Search

The application of content-based image retrieval method aims at retrieving similar fabric images and obtaining the existing process parameters to guide production. The process of sample analysis, trial weaving, and proofing can be eliminated in sample imitation production to give full play to the advantages of historical production experience and improve the core competitiveness of enterprises. By investigating and analyzing the applications of content-based image retrieval method technology in fabric retrieval, this article provides a detailed classification and summary of the existing fabric retrieval methods using content-based image retrieval method from six aspects: image preprocessing, feature extraction, similarity measurement, retrieval strategy, dataset construction, and evaluation metrics in the common framework of content-based image retrieval method. The advantages and disadvantages of different methods are analyzed and compared. Finally, the urgent problems and future research directions of fabric image retrieval are discussed, providing ideas for scholars to further study the retrieval methods. Taking fabric as the medium, this article combs the industrial application research and development process of content-based image retrieval method technology, which is helpful to understand the application examples of computer technology and provide research ideas for the application of different computer technologies in the textile industry.

Compared with solid-colored fabrics, the textures in yarn-dyed fabric images are more complex, making the task of defect detection more challenging. To achieve efficient detection, this study proposes an automatic detection framework for dyed fabric defects. The proposed framework consists of a hardware system and a detection algorithm. For efficient and high-quality acquisition of fabric images, an image acquisition assembly equipped with three sets of light sources and a mirror was developed. In addition, a defect detection algorithm based on Fourier convolution and a convolutional autoencoder is proposed. Abandoning the common way of adding noise, this paper proposes to generate image pairs for training using a random masking method in the training phase. In the autoencoder, some traditional convolutional layers are replaced with Fourier convolutional layers. Ablation experiments verify the effectiveness of the mask generation method and Fourier convolution. Compared with other defect detection methods, the proposed method achieves the best performance, which verifies the superiority of the method. The maximum detection speed of the developed system can reach 41 meters per minute, which can meet real-time requirements.

Fabric shape retention is a crucial property that impacts the durability and usability of fabric and which needs a convenient and accurate evaluation method. In the previous research, the automated crease recovery testing method was used to obtain fabric crease recovery information and evaluate the property of shape retention. Based on the previous research, an orthogonal test method was adopted to investigate the effect of different test parameters on the stability of shape retention detection in this paper. First, three factors, that of sample size, pressure, and pressure time, and three different levels of each factor were determined by the L9(34) orthogonal test table. Next, the fabric shape retention indexes were detected by nine different test schemes, and the comprehensive score of shape retention index standard deviation was obtained as the evaluation criterion of the orthogonal test results. Finally, the optimal test scheme was determined by visual analysis and variance analysis. The results show that the sample size has a certain effect on the stability of shape retention indexes, while the pressure time and the pressure have no significant influence. The optimal test scheme is that the sample size is 30 cm × 30 cm, the pressure time is 60 s, and the pressure is 40 N. The test result measured by the optimal test parameters reveals excellent stability when the vertex angle standard deviation is 2.0°, the height standard deviation is 0.06 cm, and the shape retention area standard deviation is 0.16 cm2. This paper provides an experimental basis for improving the accuracy of fabric shape retention evaluation method.

For sample reproduction, texture and color are both significant when the consumer has no specific or individual demands or cannot describe the requirements clearly. In this paper, an effective method based on aggregated convolutional descriptors and approximate nearest neighbors search was proposed to combine the texture and color feature for wool fabric retrieval. Aggregated convolutional descriptors from different layers were combined to characterize the wool fabric image. The approximate nearest neighbors search method Annoy was adopted for similarity measurement to balance the trade-off between the search performance and the elapsed time. A wool fabric image database containing 82,073 images was built to demonstrate the efficacy of the proposed method. Different feature extraction and similarity measurement methods were compared with the proposed method. Experimental results indicate that the proposed method can combine the texture and color feature, being effective and superior for image retrieval of wool fabric. The proposed scheme can provide references for the worker in the factory, saving a great deal of labor and material resources.

