Fabric Texture Research Articles

Assessment and Semantic Categorization of Fabric Visual Texture Preferences

Abstract The texture of a fabric can be perceived by the haptic and visual senses. Visual texture can be defined as a visual quality of a surface. It is an important phenomenon because it can be significant in many fields, such as textile design and e-commerce. At the same time, when we consider the semantics of the word, it is important to take into account that there are a variety of manifestations of fabrics (e.g., woven, knitted, etc.). The mechanism of visual texture perception of fabrics was investigated by measuring visual evaluation values. In our experiment, 12 textile samples with different surface textures are evaluated using thirty-four adjectives (Kansei words). For each visual texture, the adjectives with the highest mean ratings are extracted and analyzed. By using Hierarchical Cluster Analysis (HCA) and Principal Component Analysis (PCA), we aimed to discover and determine preferences for the visual texture of fabrics. The result is a semantic explanation of fabric texture with the adjectives proposed, which can help customers to evaluate the quality of the textile.

Local Characterisation and Detection of Woven Fabric Texture Based on a Sparse Dictionary

Abstract To achieve enhanced accuracy of fabric representation and defect detection, an innovative approach using a sparse dictionary with small patches was used for fabric texture characterisation. The effectiveness of the algorithm proposed was tested through comprehensive characterisation by studying eight weave patterns: plain, twill, weft satin, warp satin, basket, honeycomb, compound twill, and diamond twill and detecting fabric defects. Firstly, the main parameters such as dictionary size, patch size, and cardinality T were optimised, and then 40 defect-free fabric samples were characterised by the algorithm proposed. Subsequently, the impact of the weave pattern was investigated based on the representation result and texture structure. Finally, defective fabrics were detected. The algorithm proposed is an alternative simple and scalable method to characterise fabric texture and detect textile defects in a single step without extracting features or prior information.

Design of an environmentally friendly leather-like fabric based on thermoplastic polyurethane covered yarn

Abstract By means of knitting and weaving, the new yarn was woven into a new eco-friendly leatherette. A series of research methods and data are summarized through the optimization and improvement of the design process and the heat-setting treatment of the fabric after weaving, which will bring a breakthrough in the reform of the preparation, research and development of new environmentally-friendly materials and product application. The new environmentally-friendly imitation leather fabrics is superior to similar products and boasts advantages in product application, such fabric is comfortable, breathable, waterproof, windproof, folding-resistant, wear-resisting and biodegradable. The cost of its production is much lower than expensive leather products, in the meantime, the space for design and development in the aspect of fabric texture, pattern, and color can be expanded more compared with other leather and imitation leather products.

Pressure-dependent elastic anisotropy: A Bakken petroleum system case study

The complexity of the micropore fabric and organic texture in tight unconventional reservoirs often complicates their correlations with physical rock property parameters. Anisotropy, which is a common physical property of tight oil reservoirs, can affect directional deformation and permeability during the reservoir development and pressure depletion period. Thus, accurately measuring seismic anisotropy and its relationships with petrophysical properties can refine our understanding of vertical transverse isotropy rocks and ultimately improve fracturing design as well as production forecasting. We have developed a measurement technique of ultrasonic velocities (P and S) from multiple directions, that is, bedding-parallel, bedding-perpendicular, and at 45° to bedding under simulated in situ reservoir pressure. Following these measurements, we also correlate these findings to pressure-dependent porosity and permeability, in addition to geologic attributes and textural anisotropy. The samples that we investigate are tight carbonaceous siltstone and organic-rich mudrock cores originating from the Bakken petroleum system, which include Lodgepole, upper Bakken shale, middle Bakken, lower Bakken shale, and Three Forks. Depending on the rock fabric and mineral constituents, each formation exhibits distinctive anisotropic behavior in response to pressure changes. The results indicate that the elastic parameters and petrophysical properties are inversely related under pressure for all samples. We also find that P-wave anisotropy and SH-wave anisotropy parameters decrease gradually with increasing confining pressure. The anisotropic behavior can be related to volumetric concentration and directional connectivity of clay layers, kerogen veins, and subparallel microfractures.

