Automatic classification of woven fabric structure based on texture feature and PNN

In today’s textile industry, the classification of woven fabrics is usually manual which requires considerable human efforts and a long time. With the rapid development of computer vision, the automatic and efficient methods for woven fabric classification are desperately needed. This paper proposes an automatic and real-time classification method to analyze three woven fabrics: plain, twill and satin weave. The methodology involves two approaches to extract texture features, that is, gray-level co-occurrence matrix (GLCM) and Gabor wavelet. Then, principal component analysis (PCA) is utilized to deal with the texture feature vectors to gain minimize redundancy and maximize principal component feature vectors. Finally, in the classification phase, probabilistic neural network (PNN) is applied to classify three basic woven fabrics. With strong realtime, fault-tolerance and non-linear classification capability, PNN can be a promising tool for classification of woven fabrics. The experimental results show that PNN classifier with faster training speed can classify woven fabrics accurately and efficiently. Besides, compared with GLCM method and Gabor wavelet method, the fusion of the two feature vectors obtains the best classification result (95 %).     

Research on digital intelligent recognition method of the weave pattern of fabric based on the redundant information

Digital intelligent recognition for the weave pattern of fabric plays an important role to improve automation and artificial intelligence in textile production process. In order to improve the data processing efficiency and minimize the negative influence such as human error in the conventional methods, a rapid, automatic and accurate method for the surface structure analysis and the fabric weave pattern recognition is proposed. First of all, an imaging system was designed to obtain the double-faced images of fabric samples, and then the captured images were treated by projection algorithm in both warp and weft directions to generate a grid net which splits the image into massive nodes. In the following step, the nodes were preliminary classified based on the intensity of the node’s quadrilateral boundary and at the same time, the color of the nodes was calculated by using the color clustering method. To improve the accuracy of node classification, the types and color information of the adjacent nodes, together with double-faced image information, were utilized for error correction. At last, the node information acquired was encoded and expressed digitally by a basic matrix, two one-dimension matrices (row and column) and a color mapping table. Following the procedure above, the digital model of the weave pattern of the sample fabric is established. Experiments have been conducted and show the performance of the proposed method.     

The effect of twist liveliness on the woven fabric distortion

This paper deals with the grey fabric deformation during relaxation. It investigates the effect of twist direction and twist liveliness on the 2/2 twill weave woven fabric distortion, during relaxation This experimental work shows that twist liveliness increases the natural tendency of the twill weave woven fabric to skew. In addition when the twist direction of the warp and weft is opposite to each other the bias curling occurs too.     

Dyeing and fastness properties of vat dyes on meta-aramid woven fabric

meta-Aramid fibers have an excellent heat-resistant property and are widely used for protective clothings such as fire-fighter suit and racing suit. They can also be used as military uniforms such as flight suit or army uniform. Vat dyes are specially used for military uniforms owing to outstanding fastness properties, earth tone shade, and near infrared (NIR) camouflage. In this study, 100 % meta-aramid woven fabric was dyed with three vat dyes using an exhaustion method and their dyeing and fastness properties were investigated. Color yields of the vat dyes on the meta-aramid fabric were found to be dependent upon dyeing temperature, liquor ratio, amount of reducing agent, and amount of salt. Dyeing behavior of the vat dye on the meta-aramid fiber was very similar to that on cellulose fibers. It was found that the meta-aramid fabric dyed with 1% owf of C.I. Vat Green 1 satisfied the tolerance of the reflectance spectrum of forest green color in the Korean military standard. Thermal stability and mechanical property of the meta-aramid fabric did not significantly affected by the vat dyeing process. Wash and perspiration fastness was generally good but rubbing and light fastness was unsatisfied.     

Effects of sample dimensions on pull-out properties of woven fabric structures

The aim of this study was to understand the effects of fabric sample dimensions on pull-out properties of fabric weaves. Polyester woven fabrics were used to conduct the pull-out tests. A yarn pull-out fixture was developed and data generated from this research. Yarn pull-out forces depend on sample dimensions, fabric density, fabric weave, and number of pulled ends in the fabric. Results showed that multiple and single yarn pull-out forces of long samples were higher than those of short samples, and the multiple yarn pull-out force was higher than that of the single yarn pull-out force, and dense fabric has high pull-out force. Plain fabric weave showed high single and multiple pull-out forces compared to ribs and satin fabric weaves. The regression model could be used in this study as a viable and reliable tool. This research could be valuable for development of multifunctional fabrics in technical textile applications.     