Due to the potential value in many areas, such as e-commerce and inventory management, fabric image retrieval, which is a special case of content-based image retrieval, has recently become a research hotspot. As a major category of textile fabrics, patterned fabrics have a diverse and complex appearance, making the retrieval task more challenging. To address this situation, this paper proposes a novel approach for patterned fabric based on the non-subsampled contourlet transform (NSCT) feature descriptor and relevance feedback technique. To integrate the color information into the NSCT feature descriptor, we extract the feature of patterned fabric images in HSV color space. An outlier rejection-based parametric relevance feedback algorithm is employed to adjust the similarity matrix to improve the retrieval results. The experimental results not only show the effectiveness of the proposed approach but also demonstrate that it can significantly improve the performance of the retrieval system compared to other state-of-the-art algorithms.

Yarn evenness and hairiness are the appearance characteristics of yarn, which affect textile processing and product quality. To evaluate yarn appearance economically and effectively, an image-processing method is proposed in this paper to analyze yarn appearance on a blackboard. Firstly, an image of a yarn blackboard is captured by the scanner. Then, the yarn core and hairy fibers are segmented from the captured image with image-processing algorithms. The coefficients of variation of the yarn diameter ( CVbd) and the hairiness index ( M) are respectively calculated based on the information about the yarn core and hairy fibers in the image. Finally, the results of the proposed method are compared with those from the Uster Tester. The experimental results demonstrate that yarn appearance can be objectively evaluated using yarn blackboard images. The test results of different yarn blackboards made from the same yarn are stable and consistent. The correlation coefficient between the proposed method and the Uster Tester is 0.98, which proves that the H value can be accurately predicted by the hairiness prediction model. A hairiness prediction model built by the M value is also proven to be accurate when used to predict the corresponding value of the Uster Tester. Compared with the existing yarn evenness and hairiness test methods, the proposed method is more economical and practical.

Computer color matching can improve production efficiency and reduce costs in color spun. However, in practice the computer color matching success rate for pre-colored fiber blends has not been good, leading to customers being unsatisfied with the accuracy of the color matching results. Aiming to improve the accuracy, a hybrid of least squares and grid search method has been proposed for spectrophotometric color matching of pre-colored fiber blend based on the improved Kubelka–Munk (K-M) double-constant theory. Two-primary, three-primary, four-primary, and five-primary pre-colored cotton fiber blends were prepared as standard samples to evaluate the color matching accuracy of the proposed method. Compared with the least squares method and the grid search method, the proposed method achieved better color matching effects and greatly shortened the calculation time, respectively. For 42 pre-colored fiber blends, the average color difference between the predicted results obtained by the proposed method, least squares method, and grid search method and the spectrophotometer measurements were respectively 0.29, 0.53, and 0.36 CIE2000 units. The experimental results indicated that the proposed method could predict the formulation of standard samples quickly and effectively, and that it was superior to other methods in providing satisfactory color matching results for the enterprises.

The fabric of colored spun yarn has ever-changing appearances and styles with different fancy yarns. The fabric image is commonly designed by the designer using the software, which needs complex user interactions and difficult image segmentation. In this paper, a modified color transfer method was proposed to generate the fabric appearance of colored spun yarn. Given the color card as the target image, the style fabric image was matched as the reference image based on the dominant luminance. After transferring the two images to lαβ color space, Wavelet transform and luminance sampling were utilized to filter the redundant high-frequency information and select the representative pixels, respectively. Then, the chromatic channels were transferred based on the best matched luminance and the neighborhood relation. Finally, the image after color transfer was reconstructed by wavelet reconstruction. The proposed reference image matching maintained the result to be the ground truth. For the samples selected, the combined methods based on wavelet transform and luminance sampling improved the efficiency and performance of the proposed scheme. Experiments were conducted on different fabrics with different colors and styles. Experiments demonstrated the validity and superiority of the proposed method, which can provide referential assistance for the designer and save considerable amounts of labor.