Fabric defect detection based on completed local quartet patterns and majority decision algorithm

Visual inspection is a main stage of quality control process in many applications. Surface defect inspection plays an important role in fabric textile quality control systems. Each type of abnormality, that disturb the repetitive texture of fabric is called defect. The main aim of this paper is to propose a rotation-invariant fabric defect detection approach with high detection rate in comparison with well-known methods. In this paper, a new version of local binary pattern, that is called completed local quartet patterns, is proposed to extract fabric image local texture features. In the train step, first, the size of fabric repetitive patterns is computed using autocorrelation function on a defect-less fabric image, the completed local quartet patterns operator is applied to whole of this image and to a set of non-overlapping windows. The maximum value of non-similarity amount between feature vector extracted from the whole image and each window is considered as the defect-less threshold. Considering the threshold obtained in the training the fabric defects are detected. In order to evaluate performance, a benchmark dataset of patterned fabric images is used, that includes three groups of fabric patterns and six defect types. Experimental results indicated that the proposed method can detect defects with 97.66 percent detection rate. Simple process, rotation invariant, gray-scale invariant and high detection rate are main advantages of the proposed approach. Moreover, the proposed completed local quartet patterns descriptor operator is a general texture descriptor which can be used in many other computer vision applications to describe image contents.

Study on color representation model and computer simulation of colored spun fabrics based on image translation model

To improve the design and development efficiency of colored spun products, this paper puts forward a computer simulation scheme based on an image translation model, focusing on the ‘fancy’ coloration characteristics of colored spun fabrics. First, the Pix2PixHD image translation model was used to train and extract the fabric color texture information of colored spun fabrics, so as to construct a color texture characterization model; meanwhile, the texture fusion and color filling algorithm was constructed for the blending process of two-component dyed fibers, so as to realize the computer simulation of the two-component colored spun fabric ‘fancy’ color effect. On this basis, a texture and coloration characteristic evaluation index for colored spun fabric was established, which was applied to the quantitative analysis of computer simulation results for the first time. Meanwhile, the difference significance test was performed on the quantitative analysis results. It turned out that the computer simulation scheme established in this paper can effectively simulate the various ‘fancy’ color effects. Compared with the existing algorithms, it not only has obvious advantages in visual subjective feeling, but also has a notable improvement in objective and quantitative analysis data. The texture similarity and color similarity are increased by 5.78% and 19.17%, respectively, the peak signal-to-noise ratio and structural similarity index measure are increased by 15.72 db and 0.168, respectively. Therefore, the computer simulation scheme has ideal realistic and generalization characteristics.

Fabric Classification Using a Finger-Shaped Tactile Sensor via Robotic Sliding.

Tactile sensing endows the robots to perceive certain physical properties of the object in contact. Robots with tactile perception can classify textures by touching. Interestingly, textures of fine micro-geometry beyond the nominal resolution of the tactile sensors can also be identified through exploratory robotic movements like sliding. To study the problem of fine texture classification, we design a robotic sliding experiment using a finger-shaped multi-channel capacitive tactile sensor. A feature extraction process is presented to encode the acquired tactile signals (in the form of time series) into a low dimensional (≤7D) feature vector. The feature vector captures the frequency signature of a fabric texture such that fabrics can be classified directly. The experiment includes multiple combinations of sliding parameters, i.e., speed and pressure, to investigate the correlation between sliding parameters and the generated feature space. Results show that changing the contact pressure can greatly affect the significance of the extracted feature vectors. Instead, variation of sliding speed shows no apparent effects. In summary, this paper presents a study of texture classification on fabrics by training a simple k-NN classifier, using only one modality and one type of exploratory motion (sliding). The classification accuracy can reach up to 96%. The analysis of the feature space also implies a potential parametric representation of textures for tactile perception, which could be used for the adaption of motion to reach better classification performance.