Development of moisture transition ability on porous complex structured woven fabric with convergence of pattern,porosity, and plasma technology

A porous complex structured woven fabric was manufactured to maximize the moisture transition ability of the prepared fabric by increasing the absorptive property of the fabric through surface modification using plasma, which is a dry modification method. Porous single and complex structured woven fabrics were produced by applying pattern, porosity, and plasma technology, including fabric patterning based on the sheath/core complex structure, the formation of porosity by removing the weft thread or warp thread, and hydrophilic surface treatment using plasma and the improvement in water absorption of different fabrics by the porous and plasma treatment was investigated. Therefore, two different types of fabrics were prepared. One is the porous single structured FAB-SINGLE fabric which was taken out in the direction of the Polyester (PET) warp thread of a general single structure to form a porous. Another is FAB-COMPLEX fabrics that the water-soluble polylactic acid (PLA) yarns with a 1.7 to 2.0 times longer absorption distance than that of PET yarns were inserted into the weft threads, and the PLA yarns were dissolved in a solvent to form the porous complex fabric. And then the physical properties and water absorption of the two types of fabric were compared after the plasma treatment. The results showed that when the FAB-SINGLE fabric, which has porosity induced by the removal of the warp threads in a certain gap, was plasma treated for 5 min, the contact angle was decreased to the extent that a measurement of the contact angle was impossible, whereas the fabric that had not undergone a plasma treatment had a contact angle of 123.6 o. The contact angle of the FABCOMPLEX with porosity caused by the dissolution of the PLA yarns was reduced from 76.8 o to 0 o after 3 minutes of a lowtemperature plasma treatment, indicating that the hydrophilic property was increased. In addition, the water absorption measurements showed that the absorption height was increased from 2.3 cm of the fabric sample that had not been treated with plasma to the highest absorption height of 8.3 cm, suggesting that the water absorption also increased with the improvements in moisture transition ability by the plasma treatment. The physical tensile strength of the fabrics was not changed by the plasma treatment, despite the changes on the fabric surface, suggesting that the combination of double complex structures and the plasma treatment helped improve the water absorption.     

Formability analysis of worsted woven fabrics considering fabric direction

Over years predicting fabric behaviour during garment manufacturing process was considered by researchers in order to reduce manufacturing problems and achieve high quality products. Fabric formability which is affected by bending and tensile behaviour through the application of small loads is a property which can predict fabric performance precisely. However, this property changes regarding fabric direction and is not constant. In this study, fabric formability is examined for worsted woven fabrics in a more detailed way by evaluating this property in various fabric directions. It was concluded that fabric formability could be expressed as a sinusoidal function of sample orientation towards warp direction. Moreover, studying several weave structures with different weft densities reveals that the less the firmness of fabric construction the more the value of fabric formability which indicates the better adaption of fabric to the exerted deformation.     

Modelling tearing behavior of durable press finished woven fabric

Tearing strength is one of the most important and critical properties related to durable press finished cotton woven fabric. In the past, modelling of tearing strength of cotton woven fabrics was based on untreated cotton woven fabric but not in durable pressed finished fabric. In this paper, a mathematical model was established to demonstrate the tearing strength mechanism of durable press finished cotton woven fabrics by dimensional analysis based on yarn diameter, cover factor, Young’s modulus and fabric elongation. The proposed model agreed well with experimental results and the proposed model can be used for optimizing durable press finishing process of cotton woven fabric.     

Effect of heat-treatment on stretch of poly(trimethylene terephthalate) woven fabric

The properties of a woven fabric made of poly(trimethylene terephthalate) (PTT) were investigated. The PTT fabric of draw textured yarn (DTY) showed excellent stretch as good as a fabric containing spandex. However, the unique stretch of the PTT fabric reduced dramatically by simple heat-treatment even at as low as 80 °C. To understand the phenomenon, the crimp rigidity of the DTY was observed by SEM. It was found that the drastic reduction of stretch was caused by irreversible uncrimping of PTT DTY after heat-treatment. Conclusively, it is of importance to optimize the texturing conditions for PTT DTY to make the crimp more stable.     