Weaving enterprises are faced with problems of small batches and many varieties, which leads to difficulties in manual scheduling during the production process, resulting in more delays in delivery. Therefore, an automatic scheduling method for the weaving process is proposed in this paper. Firstly, a weaving production scheduling model is established based on the conditions and requirements during actual production. By introducing flexible model constraints, the applicability of the model has been greatly expanded. Then, an improved ant colony algorithm is proposed to solve the model. To address the problem of the traditional ant colony algorithm that the optimizing process usually traps into local optimum, the proposed algorithm adopts an iterative threshold and the maximum and minimum ant colony system. In addition, the initial path pheromone distribution is formed according to the urgency of the order to balance each objective. Finally, the simulation experiments confirm that the proposed method achieves superior performance compared with manual scheduling and other automatic methods. The proposed method shows a certain guiding significance for weaving scheduling in practice.

Objective fabric smoothness appearance evaluation plays an important role in the textile and apparel industry. In most previous studies, objective fabric smoothness appearance evaluation is defined as a general pattern classification problem. However, the labels in this problem exhibit a natural ordering. Nominal classification ignores the ordinal information, which may cause overfitting in model training. In addition, for the existence of subjective errors, measurement errors, manual errors, etc., the labels in the data might be noisy, which has been rarely discussed previously. This paper proposes an ordinal classification framework based on label noise estimation (OCF-LNE) to objectively evaluate the fabric smoothness appearance degree, which takes the ordinal information and noise of the label in the training data into consideration. The OCF-LNE uses the basic classifier in pre-training as a label noise estimator, and uses the estimated label noise to adjust the labels in further training. The adjusted labels can introduce the ordinal constrain implicitly and reduce the negative impact of label noise in model training. Within a 10 × 10 nested cross-validation, the proposed OCF-LNE achieves 82.86%, 94.29%, and 100% average accuracies under errors of 0, 0.5, and 1 degree, respectively. Experiments on different fabric image features and basic classification models verify the effectiveness of the OCF-LNE. In addition, the proposed method outperforms the state-of-the-art methods for fabric smoothness evaluation and ordinal classification. Promisingly, the OCF-LNE can provide novel ideas for image-based fabric smoothness evaluation.

The layout of colored yarns in yarn-dyed fabrics is a significant part of designing and production in the textile industry, which is still analyzed manually at present. Existing methods based on image processing have some limitations in accuracy and stability. Therefore, an automatic method is proposed to recognize the layout of colored yarns and some other basic fabric structure parameters: the fabric density and weave pattern. First, a large dataset with fabric structure parameters is constructed. The fabric images are captured by a wireless portable device. Then the yarns and floats are accurately located using a novel multi-task and multi-scale convolutional neural network. Finally, a density-based color clustering algorithm is proposed to recognize the layout of colored yarns. The results of extensive experiments show that the proposed method can automatically identify the basic structure parameters with high effectiveness and robustness.

Fabric shape retention is one of the most important attributes of fabrics that can influence the quality of the end use product. In this paper, we present a computer vision-based method to analyze the sequential images, which records the dynamic change of a deformed fabric, to model the recovery process, and extract the features of the recovery curve to characterize the shape retention after the deformation. Image processing and the perceptual hash algorithm were used to convert the measurements of a fabric shape variable at different times into Hamming distance points. The recovery function of the fabric shape was formed by fitting the Hamming distance points with exponential function, and three new shape retention indexes, that is, the average slope, the abscissa of the inflation point, and the radius of curvature at the inflation point, were defined based on the recovery function. The experiment showed that the shape retention of 12 fabric samples after deformation could be effectively distinguished by the new indexes. This paper also discussed the relationships between the new indexes and the transitional measurements indicating the fabric shape retention.

Deep learning-based defect inspection has gained popularity in recent years. The dataset requirements for the supervised learning-based method are currently high, but the types of defects are numerous and difficult to gather. This work proposes a local image reconstruction-based unsupervised fabric defect segmentation method to address this problem. Cyclic structures make up the normal portion of the fabric image, whereas the defects are anomalous and minor in comparison. As a result, the defect will be recreated as a normal texture utilizing the information from its surrounding areas, and the defect information will be preserved in the residual image. By masking the same area with various shapes, different reconstruction outcomes and residual images can be achieved. The signal of the defect will be amplified and the noise will be decreased due to the random distribution when the generated residual pictures are fused, which can effectively identify the defect from the noise and lower the false detection rate. On the denim fabric dataset, the proposed unsupervised method can achieve high precision fabric defect segmentation, with the defect detection rate and detection precision reaching at least 85% and 89%, respectively, with high efficiency (approximately 60 m/min inspection speed), outperforming other fabric defect segmentation methods.

