumption, but also limit the real-time and portability of virtual try-on. Additionally, inaccurate parsing results can lead to misleading final generated images. To overcome these challenges, we propose a self-supervised feature matched virtual try-on network, which can directly generate high-quality try-on results from human body images and target clothing images without any additional input. Specifically, we design an optical flow warp module, which focuses on the optical flow changes between the person image and the clothing image to achieve accurate clothing alignment and deformation. Furthermore, a feature refine warp module is designed to enhance the features of the extracted optical flow information and the original character segmentation and analysis operations, reducing the influence of background clutter features on the content, and ensuring that the wrinkles and deformation of the replacement clothes are close to the original clothes. The feature match module is developed to calculate the feature matching loss of the converted clothing and the generated results of the teacher network and the student network, and the corresponding knowledge is distilled and passed to the student network to assist in self-supervised training. We conduct experiments on the VITON dataset and show that our model can generate high quality and high resolution, and our proposed method outperforms the state-of-the-art virtual try-on methods both qualitatively and quantitatively.