Yarn Images Research Articles

Neural inverse procedural modeling of knitting yarns from images

We investigate the capabilities of neural inverse procedural modeling to infer high-quality procedural yarn models with fiber-level details from single images of depicted yarn samples. While directly inferring all parameters of the underlying yarn model based on a single neural network may seem an intuitive choice, we show that the complexity of yarn structures in terms of twisting and migration characteristics of the involved fibers can be better encountered in terms of ensembles of networks that focus on individual characteristics. We analyze the effect of different loss functions including a parameter loss to penalize the deviation of inferred parameters to ground truth annotations, a reconstruction loss to enforce similar statistics of the image generated for the estimated parameters in comparison to training images as well as an additional regularization term to explicitly penalize deviations between latent codes of synthetic images and the average latent code of real images in the encoder’s latent space. We demonstrate that the combination of a carefully designed parametric, procedural yarn model with respective network ensembles as well as loss functions even allows robust parameter inference when solely trained on synthetic data. Since our approach relies on the availability of a yarn database with parameter annotations and we are not aware of such a respectively available dataset, we additionally provide, to the best of our knowledge, the first dataset of yarn images with annotations regarding the respective yarn parameters. For this purpose, we use a novel yarn generator that improves the realism of the produced results over previous approaches.

Reverse reconstruction of geometry modeling and numerical verification of 2.5D woven composites based on deep learning

This paper proposes a reverse reconstruction method to generating accurately and high-effectively the meso-scale geometry modeling of 2.5D woven composites based on the deep learning. The method first segments the yarn from the X-ray computed tomography (Micro-CT) images based on the deep convolutional neural network (DCNN). Then, reconstruct the yarn surface model from segmented yarn images by using the marching cube algorithm. Consequently, the reverse model is generated by outlining the yarn surface model. Moreover, the yarn geometric parameters are analyzed to evaluate the geometric accuracy of the reverse model. Simultaneously, for the validation of the reverse model, the parametric model, the ideal model, and the experimental tests are considered. Where the parametric model and ideal model are established based on the geometric parameters of yarns. The results show that the DCNN is capable of accurately segmenting yarns from Micro-CT images with a global accuracy of 95.08%. The stiffness prediction error of the reverse model is only 0.706%, which is less than the error of the parametric model (3.77%) and much less than the ideal model. The reverse reconstruction method improves the efficiency of geomerty modeling by focusing on actural images rather than statistical parameters.

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.

Measurement of yarn apparent evenness based on modified Canny edge detection

To evaluate accurately yarn apparent evenness, a simple yet effective method based on modified Canny edge detection was presented. Firstly, the originally captured yarn image is processed by Gaussian filtering, and the weighted least square method is used to calculate the horizontal and vertical directions of the image gradient for obtaining gradient images. Then the non-maximum suppression is applied to process the obtained gradient images and the double threshold algorithm is used to get the yarn edge curve. Finally, the average yarn diameter and the yarn coefficient variation (CV) of yarn were calculated via the number of pixels at the upper and lower edge points of the yarn evenness. To verify the validity and accuracy of the method, yarns with different linear densities were tested. The experimental results demonstrate that the proposed method can accurately detect the unevenness of the yarn apparent diameter.

Dynamic Yarn-Tension Detection Using Machine Vision Combined with a Tension Observer.

Machine vision can prevent additional stress on yarn caused by contact measurement, as well as the risk of hairiness and breakage. However, the speed of the machine vision system is limited by image processing, and the tension detection method based on the axially moving model does not take into account the disturbance on yarn caused by motor vibrations. Thus, an embedded system combining machine vision with a tension observer is proposed. The differential equation for the transverse dynamics of the string is established using Hamilton's principle and then solved. A field-programmable gate array (FPGA) is used for image data acquisition, and the image processing algorithm is implemented using a multi-core digital signal processor (DSP). To obtain the yarn vibration frequency in the axially moving model, the brightest centreline grey value of the yarn image is put forward as a reference to determine the feature line. The calculated yarn tension value is then combined with the value obtained using the tension observer based on an adaptive weighted data fusion method in a programmable logic controller (PLC). The results show that the accuracy of the combined tension is improved compared with the original two non-contact methods of tension detection at a faster update rate. The system alleviates the problem of inadequate sampling rate using only machine vision methods and can be applied to future real-time control systems.