Texture-Based Woven Image Classification using Fuzzy C-Means Algorithm

There are a lot of texture-based image data stored in the storage media Internet. Most of these data portray the cultural fabric texture results from a State. Because of the many variants of the existing texture, the data need to be easily accessible through the Internet. Moreover, the area of origin of weaving the surface is easily known. Therefore, it is necessary to develop a classification system based on woven image data. The texture of the image data stored in a database on the Internet can be grouped/clustered well, making it easy to access. This study examines a texture-based woven image classification using fuzzy c-means algorithm. This method combines extraction methods Gabor filter, fuzzy c-means algorithm and Euclid distance similarity measure. An experiment was done using the system as many as 60 woven images from Bali, NTT and Central Java areas, each taken as many as 25 images weaving. The test results stated that testing using the test images taken from the images in the database generates a 100% accuracy rate, and testing using test images taken from outside the database produces an accuracy rate of 94%.

INTEGRATION OF GEOLOGY AND PETROLEUM ENGINEERING ASPECTS FOR CARBONATES ROCK TYPING

Carbonate rocks are highly heterogeneous. That which leads to rock typing of carbonate rocks is noteasy to do even by integrating static and dynamic properties of rocks. In accordance with the defi nition ofrock types that are commonly used, rocks or parts of rocks that have been deposited in the same environmentand experienced similar diagenetic process have similar physical characteristics, such as grain orrock fabric texture, pore geometry and structure pores, then the characters that will be used as the basisfor determining rock types. The use of rock fabric has been performed by many previous researchers. Whilethe use of attributes in the rock pores typing is still limited and more emphasis on engineering purposes.The objective of this study is to integrate all three of these characteristics in the determination ofrock typing. Theories that have been established and related to fl uid fl ow in capillaries and porousmedia that will be used to characterize the pore geometry and pore structure. Furthermore, thecharacteristics of the geological evidence will be conducted using core description, petrographyand other data to obtain the relationship between aspects engineering and aspects geology inaccordance with concept or defi nition of rock type in question. In rock typing, permeability and porosity characterize the pore geometry and pore structure. This study proves that there is a strongrelationship between the characteristics of the detail geological and architecture pores. Thus,the resulting methodologies rock typing can be universal with respect to aspects of geology andpetroleum engineering.

CLO3D-Based 3D Virtual Fitting Technology of Down Jacket and Simulation Research on Dynamic Effect of Cloth

A 3D virtual fitting system for down jackets based on CLO3D is proposed and implemented in this paper. CLO3D system realizes virtual fitting, including three-dimensional body modeling, parametric punching, three-dimensional virtual sewing fitting, fabric texture attribute setting, and dynamic display, which realizes the design and realization of display. The clothing deformation algorithm based on human input posture is used to deform the clothing model, which presents the physical characteristics of virtual clothing more truly. At the same time, the image acquisition equipment is used to obtain the real-life image, and the clothing image transfer algorithm is used to superimpose the virtual clothes and the real-life image. The position of human joints is obtained by feature extraction technology, and the scaling ratio of the virtual clothes is calculated so that the virtual clothes are closely combined with the real-life image. Compared with similar virtual fitting systems in the industry, the information processing process of this system is more intelligent, the interaction is more natural, and the fitting effect is more realistic. We make every effort to make the virtual fitting system reduce the gap between virtual and reality and tend to be more realistic and popular.

Influence of process parameters on the characteristics of electrohydrodynamic-printed UV-curing conductive lines on the fabric