Color is difficult to distinguish by human vision and is described by keywords, resulting in low efficiency of wool fabric retrieval in factories at present. To obtain the process sheets of existing products and reduce the work of color measurement in sample analysis, this paper proposes an effective method based on dominant colors (DCs) and color moments (CMs) for wool fabric image retrieval. Firstly, the image was scaled to reduce computational time. Then, the hue, saturation, value color space was divided into 128 parts by the fast color quantization algorithm to extract the DCs of the image. Meanwhile, the CMs based on image partition were calculated in CIE L* a* b* color space to describe the spatial color information. Subsequently, different similarity measure methods were carried out based on the DC feature and CM feature. Finally, experiments were conducted on a wool fabric image database with 20,000 images for parameter optimization and verification. The average precision and recall were up to 87% and 44%, respectively. Experimental results show that the proposed scheme can retrieve images with the same or similar colors quickly and effectively and it outperformed other methods, providing referential assistance for the factory worker when retrieving wool fabrics.

Fabric smoothness appearance assessment plays an important role in the textile and apparel industry. To evaluate fabric smoothness objectively, different methods have been proposed based on computer vision technology. To further improve the performance and promote the application of the assessment methods, this paper reports a hybrid computer vision system for objective assessment of fabric smoothness appearance with an ensemble classifier to integrate the advantages of the different image feature sets, which are extracted based on different image processing technologies. The image acquisition environment is established in this system with the selection of illumination parameters—intensity, position angle and altitudinal angle—by a designed strategy. The main steps of the strategy include determination of priority by information gain analysis and parameter selection by classifier performance analysis. The support vector machine classifiers trained by each feature sets are grouped into an ensemble by a self-adapting weighted voting method and the redundant feature sets are eliminated based on the weights of the feature sets. The final result shows evaluation accuracies with 82.86% under 0-degree error, 97.14% under 0.5-degree error and 100% under 1-degree error, which outperforms the other methods in the same environment and verifies the applicability of the proposed system.

As a special case in content-based image retrieval, fabric retrieval has high potential application value in many fields. However, fabric retrieval has higher requirements for results, which makes it difficult for common retrieval methods to be directly applied to fabric retrieval. It is also a challenging issue with several obstacles: variety and complexity of fabric appearance, and high requirements for retrieval accuracy. To address this issue, this paper presents a novel method for fabric image retrieval based on soft similarity and pairwise learning. First, a soft similarity between two fabric images is defined to describe their relationship. Then, a convolutional neural network with compact structure and cross-domain connections is designed to learn the fabric image representation. Finally, listwise learning is introduced to train the convolutional neural network model and hash function. The generated hash codes are used to index the fabric image. The experiments are conducted on a wool fabric dataset. The experimental results show that the newly proposed method has a greater improvement than our previous work.

Factories must proof different colors on fabric in order to verify the feasibility of the color scheme. This proofing process is time-consuming and laborious. To recolor printed fabric images, a novel image recoloring method was proposed in this paper. This method can provide convenience for printed fabric designers and can be used to simulate printed fabric proofing. The relative total variation model was implemented to remove the fabric image texture and noise. Next, in the CIE1976 L* a* b* color space, the mean-shift clustering algorithm was utilized to segment the reference image and the target image to obtain the separated color regions. Then, the color regions of the reference image and the target image were matched based on the salient map and the values of the L* a* b* channels. Finally, local color transfer was performed between the matched color regions based on the matching results. Experiments were conducted on 100 printed fabrics with different color schemes. Results indicated that the proposed method can transfer the color appearance of the reference printed fabric image to the target printed fabric image and realize printed fabric image recoloring.