Analysis and measurement of the shape of spinning balloons

The development of superconducting magnetic bearings as the twisting element in ring spinning renews the study of the dynamic model of the ring spinning process. In this paper, the variational equation describing the steady motion of the yarn is developed using Hamilton’s principle, the balloon shape is represented by the Bezier polynomial, the undetermined coefficient is solved by Galerkin method, and the semi-analytical solution of the steady-state balloon shape is obtained. Digital images of the balloon yarn are collected by binocular cameras and a stroboscope, and the balloon curve is reconstructed by stereo vision technology. The calculated balloon curve is in good agreement with the measured balloon curve. The balloon shapes and the radial forces acting on the permanent magnetic ring at different radii of the wind-point on the bobbin are investigated by the semi-analytical model when the spindle is spinning at different speeds. The solution procedures developed can be used to explore the vibration and stability of the system, consisting of the magnetic stiffness, permanent magnetic ring, and balloon yarn in the superconducting magnetic bearing twisting mechanism.

A knowledge augmented deep learning method for vision-based yarn contour detection

Contour detection extracts accurate object boundaries from natural images, which plays a critical role in the vision-based inspection. However, contour detection is still challenging in yarn quality inspection tasks, since the current methods pursue global high-precision contours while ignoring detecting the boundaries of interest from intertwined objects in complex local regions. This paper proposes a knowledge augmented contour detection method with deep learning to extract pure backbone boundaries from intertwined objects for more accurate yarn quality inspection. Firstly, according to the directional gradient distribution of yarn images in the visual system, a radial pixel difference convolution is improved to extract interested edge features. Secondly, considering the graphical characteristics of the yarn to be inspected, a mask layer of texture erosion is designed to further filter irrelevant details from extracted edge features. The comparative experiments during actual spinning processes demonstrate that the proposed method achieves a better ODS (optimal dataset scale, a standard contour detection evaluation measure) of 0.815, and reduces the quality inspection error from about 1.5% to tolerated 0.534%.

MATLAB Algorithms for Diameter Measurements of Textile Yarns and Fibers through Image Processing Techniques.

Textile yarns are the fundamental building blocks in the fabric industry. The measurement of the diameter of the yarn textile and fibers is crucial in textile engineering as the diameter size and distribution can affect the yarn’s properties, and image processing can provide automatic techniques for faster and more accurate determination of the diameters. In this paper, facile and new methods to measure the yarn’s diameter and its individual fibers diameter based on image processing algorithms that can be applied to microscopic digital images. Image preprocessing such as binarization and morphological operations on the yarn image were used to measure the diameter automatically and accurately compared to the manual measuring using ImageJ software. In addition to the image preprocessing, the circular Hough transform was used to measure the diameter of the individual fibers in a yarn’s cross-section and count the number of fibers. The algorithms were built and deployed in a MATLAB (R2020b, The MathWorks, Inc., Natick, Massachusetts, United States) environment. The proposed methods showed a reliable, fast, and accurate measurement compared to other different image measuring softwares, such as ImageJ.

A knowledge augmented image deblurring method with deep learning for in-situ quality detection of yarn production

In the in-situ quality detection of yarn production, image deblurring plays a critical role in the vision-based detection systems to restore a sharp image and provide more accurate input for inspection. However, image deblurring is still challenging since the current methods are mainly based on the pre-defined blur degree. In dynamic yarn production, the relationship between the defocus blur degrees and the poses of the yarn body is highly associated, which can be excavated to prior knowledge in image deblurring to achieve more effective restoration. Thus, a knowledge augmented deep learning model is proposed to adaptively deblur yarn images with variable defocus blur degrees. A pose classification module designed by prior knowledge is embedded into the deep neural network, which classifies the yarn poses and feeds them into multi-scale deblurring channels. In each channel, we incorporate the image gradient prior into the specially designed loss function to attract the attention of the deblurring network on the edge details of the yarn. The experimental results from actual spinning processes demonstrate that the proposed method performs a better effect not only in the variable-scale deblurring of the global image but also in the restoration of the edge details.

A computer vision based online quality control system for textile yarns

Yarn quality control is a crucial step in producing high quality textile end products. Online yarn testing can reduce latency in necessary process control by providing rapid insights into yarn quality, leading to production of superior quality yarns. However, both widely used capacitance based evenness testers and emerging imaging based evenness testing systems are largely offline in operation (i.e. a posteriori). A suitable online system that could be employed to test quality of a variety of yarns in normal industrial processing conditions does not yet exist.In this study, we propose an online evenness testing system for measurement of a certain type of yarn defect called nep by using imaging and computer vision techniques. The developed system directly captures yarn images on a spinning frame and uses Viola-Jones object detection algorithm for real-time detection of nep defects. The validation of nep detection algorithms and comparison of the new method with an existing evenness tester in terms of nep count demonstrated its reasonable defect detection accuracy and promising potential for application in wider yarn spinning industry.