As a similar technology to the near-field static electrospinning, the emerging electrohydrodynamic (EHD) printing technology with digital printing process and compatibility of viscous particle-blended inks is one of the simplest methods of fabricating multifunctional electronic textiles. With increasing demands for textile-based conductive lines with controllable width and excellent electrical performance, it is of great importance to know the influence of key process parameters on the morphology and electrical properties of EHD-printed UV-curing conductive lines on the fabric. This work will systematically explore the effect of the EHD printing process parameters (i.e. applied voltage, direct-writing height, flow rate and moving velocity of the substrate) on the morphology and electrical performance of the EHD-printed textile-based conductive lines, especially focus on the diffusion and penetration of inks on the rough and porous fabric. The UV-curing nano-silver ink with low temperature and fast curing features was selected, and the line width and electrical resistance of printed lines under different process parameters were observed and measured. The results showed that, unlike previous results about EHD printing on smooth and impermeable substrates, the ink diffusion related to fabric textures had a greater effect on the fabric-based conductive line width than the applied voltage and direct-writing height in the case of a stable jet. Meanwhile, the relationship between the line width and the flow rate met the equation of , and the minimum volume on fabric per millimeter was 0.67 μl to form continuous line with low electrical resistance. Additionally, the higher substrate moving velocity resulted in a smaller line width, while it deteriorated the thickness uniformity and electrical property of printed lines. Generally, due to the effect of surface structure of the fabric on the spreading and penetrating behavior of inks, the flow rate and the substrate moving velocity are two significant parameters ensuring the electrical property of printed lines. It is believed that these findings will provide some guides for applying EHD printing technology into flexible electronics on the woven fabric.

Effects of Outer Shell Fabric Color, Smoke Contamination, and Washing on Heat Loss through Turnout Suit Systems

Firefighters frequently have to work in direct solar radiant heat. To reduce firefighter heat stress, the influence of turnout garment properties on heat gain from solar radiation must be understood. This research studied the effects of color, texture, washing, and contamination of outer shell fabrics on heat loss through firefighter turnout fabric materials in simulated solar exposures. It showed that solar radiation could be a major factor in heat loss through turnout suits. Solar radiation equivalent to a sunny day completely reversed heat exchange through the turnout fabric systems, converting a heat loss of about 240 W/m2 to a heat gain exceeding 100 W/m2. Solar radiation caused turnout fabric systems to dry out and this decreased the performance of turnout systems that incorporated bi-component moisture barriers. Most significantly, the color of the outer shell had a major influence on lowering turnout heat loss in solar exposures. Composites with a black-dyed outer shell absorbed more solar energy than composites with lighter colored shell materials. Soot and fire-ground contaminants present on turnout outer shell fabrics also reduced heat loss under solar exposure. The findings of this study answered long-standing questions about the importance of turnout fabric color on heat exchange with the environment. The results provide additional motivation for efficient turnout cleaning practices, not only to reduce potentially toxic exposure to smoke contaminants, but to reduce turnout-gear-related heat strain on firefighters.

Primena veštačke neuralne mreže u određivanju obraza tkanja

The weave pattern (texture) of woven fabric is considered to be an important factor of the design and production of high-quality fabric. Traditionally, the recognition of woven fabric has a lot of challenges due to its manual visual inspection. The approaches based on early machine learning algorithms directly depend on handcrafted features, which are time-consuming and occurs more errors. Hence, an automated system is needed for classification of woven fabric to improve productivity. Along with the rapid development of computer vision, the automatic and efficient methods for woven fabric classification are desperately needed. The prediction of fabric weave pattern Fabric is done by acquiring the high-quality images of the fabric. Then the acquired images are subjected to weave classification algorithm. The output of the processed image is used as an input to the Artificial Neural Network (ANN) which uses back propagation algorithm to calculate the weighted factors and generates the desired classification of weave patterns as an output. In this review paper discussed about the study on the various neural network that are used for prediction of fabric weave pattern.

An objective fabric pilling evaluation based on wavelet transform and Gabor filter

A new objective fabric pilling detection method is proposed for monochrome fabric without pattern. Firstly, through wavelet multi-resolution decomposition and reconstruction, remove the high-frequency noise such as fluff which is significantly different from the size of pills and low-frequency noise such as uneven illumination. After wavelet multi-resolution decomposition of fabric image, through analyzing the energy change law between each wavelet decomposition layer, and then the fabric is judged whether it is rough or fine texture. Then, according to the different color characteristics of fine texture and rough texture fabrics, the even symmetry two-dimensional Gabor filter with smoothing effect and the odd symmetry two-dimensional Gabor filter with edge extraction ability in different directions are selected for texture removal. Finally, fabric pilling parameters are extracted to realize fabric pilling grade evaluation. The main contribution of this method is: on the premise of removing the noise such as uneven illumination and fluff, on the basis of considering the different color change laws of fine texture and rough texture, using the directionality of fabric texture and the randomness of pills direction to effectively remove the texture noise, so as to improve the accuracy of fabric pilling grade evaluation.