Evaluation of anti-stabbing performance of fabric layers woven with various hybrid yarns under different fabric conditions

Various types of special fibers are used for human body protection, mostly in the form of fiber-reinforced composites. These composites are made of special fibers and matrix resin; however, they are often not comfortable for the wearer due to the lack of flexibility and air permeability. This study focuses on an evaluation of human body protective performance against stabbing for various special fibers such as aramid, basalt, and steel fibers, being utilized in cotton hybrid forms. These hybrid forms are designed to improve wearer comfort, while maintaining adequate anti-stab resistance. Specimens prepared with various fabric densities are tested in terms of anti-stabbing performance, according to the NIJ standard. In addition, we investigate the influence of factors such as fiber type, the number of fabric layers, fabric weight, and fabric density on anti-stabbing performance. Results show that the penetration depth of the impactor, which punctures and protrudes through the specimens, decreases with the number of layers, the thickness, and the mass of the armor sample; however, these factors have different relationships according to the material type. Consequently an objective evaluation of anti-stabbing performance is needed. We suggest an anti-stabbing index that can be applied as a criterion to evaluate the antistabbing performance of various specimens woven with special fibers under different fabric conditions. Using the new index, anti-stabbing performances of various specimens can be compared and raw material and fabric conditions that offer the most efficient anti-stabbing performance can be selected.     

Properties of stick-slip stage of yarn pull-out in para-aramid woven fabric

The aim of this study was to understand stick-slip properties of para-aramid woven fabrics. For this reason, pullout test was conducted on para-aramid Kevlar®29 and Kevlar®129 woven fabrics. The stick-slip and accumulative retraction force regions were defined based on the force-displacement curve. It was found that the stick-slip force and accumulative retraction force depended on fabric density and the number of pulled ends in the fabric. Stick-slip force in the multiple yarn pull-out test was higher than those of the single yarn pull-out test. Stick-slip force in single and multiple yarn pull-out tests in the dense K29 fabric were higher than those of the loose K129 fabric. In addition, long fabric samples showed high stick-slip force compared to that of the short fabric samples. On the other hand, the amount of stick-slip force was related to the number of interlacement points in the fabric whereas the amount of accumulative retraction force was related to fabric structural response.     

Analysis of woven fabric structure using image analysis and artificial intelligence

An integrated hardware and software system has been developed that can automate the analysis process of various woven fabric structures. Although the analysis of woven structure is one of the most important steps in the fabric design and quality control process, it has been dependent only on human skills with primitive devices. In this study, a dedicated hardware system has been developed to obtain an ultra-high resolution fabric images. Then a series of image analysis technique was applied to locate the intersecting regions of warps and wefts on those images. Finally, an artificial neural network was formed to determine the woven structure of fabric based on the two shape parameters extracted from those regions.     

全球棉花及棉纺织品和服装零售的趋势

1全球棉价走势 全球棉价的长期平均值为每磅72美分。自1995年WTO农业协议生效以来，全球棉价持续走低，2001年跌至每磅42美分左右，是29年以来的最低水平（见图1）。仅在2003年11月棉价才在短期内突破76美分（见图2）。随后又急剧下跌，于2004年12月跌至每磅43美分。棉价上涨的主要原因是棉价触底后。全球棉花库存持续减少，供需失衡造成的。近期棉价（2005年11月17日）维持在每磅56美分左右。     

The effect of weft density on the skewness of the twill weave woven fabric

This experimental study investigates the effect of weft density on the skewness of the twill weave woven fabrics. A total of 12 rolls of woven fabrics - 2/2, 3/3 and 4/4 - twill weave, with 20, 22, 24 and 26 weft densities were produced and their skewness due to relaxation was measured. The measured values show that as the weft density increases from 20 to 26, the skewness decreases from 2.4, 2.9, 3.6 to 1, 1.1 and 1.15 respectively. This decrease supports the idea that the increase in weft density drops the effect of the weave type on skewness. In fact, this experimental work reveals that increase in weft density lowers the free spaces between the floats, shortens the float length and raises the shearing rigidity of the fabric and as a result the ability of the warp floats’ in-plane lever to move and skew is lowered.     