Optimization of acquisition parameters of slurry coating characteristics based on multiple yarn simultaneous detection

A simultaneous detection method was proposed to detect slurry coating characteristics based on the same spatial resolution of starch-based sized and raw yarns. A dynamic image acquisition device was improved to capture the apparent images of multiple yarns simultaneously after the starch–iodine color reaction. The slurry coating characteristics were calculated utilizing image-processing technology. For the sake of effective and stable detection, the effects of illumination conditions on the concentration of I2-KI solution were studied through the absorbance value test. The effects of image-processing parameters on the experimental results were analyzed respectively by measuring six kinds of yarn of different counts and size pick-up. The results showed that the illumination conditions within an illumination time of 0–60 min, illumination intensity of 0–80,000 lux and illumination distance of 0.01–0.20 m had no significant effects on the concentration of I2-KI solution. Eight rows of pixels in the central axis areas of the yarn were determined as the effective statistical areas. It was determined that the sample size can meet the needs of stability test in 200 pieces. A dynamic threshold method, which served the intersection of the gray histogram of sized and raw yarn under the same spatial resolution as the threshold, can effectively segment the slurry coating areas. On the above basis, the optimization acquisition parameters of the detection method were obtained. The proposed method can meet the requirements of the efficiency test, common applicability and ease of operation.

The Comparison of the Edge Detection Methods in the Determination of Yarn Hairiness through Image Processing

In this study, an image processing approach for the determination of yarn hairiness was presented. Yarn images taken under microscope were examined in MATLAB software. Seven different edge detection algorithms were used in order to separate the hairs from the yarn body accurately. Seven different textural properties of obtained yarn images were compared with Zweigle hairiness test results. The best hairiness results were obtained in Sobel and Prewitt edge detection methods. The findings have indicated that there were stronger correlation values for Sobel and Prewitt methods between Zweigle indices and four different textural features.

A method to evaluate the diameter of carded cotton yarn using image processing and artificial neural networks

Cotton yarn diameter is an important characteristic that reflects the quality of the yarn to a large extent. In this paper, a new method was proposed to determine the diameter of cotton yarn using digital image processing and artificial neural networks. After processing scanned yarn image, the inputs of ANN were represented by yarn count and the white pixels number of edge detection of processed image. The output of ANN was the diameter of cotton yarn. This ANN has been tested on new samples. The results were compared with actual results as well as both empirical formulas (Peirce’s method and Mogahzy’s method) of yarn diameter which is allocated to calculate the diameter of cotton yarn. ANN has given more acceptable results than both Peirce’s relationship and Mogahzy’s relationship. To deal easily with the algorithm of this research, a simple graphical user interface has been established.

Investigation into the effects of yarn structure and yarn count on different types of core-spun yarns

The scope of this research is to study the effect of yarn structure and yarn count on properties of types of core-spun yarns, including elastic core/T400, elastic core/Lycra, dual core, and tri-core yarns. Five types of yarn structures and three yarn counts were produced. Mechanical properties, yarn irregularity, imperfections, and hairiness were measured. Full-factorial analysis and Tukey tests were performed on the test results. It was concluded from factorial analysis that yarn count, yarn structure, and two-way interaction had a significant effect on yarn properties, except for yarn hairiness where the effect of yarn structure and two-way interaction was not significant. A Tukey pairwise comparison was used in this study to specify exactly the subgroups of yarn count and yarn structure that have a significant mean difference. The scanning electron microscopy (SEM) images of the dual-core yarns and tri-core yarns were performed to illustrate the structure of these yarns.

Mechanical and cellular characterization of electrospun poly(l-lactic acid)/gelatin yarns with potential as angiogenesis scaffolds

Electrospun PLLA/gelatin yarns with different compositions were fabricated as tissue engineering scaffolds. The yarns were characterized by scanning electron microscopy (SEM) and tensile mechanical testing. Cell interaction with yarns was investigated by measurements of cell viability, proliferation, morphology, phenotype, and angiogenic activity (measurement of nitric oxide) using human umbilical vein endothelial cells (HUVECs). The SEM images of yarns showed a uniform structure with axial alignment of the fibers in the yarn surface. The mechanical properties of the yarns changed with the amount of PLLA, indicating the yarn of 40% PLLA and 60% gelatin had the highest stress-at-break (2.47 MPa). Also, there was an increase in the toughness with increasing in the amount of PLLA content in the PLLA/gelatin composition. After 7 days, HUVECs exhibited the best viability and proliferation responses on a yarn of 70% PLLA and 30% gelatin, having 223.56% increase in viability and 306.17% increase in proliferation compared with those of HUVECs alone without any yarns (the control group). Measurement of nitric oxide after 5 days suggested potential applications of yarns in angiogenesis, such as cardiovascular disease and wound healing, with a yarn of 70% PLLA and 30% gelatin having the highest ratio of released nitric oxide (156.20% of the control group). Having a uniaxial structure, the PLLA/gelatin yarns introduced in this study can provide more effective implantation in tissue engineering applications facing geometric and accessibility constraints, such as fibrous tissue regeneration.