Tactile-Based Fabric Defect Detection Using Convolutional Neural Network With Attention Mechanism

This paper proposes a fabric structure defect detection method based on the vision-based tactile sensor. The result will be robust by using the tactile sensor regardless of dyeing patterns which can influence the result if some other sensors are used, e.g., vision perception. It also reduces the influence of ambient light on defect detection. Therefore, the proposed method can be more robust and universal than conventional visual methods. A robotic arm equipped with the tactile sensors was used to automate and standardize the data collection process and construct fabric datasets. In addition, a convolutional neural network integrated with attention mechanism in the channel domain was developed to detect fabric types. The proposed network employed frequency domain filtering to remove or weaken the influence of normal fabric texture information to improve defect detection efficiency and accuracy. Finally several experiments were conducted to demonstrate the proposed method’s superiority to a visual defect detection method for detecting structural defects. In addition, the efficiency of the proposed method is evaluated. Experimental results show that the proposed method is feasible and efficient to meet the real-world detection requirements.

Control of climate, sea-level fluctuations and tectonics on the pervasive dolomitization and porosity evolution of the Oligo-Miocene Asmari Formation (Dezful Embayment, SW Iran)

The Asmari reservoir properties in various hydrocarbon fields across the Dezful Embayment (SW Iran) are modified by dolomitization. Petrographic and geochemical analyses of the dolomitized Asmari Formation units highlight their origin in the Bibi Hakimeh and Gachsaran oilfields. The petrographic studies revealed that dolomite in the Asmari Formation can be classified texturally (based on crystal sizes) into three main groups: (i) very fine crystalline (D1, <20 μm), (ii) fine to medium crystalline (D2, 20–150 μm) and (iii) coarse crystalline dolomites (D3, >150 μm). Petrography, fluid inclusions, stable isotopes (δ13C, δ18O), radiogenic isotopes (86Sr/88Sr) and major and trace elemental analyses were used to interpret the origin and paragenetic sequence of each dolomite group. Pervasive dolomitization prevails in the upper part of the Asmari Formation where very fine and medium crystalline dolomites with partially and fully fabric-retentive and fabric destructive textures, replaced micrite and allochems of the platform-top facies, respectively. The parent fluids of the very fine dolomites originated from contemporaneous Oligo-Miocene seawaters produced in a sabkha environment. The fine to medium dolomites (D2) most likely shared the same seawater origin and relate to refluxing, sabkha-derived fluids. The medium to coarse crystalline dolomite has more depleted oxygen isotopes than the former, very fine to fine crystalline, dolomites suggesting a burial dolomitization origin. The estimated high salinities (≈19 to 20 wt% NaCl) together with compatibility of oxygen and strontium isotope data with evaporative seawater values, suggest Oligo-Miocene seawater was the parent fluid for precipitation of coarse and cement phase of the medium crystalline dolomites. This study reveals that reactivated basement faults with associated fractures have probably played an important role in convecting and heating evaporative seawater along their planes. This heated seawater provided the required fluid for recrystallization of coarser matrix and cement phases of medium (D2) and coarse (D3) dolomites at depth. Therefore, the interaction of climate, sea-level changes, and tectonics played a critical role in formation and development of pervasive dolomitization in the Asmari Formation. Additionally, dissolution (partly as a consequence of dolomitization) was one of the key processes during early diagenesis in the formation of different types of porosity such as biomolds, vugs and intraparticles porosity. This study shows that the reservoir quality improves from finely crystalline dolomite towards samples dominated by coarsely crystalline dolomites.

