Zhongjian Li

Measuring the unevenness of yarn apparent diameter from yarn sequence images

This article presents a novel method for measuring the unevenness of yarn apparent diameter based on yarn sequence images captured from a moving yarn. A dynamic threshold module was designed to gain the global threshold for segmenting yarns in the sequence images. In the module, a K-means clustering algorithm was employed to classify the pixels of each frame in the sequence into two clusters—yarn and background. The cluster center of the current frame was used as the initial value of the cluster center for the next frame in the sequence to expedite the segmentation process. From the segmented yarn image, the yarn core was further extracted utilizing the characteristics of yarn hairiness, and two judgment templates were adopted to remove burrs, isolated points and unrelated small areas in the images. The yarn apparent diameter was measured on the yarn core at a given interval. The same kind of yarns were tested by using this method and Uster Evenness Tester 5. The experimental results show that the proposed method can accurately detect the unevenness of yarn apparent diameter and provide new useful information about yarn unevenness, such as the short-term, the long-term, and the periodic variations of yarn apparent diameters.

Applying Image Analysis for Automatic Density Measurement of High-tightness Woven Fabrics

To realise the density measurement of high-tightness woven fabrics, an efficient inspection method based on the structure relation is developed in this paper. The structure relations of typical HTWF, twill and satin weave are analyzed and a calculation equation of warp density is given with the fabric weave, weft density and wale density. In the experiment, the weft and wale densities are measured with the Fourier transform, image reconstruction and threshold processing based on separately captured images. The warp density is finally calculated based on the mean value of wale and weft density and the given calculation equation constructed with the weave pattern. The experimental results prove that the automatic measurement density system can realize the precise measurement of high-tightness woven fabric density with satisfactory precision and can replace the current manual analysis method.

Intelligent recognition of dominant colors for Chinese traditional costumes based on a mean shift clustering method

Abstract Chinese traditional costumes have been recognized as one of the most influential sources for Western designers to obtain oriental inspirations and create Asian chic, especially the dominant colors and design style. In this paper, an effective color clustering method based on Mean shift clustering algorithm is developed for Chinese traditional costumes image. The proposed method consists of four steps: (1) costumes image acquisition, (2) costumes image denoising, (3) object segmentation, and (4) color clustering and dominant colors extraction. Firstly, a digital SLR (Single Lens Reflex) camera is used to capture the costumes images. Secondly, the sub-images in the three color channels are filtered by median filter separately. Thirdly, the filtered images are segmented based on the background color in the Lab color space, and the object costumes is separated from the background. Fourthly, the pixels of the costume image are classified into several clusters by Mean shift clustering algorithm, and the dominate colors are extracted from the classification results. The experimental results demonstrate that the proposed method can extract the dominant colors from costumes images with great accuracy when the bandwidth of Mean shift clustering algorithm is set as 0.05.

Evaluation of an Intelligent Computer Method for the Automatic Mosaic of Sequential Slub Yarn Images

Abstract This paper is the second part of a series reporting the recent development of a computerised method for automatic mosaic sequential yarn images. In our earlier work, an effective method for stitching sequence slub yarn images automatically was developed based on image processing and the normalised cross correlation (NCC) method. 100 image pairs of two kinds of slub yarn were measured in certain specific conditions, such as the frame rate, size of stitching template, etc., and the measurement results were evaluated with the manual method. In this paper, the effects of various influencing factors are numerically examined, including the stitching template size, threshold value, frame rate, and computing time of the mosaic algorithm. The feasibility and accuracy of the fully computerized method were evaluated further under the various influencing parameters. One hundred percent cotton ring spun single slub yarns of 27.8, 15.6, and 9.7 tex were prepared and used for the evaluation. The measurement results obtained by the method proposed are analysed and compared with those measured manually by Adobe Photoshop. The experimental results show that the method proposed can accurately find the stitch position and has a high consistency with the manual method when the matching template is 100 × N pixels, the threshold value T1 ∈ [20, 40] and T2 ∈ [51, 80], and the frame rate is greater than 40 fps.

An intelligent computer method for automatic mosaic of sequential slub yarn images based on image processing

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.

Formation of digital yarn black board using sequence images

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.

Measurement of long yarn hair based on hairiness segmentation and hairiness tracking

Abstract For the problem of hairiness information missed in existing hairiness measurement method, the goal of this work is to accurately measure the length of long yarn hairiness and obtain the path over every hairiness point of the whole hairiness. To achieve this goal, the yarn images were captured by the video microscope (MOTIC) and the thinned hairiness images were obtained by a series of image processing. The different measurement baseline and step value were choose to segment long hairiness in the method of hairiness segmentation, and the different hairiness lengths were obtained, the results of length show that the length of 0.5mm (baseline)and 3 pixels (step value) is closest to hairiness real length. And then, the more accurate lengths of the hairiness were calculated by the method of hairiness tracking. The lengths of the two new methods are longer than the length of the method of fixed length (1mm), but the lengths of hairiness tracking is longer than the longest lengths of hairiness segmentation. The compared results show that the method of hairiness tracking can record the information of every point in hairiness and calculate the pixels of a hair fiber, and acquire more complete information of full hairiness then hairiness segmentation.

Real-time Segmentation of Yarn Images Based on an FCM Algorithm and Intensity Gradient Analysis

This paper presents a new method for real-time segmentation of yarn images which are captured by a real-time image acquisition device. The first frame of the images is clustered by the local average intensity and entropy of the image based on the FCM (Fuzzy C-means) algorithm to obtain a segmentation threshold value. The pixels with an intensity below the threshold value in each column of the image are convolved with a convolve template to construct an intensity gradient curve. The points of maximum value and minimum value in the curve are considered as the upper and lower edge points of yarn. A robust real-time segmentation algorithm of yarn images is obtained for evaluating yarn diameter more precisely. Finally two indices of SE (Segmentation Error) in % and ADE (Average Diameter Error) in % are proposed to evaluate the segmentation method, which is then compared with the manual method.