With huge and ever-growing products in the factory, image retrieval can help the worker retrieve the same, or similar, existing products rapidly and accurately to guide production. In this paper, an effective method based on Fourier transform and local binary pattern is proposed to improve the retrieval efficiency of wool fabric. After capturing the fabric image, histogram equalization was implemented on the value of the Hue, Saturation, Value (HSV) mode to enhance the contrast. Subsequently, Fourier transform together with local binary pattern operator were performed to obtain the frequency spectrum and the local binary pattern, respectively. Each frequency spectrum was divided into 22 rings with the same width, and the standard deviation of the frequencies in each ring was calculated as a Fourier feature. Distinct output values of each local binary pattern were counted and normalized as local binary pattern features. Finally, Euclidean distance was adopted to measure the similarity based on the Fourier feature and local binary pattern feature. Twenty thousand wool fabric images were captured to demonstrate the efficacy of the proposed method. Experimental results indicate that the framework is effective and superior for image retrieval of wool fabric, providing referential assistance for the worker in the factory and improving retrieval efficiency.

In order to analyze the parameters of slub yarn from sequential images accurately, an automatic image mosaic method is proposed in this paper. In this method, a series of overlapping yarn images, which are captured from a moving slub yarn, are stitched into a panorama automatically. Background subtraction, image segmentation and judgment template traversal methods are applied to preprocess the sequential images for obtaining a test image. Subsequently, certain rows in the bottom of the test image are used as a template image to match the next image. The matching coefficient matrix is calculated between the template image and next image based on the normalized cross-correlation method. In the matrix, the coordinates of the peak value are found as the optimal matching points. Two kinds of slub yarn images captured under 40 fps are stitched by using the proposed method and the manual method, respectively. Finally, an objective method is formulated to evaluate the qualities of the image mosaic by the proposed method. The experimental results show that the proposed method can find the match position accurately and is highly consistent with the manual method.

Seam puckering is often considered an undesirable wrinkling appearance along a seamline, and is a problem that concerns fabric, sewing machine and sewing thread manufacturers. Until now, the standardized evaluation method for seam-puckering grading is still a visual-based, subjective method. This research project was aimed at developing a computer-vision system for automatic seam-puckering evaluation to improve the consistency and efficiency of grading. Fabric seam images were captured by a customized image acquisition system, and the seam images and the optimal image parameters, such as length and width, were determined according to the results of human inspection. The seamline was located with edge detection and Hough transform techniques. After rotating and cropping the image, the projection profile was then obtained and smoothed with the locally scatter-plot smoothing (LOESS) algorithm. Five characteristic features were extracted from the smoothed profile. Finally, an artificial neural network classifier was created to realize the automatic assessment of the seam-puckering grade. The experimental results proved that the proposed system can achieve accurate seam-puckering grades, and has the potential to replace the current manual evaluation.

Obstructed by the yarn core, the detectable length and the detection rate of a hairy fiber are mainly determined by the geometry of the yarn and the location of the fiber in an optical system. This paper presents a new theoretical method of analyzing detectable angles of yarn hairiness in optical measurements. Firstly, a cylindrical model of the yarn core is constructed by using the yarn diameter, and spiral lines on the cylinder are drawn using the twist angle of the yarn. Secondly, hairy fibers are simulated by short-line segments passing a spiral line and the Z-axis of the model. The yarn model is projected onto a plane under the assumption of a collimated light source, which is the condition similar to that of optical measurements. The yarn model is cut by a plane parallel to the axes of the Cartesian coordinate system ( XOY) at the emergence points of hairy fibers. Finally, the relationship between the hairiness length and other factors, such as the test length, yarn diameter and detectable angle (i.e. the angle at which hairy fiber can be detected) is established. It has been demonstrated that the detection angle dictates not only the length of each hairiness but also the rate of detectable hairiness in the scene. Given a detectable angle, the upper and lower limits of detectable hairiness lengths can be predicted. The verification results of the detection rate by three measurement methods indicate that the detection rates of optical measurements have a certain guidance function for correcting the hairiness results of optical measurements.