Using analytical hierarchy process to optimize mechanical properties of multi-twisted buckled silk yarn as a collagenous tissue scaffold

The present research is focused on optimization the buckling process factors to produce buckled silk yarn using the Analytic Hierarchy Process (AHP) method to gain the best mechanical properties. To achieve this aim, the improvement of mechanical performance is investigated by surface changes of single yarns due to air-jet buckling process. SEM images of yarns approved the efficiency of buckling process by increasing the yarn diameter. According to the decision matrix, the best conditions of buckling process were related to 40 Psi as air pressure and 80 rpm as speed. In the following step, multi-twisted buckled silk yarn was designed and compared in load at break aspect with native collagenous tissues. To sum up, buckling process and also analytic hierarchy process optimization method are the acceptable approaches to design the best structure of multi-twisted buckled silk yarn that has a good potential as a scaffold in collagenous tissues.

Texture features extraction of multi-coloured fancy yarn

In the present work, a framework of extracting important texture features of multi-coloured fancy yarns is proposed. Aself-developed image capturing apparatus is used to record the image of fancy yarn. Subsequently, the captured digitalimages are processed to produce spatially corresponding pixel points to reconstruct digital images of the object,including image greying, filtering and morphology processing. At last, different segmentation methods are used to extractthe texture features of fancy yarns, and the optimal segmentation method to each kind of fancy yarn is analysed.

Detection of Bobbin Yarn Surface Defects by Visual Saliency Analysis

In order to solve the problem of unstable quality of the traditional bobbin yarn surface defect detection, a method for detecting the surface defect of bobbin yarn using visual saliency analysis is proposed. Firstly, the Difference of Gaussian algorithm is used to suppress the texture of the image, and the contrast between the defect area and the background is enhanced. Then, the method of wavelet threshold is applied to filter the noise in the images after the Difference of Gaussian, and the detailed features of the defect area are preserved while the noise interference is eliminated. Finally, the frequency tuned visual saliency algorithm is used to extract and segment the defective regions accurately. After the process about the Difference of Gaussian and wavelet threshold denoising, the original image of the bobbin yarn can make the image highlight the feature information of the defect area on the basis of ensuring elimination of the background texture and noise, and facilitate the detection of the defect area by combining visual saliency analysis. In the detection of the accuracy and integrity of the defect area, the detection method of this paper is better than the control method, and the defect segmentation result is more accurate. The proposed method for detecting the surface defect of the bobbin can not only completely eliminate the influence of the background texture of the bobbin surface, but also accurately and completely detect the surface defect of the bobbin, and the defect details remain intact. In this paper, the effectiveness of the algorithm is further verified by objective tests. The precision and recall rate of the test are 95.15 % and 98.00 %, respectively, which can meet the needs of actual detection.

Development of helical auxetic yarn with negative Poisson’s ratio by combinations of different materials and wrapping angle

Auxetic materials have negative Poisson ratio which has a multiple ranges of functional applications. The helical auxetic yarn was successfully developed through direct twist system by using core and wrap yarn or filament, which shows Auxeticity when the HAY is stretched in longitudinal direction in response it expand in transverse direction, Helical Auxetic Yarns were developed using various parameters of the core and warp filament, these parameters are wrapping angle (Twist per meter), diameter ratio, and modulus ratio. The strength of Helical yarn was characterized using single yarn strength and Image J software was used for the calculation of poisson’s ratio. According to test results, it is concluded that the core filament of helical auxetic yarn increased its thickness in transverse direction under stress, and a considerable negative poisson’s ratio was calculated. The values of negative poisson’s ratio described that the auxeticity had a direct relation with core filament thickness or diameter and inversely proportional to the linear density of wrap filament, in case of the wrap angle the auxeticity of HAY yarn had an inverse effect with wrap angle. Kevlar/polypropylene combination sample showed maximum auxeticity at a 15-degree angle while Kevlar/nylon combination sample showed minimum auxeticity at a 25-degree wrap angle.

Research on Yarn Diameter and Unevenness Based on an Adaptive Median Filter Denoising Algorithm

In this paper an adaptive median filtering denoising algorithm is proposed to measure yarn diameter and its unevenness. Images of nine different yarn samples were captured using one set of a self-developed yarn image acquisition system. Image separation of the background and yarn sections was conducted using a combination of adaptive median filtering, adaptive threshold segmentation and morphological processing. The noise-free yarn image was used for diameter detection of the subsequent yarn image and the discrimination of the yarn unevenness. Experimental results show that the testing data of yarn unevenness detection based on the adaptive median filter denoising algorithm is very consistent with the data using the traditional method. It is proved that the yarn detection method proposed, based on an adaptive median filter denoising algorithm, is feasible. It can be used to calculate yarn diameter accurately and measure yarn unevenness efficiently, so as to determine the quality of yarn appearance objectively.