Detergents containing cationic hydroxyethyl cellulose: Benefits on dark garments leveraging a consumer relevant wash method

AbstractThe industrial standard methods to evaluate color care of detergents leverage technical fabrics and use known dye standards from A.I.S.E. (International Association for Soaps, Detergents and Maintenance Products). This has some limitations: (1) it is not always following the latest fashion trends; (2) overall color fading of a garment is due to both dye bleeding out of the fabric as well as friction during the wash leading to fabric texture changes. The latter depends on parameters such as fabric type and surface area that could be better assessed on real garments. To overcome the above limitations, we have designed a new protocol considering the incidence of garment types, fiber and dye chemistry. Leveraging this protocol, we assessed the effect of the presence of a cationic hydroxyethyl cellulose in a commercial detergent formulation on dark fabrics/garments. Our results indicate that the commercial detergent formulation with cationic hydroxyethyl cellulose delivers dark/black color benefit.

Automatic Unsupervised Fabric Defect Detection Based on Self-Feature Comparison

Due to the huge demand for textile production in China, fabric defect detection is particularly attractive. At present, an increasing number of supervised deep-learning methods are being applied in surface defect detection. However, the annotation of datasets in industrial settings often depends on professional inspectors. Moreover, the methods based on supervised learning require a lot of annotation, which consumes a great deal of time and costs. In this paper, an approach based on self-feature comparison (SFC) was employed that accurately located and segmented fabric texture images to find anomalies with unsupervised learning. The SFC architecture contained the self-feature reconstruction module and the self-feature distillation. Accurate fiber anomaly location and segmentation were generated based on these two modules. Compared with the traditional methods that operate in image space, the comparison of feature space can better locate the anomalies of fiber texture surfaces. Evaluations were performed on the three publicly available databases. The results indicated that our method performed well compared with other methods, and had excellent defect detection ability in the collected textile images. In addition, the visual results showed that our results can be used as a pixel-level candidate label.

Fabric‐Assisted MXene/Silicone Nanocomposite‐Based Triboelectric Nanogenerators for Self‐Powered Sensors and Wearable Electronics

AbstractSurface modification of triboelectric negative layers is an essential factor for boosting the output performance of triboelectric nanogenerators (TENGs). Herein, a novel scalable surface modification method is introduced using a fabric‐assisted micropatterning technique on a highly negative MXene/silicone nanocomposite surface (charge generating) with MXene layer (charge trapping) for self‐powered sensors and wearable electronics. The microstructured surface is fabricated directly from a fabric template requiring no surface‐active agent, high‐pressure equipment, or high vacuum. To boost the proposed double‐side‐contact TENG (DSC‐TENG) output performance, different parameters of the fabric textures are tested and optimized for the roughened microstructures, namely the MXene layer and relative humidity. Under optimal conditions, the fabricated DSC‐TENG improves the voltage and peak current density by factors of 9.8 and 20, respectively, regarding flat silicone. It exhibits a maximum peak power density of 55.47 W m−2 at load resistance of 0.18 MΩ, and a corresponding decrease in resistance by 75% using MXene content of 3 mg cm−2. Also, DSC‐TENG‐based smart home control of electrical appliances, theft protection, self‐powered electronic devices, password authentication, and human motion monitoring via smartphone for the IoT are demonstrated. The proposed method can be implemented for different types of polymers, thereby enabling the large‐scale fabrication of high‐performance TENGs in industrial applications.

Fabric Defect Classification based on Deep Hashing Learning

Classifying categories of fabric defects can greatly help to identify the source of causing fabric defects in the textile manufacturing process. Most existing artificial intelligence based methods focus on identifying and locating defective regions and do not analyze the categories of the defects. On the other hand, as current fabric defect detection methods depend on handcrafted features, they can only handle fabric with specific patterns or textures. In this paper, we propose a novel model which can learn high-level representation from the automatic observations of the input images that can recognize the categories of the defects for various fabric patterns and textures, instead of only locating defects on specific patterns. Experimental results show that the proposed method is superior to the state-of-the-art deep hash methods in terms of fabric defect classification.