To measure the warp and weft densities of high-tightness fabrics, an efficient inspection method utilizing a novel density–texture formulation is developed. The density–texture relationship of twill and satin weaves is analyzed, and a formulation based on the weft and wale densities is developed and applied to calculate the warp density. In the experiment, the weft and wale densities are detected using a projection method on separately acquired transmittance images, and the warp density is calculated using the density–texture formulation. Experimental results proved that the proposed method is effective for measuring yarn densities of high-tightness fabrics with twill and satin weaves under realistic production conditions and can satisfy the requirement for production practice.

This paper presents a new method for building a digital yarn black board (DYBB) with the yarn diameter data obtained from processing sequential yarn images. An image acquisition and processing system, mainly consisting of a video camera, a single-chip micro-computer and a stepper motor, was set up to capture sequence images of a moving yarn and extract yarn diameter data after the image threshold and morphological opening operation. Then, the diameter data of the yarn was used to construct the DYBB by redrawing all the scans in white on a black plane once they were aligned at the centers. The DYBB provides functions, such as local data amplification, fast focusing, phase adjustment and space adjustment, for more intuitive and convenient evaluation of yarn evenness.

A large amount of seam detection for inhomogeneously textured fabrics makes those performing it fatigued, which leads to misjudgments by human vision, especially for the seam detection of patterned inhomogeneously textured fabrics. The traditional wavelet texture analysis is no longer applicable to fabrics with inhomogeneous textures and irregular patterns. In this paper, a novel mean weighting factor is proposed to obtain an optimized discriminant measure to detect the fabric seams. Firstly, the wavelet coefficients are extracted in individual decomposition levels. Then a mean weighting factor is calculated on the use of the difference of the coefficient values between two consecutive decomposition levels, and a better discriminant measure for seam detection is obtained. Lastly, a thresholding process is used to segment the seam information from the background. The experimental results show that the proposed approach effectively carries out the seam detection in the inhomogeneously textured fabric images.

Fabrics are often subject to repeated creasing and bending deformations, such as elbow movements, and the resilience of crease recovery is an important property that affects fabric’s serviceability. In this research, nine types of woven fabrics were examined on an automated crease recovery tester repetitively to investigate the crease recovery behaviors, and possible factors affecting the creasing resilience. Each specimen was pressed and its recovery process was recorded by sequential images, which allowed the recovery angle to be calculated in real-time. This process was repeated 30 times for the same specimen. The parameters, such as initial angular velocity, instant recovery time and angle, stable recovery time and angle, were extracted from the recovery curve of each cycle, and calculate the differences between different cycles to characterize the changes of crease recovery in repeated tests. The experimental results show that the more the circulating test conducts, the earlier the instant and stable recovery time appear. The stable recovery angles decrease rapidly in the first few cycles, fall more slowly when the testing cycle increases, and finally become stable at a cycle near the 25th cycle. Cotton fabrics take fewer cycles to reach steady than wool fabrics. The high elasticity of polyester fibers affects the resilience remarkably.

In this paper, an effective method based on the smallest repeat unit recognition (SRUR) algorithm is proposed to inspect the color effect of yarn-dyed fabric automatically. This method consists of three main steps: (1) color pattern preliminary recognition; (2) weave repeat unit recognition; (3) color yarn repeat unit recognition. In the first step, the floats in the fabric are located by yarn position segmented with mathematical statistics of sub-images and the colors of all floats classified by the fuzzy C-means algorithm. The color yarn layout is recognized by statistical analysis and the color pattern is roughly generated. In the second step, the weave repeat unit is found based on the preliminary color pattern. The weave repeat unit is extracted from the incompletely recognized weave pattern matrix by the SRUR algorithm. In the last step, according to the weave repeat unit and the preliminary identified color pattern, the color yarn layout is rectified by the improved statistical analysis, and the color yarn repeat unit is finally obtained by the SRUR algorithm. According to the weave and color yarn repeat units, the color effect is produced. The experimental analysis proved that the proposed method can recognize color effects of yarn-dyed fabrics with satisfactory accuracy.