Applying image analysis to automatic inspection of fabric density for woven fabrics

The gray line-profile method is introduced to find fabric density. Some patterned fabrics like stripe design as well as solid fabrics of basic weave structures are used to verify the efficiency and accuracy of the method. The approach is compared with Fourier transform method. Although the gray line-profile method is concise, it shows good results in both solid and patterned fabrics. In addition, it does not require a pre-processing or filtering technique in space or frequency domain to enhance the image suitable for the analysis. However, the approach is slightly influenced by the filter size for finding the local minimums of profile graph.     

Screen printed silver patterns on functionalised aramid fabric

In this work, a simple and low cost method based on screen printing is presented to synthesize a conductive silver pattern on aramid fabric. The aramid fiber was treated with (3-mercaptopropyl)-trimethoxysilane to introduce a tail mercapto group promoting the ordered binding of silver nanoparticles. SEM and AFM images indicated a uniform distribution of silver nanoparticles on fiber surface. FTIR and XRD patterns confirmed the silver layer on the fibers. Furthermore, the electrical property of conductive fiber was characterized by conductive AFM and a digital multimeter, the surface resistance of conductive fabric was as low as 0.20 Ω/cm. And single fiber tensile test indicated that the mild treating process has no significant influence on the mechanical properties of the fiber.     

A new approach for numerical identification of bending behavior of plain woven fabric

There is a variety of approaches for investigating bending behavior of woven fabrics. Some of them are based on fabric deformation with one edge fixed; the others are based on measurement of force, moment or energy producing bending deformation. In all methods, bending properties is acquired after testing prepared fabric samples. Therefore, in this work an attempt is made by a mechanical model and a novel calculation technique to determine bending characteristics of the plain woven fabrics before sample production. Theoretical data including bending length, bending rigidity and bending modulus were directly determined for supposed fabric samples with a given yarn count and yarn density using Peirce’s structural model for plain woven fabric and a especial code written in Maple12. Besides, fabric samples with the defined characteristics were woven on a Sulzer-Ruti weaving machine. Then, these fabrics were tested for bending behavior using Shirley bending tester. Comparison showed good agreement between predicted and measured bending characteristics of the fabrics. However, theoretical bending rigidities of the samples were more than experimental values.     

Warp and weft directional tensile properties of multistitched woven fabric E-glass/polyester nano composites

The aim of this study was to understand the warp and weft directional tensile properties of the developed two dimensional (2D) multistitched multilayer E-glass/polyester woven nano composites. It was found that the warp and weft directional specific tensile strength and modulus of unstitched structure were higher than those of the machine stitched and machine stitched/nano structures due to stitching caused filament breakages. When the nano silica material in the unstitched E-glass/polyester composite structure increased, the warp and weft directional specific tensile strength and the modulus of the unstitched/nano structures increased. The failure of warp and weft directional 2D unstitched and unstitched/nano woven E-glass/polyester composite structures had a complete delamination in their cross-sections. But, the failure of warp and weft directional 2D stitched and stitched/nano woven E-glass/polyester composite structures had a local delamination in their cross-sections and the failure was confined at a narrow area. The warp and weft directional specific damaged areas of unstitched structure were higher than those of the stitched and stitched/nano structures. Also, the warp and weft directional specific damaged areas of machine stitched structure were slightly higher than those of the machine stitched/nano structure. It could be concluded that the addition of nano silica to the stitched structures improved to their damage resistance.     

Characterizations of stick-slip stage of yarn pull-out in dry and softening treated polyester plain woven fabric

The aim of this study was to understand the stick-slip properties of polyester plain woven fabric. For this reason, pull-out test was conducted on dry and softening treated polyester woven fabrics. It was found that stick-slip force and accumulative retraction force depend on the number of pulled ends in the fabric, fabric sample dimensions and softening treatments. Stick-slip forces of polyester fabric in the multiple yarn pull-out test were higher than those of the single yarn pull-out test. Stick-slip force in single and multiple yarn pull-out tests in the dry polyester plain fabric were generally higher than those of the softening treated polyester plain fabric. On the other hand, the amount of stick-slip force was related to the number of interlacement points in the fabric whereas the amount of accumulative retraction force was related to fabric structural response.