Wrinkle recovery is a dynamic process in which a folded fabric specimen continues to be unfolded by itself, and is often evaluated by angle changes between two folded fabric wings. Inspired by the advantages of video sequence in dynamic measurement, we developed a video capturing and processing system for dynamic measurements of fabric wrinkle recovery angle. In the experiment stage, a wrinkled specimen is first compressed by a pneumatic presser for a certain duration, and then videoed using a charge-couple device camera during its entire recovery process. Each image frame in the video sequence is processed to detect the free wing of the wrinkled specimen. To calculate the recovery angle accurately, image-processing algorithms, such as binarization, thinning operation and Hough transform, are implemented subsequently. Finally, the Wilcoxon rank-sum test is carried out to evaluate the difference between the data measured using the American Association of Textile Chemists and Colorists (AATCC) 66-2008 method and this proposed method. Experimental results indicate that the data calculated by our proposed method are consistent with those ones measured by the AATCC 66-2008 method. Compared with the existing fabric wrinkle recovery measurement devices, such as the SDL-M003 wrinkle recovery tester, the developed measurement system has made three important contributions: (1) it automates the entire testing procedure so that human interference is eliminated; (2) it records the complete change of the wrinkle angle so that the recovery property can be analyzed dynamically; and (3) it uses video sequence analysis to calculate recovery angles so that the measurement is more accurate and efficient.

The traditional approach to unevenness characterization of yarn is based on the CV (i.e. coefficient of variation) of mass between defined portions of yarn measured with the USTER evenness tester. In fact, yarn with the same parameters has different evenness in fabric, and the evenness of yarn in fabric is different from the source yarn, which is caused by the producing process and parameters of the fabric. However, there is no good method to describe the appearance of yarn in fabric. The paper focuses mainly on a novel method known as yarn evenness in fabric (YEF). The method processes the image of the fabric and is divided into four steps. The first step is the acquisition of the relative image from the sample of woven fabric. The second step is the pretreatment of the image and segmentation of the warp and weft from the fabric based on fast Fourier transform and inverse fast Fourier transform. The third step is to separate the single yarn from the warp or weft sets by the gray unidirectional mean method. In the fourth step, the average relative thickness was selected for characterizing yarn. SD data of thickness that we will analyze in future is also a method. Experimental results on virtual and physical woven fabric showed that the method mentioned can obtain the fine information of yarn from fabric in details. The method of YEF was programmed by Matlab software. Computational burdens are about 11.4 seconds on average, for one meter of warp and weft yarn samples. The program could be valuable when applied to the practical industry.

In this study, an automatic recognition system based on image analysis is constructed to identify the density, the color effect, the layout of color yarns, and the woven pattern of yarn-dyed fabric. To inspect the density, first the skew angles of yarns are detected by Hough transform and then the texture and boundary information of yarns are enhanced by steering filter and graygrads image. The yarns and floats are located in the enhanced images with gray-projection method. To get the color effect, FCM algorithm is used to classify the floats with the color features extracted from each float and the number of yarn colors obtained with cluster validity analysis. The color effect is then extracted from the color pattern obtained from the float classification results. To detect the layout of color yarns, a novel method is proposed in this study. The woven pattern of the yarn-dyed fabric is recognized based on woven fabric pattern database. Experiments on actual yarn-dyed fabrics show that the recognition system proposed in this study is effective for detecting the structure parameters of yarn-dyed fabric.

In the process of analyzing the yarn-dyed fabric, two kinds of color information about color yarns should be detected: (1) the number of yarn colors; (2) the layout of the color yarns. The traditional detection methods are time-consuming and labor-intensive. An automatic method based on image analysis is proposed in this study. The image of yarn-dyed fabric captured with a flat scanner is analyzed by a fuzzy C-means clustering (FCM) algorithm. By the analysis of the image of the yarn-dyed fabric based with the FCM algorithm, we can conclude that the number of yarn colors can be obtained with cluster validity analysis, and the layout of color yarns can be inspected automatically with the help of Hough transform. Experiments on two actual fabrics show that the approach proposed in this study is effective for detecting the number of yarn colors and the layout of color yarns in the yarn-dyed fabric.