Journal of Textile Research ›› 2019, Vol. 40 ›› Issue (05): 150-156.doi: 10.13475/j.fzxb.20180404607

• Management & Information • Previous Articles     Next Articles

Identification and application of yarn hairiness using adaptive threshold method under single vision

WANG Wendi, XIN Binjie(), DENG Na, LI Jiaping, LIU Ningjuan   

  1. Fashion College, Shanghai University of Engineering Science, Shanghai 201620, China
  • Received:2018-04-19 Revised:2019-02-12 Online:2019-05-15 Published:2019-05-21
  • Contact: XIN Binjie E-mail:xinbj@sues.edu.cn

RichHTML

4

PDF (PC)

67

Abstract:

In order to measure the yarn parameter information more accurately, the image grayscale enhancement algorithm and the linear region threshold segmentation algorithm were proposed to solve the serious loss of hairiness information after yarn image processing with the image background processing and the threshold segmentation algorithm. Using the self-built image acquisition system, six different types of yarn samples were acquired, and then the accuracy and validity of the image recognition algorithm was verified. Experimental results show that the proposed two algorithms can significantly reduce the loss of yarn image information and have good robustness. The length and number of yarn hairiness detected by the image processing method are similar to those of the visual inspection method. The grayscale contrast of the yarn and yarn image background is enhanced, and the effect of poor image segmentation due to a single threshold is avoided, thereby improving the recognition accuracy and measurement accuracy of the yarn hairiness. The research results provide an effective yarn image analysis algorithm for the subsequent development of a commercial yarn hairiness detection system.

Key words: yarn hairiness, adaptive grayscale enhancement, regional threshold segmentation, image processing, image analysis

CLC Number: 

  • TP319

Fig.1

Yarn hairiness image acquisition system. (a) Schematic diagram of yarn image acquisition system; (b) Dark box structures"

Tab.1

Basic parameters of yarn sample"

试样编号 纱线成分 成纱方式 梳纱工艺 纱线线密度/tex
1# 棉 环锭纺 精梳 14
2# 棉 环锭纺 精梳 18
3# 棉 环锭纺 精梳 26
4# 棉 环锭纺 普梳 26
5# 棉 转杯纺 精梳 28
6# 涤纶 环锭纺 精梳 28

Fig.2

Original yarn images"

Fig.3

Image difference processing. (a) Background image;(b) Partial enlargement of image after image differential processing; (c) Gray value histogram after image difference processing; (d) Local gray value matrix of image after image difference processing"

Fig.4

Image grayscale contrast after background removal. (a) Background removal image IA;(b) Gray stretched enhanced image IB;(c) Adaptive grayscale enhancement image IC"

Fig.5

Image local gray value matrix after image processing. (a) Local gray value matrix of image IA;(b) Local gray value matrix of image IB; (c) Local gray value matrix of image IC"

Fig.6

Wiener filtered image comparison. (a) Image IB after treatment (ID); (b) Image IC after treatment (IE)"

Fig.7

Image comparison after OTSU threshold segmentation. (a) Image ID after processing (IF);(b) Image IE after processing (IG)"

Fig.8

Image comparison after OTSU threshold segmentation. (a) Image ID after grayscale processing and wiener filter treatment for two times (IH);(b) Image (IE) after grayscale processing and wiener filter treatment for three times (IK)"

Fig.9

Comparison between linear region threshold segmentation and full threshold segmentation. (a) Threshold segmented image of IL;(b) Linear region threshold segmentation image of IM"

Fig.10

Yarn image morphology processing. (a) Image IM after morphological processing; (b) Image IO after morphological processing;(c) Image IP after thinning image IO"

Tab.2

Comparison of image method and visual inspection for detecting length and number of yarn hairiness"

编号 毛羽长度/
mm		 毛羽根数 偏差/%
图像法 目测法
1 107.4 86.7 23.88
2 23.3 22.3 4.5
1# 3 5.1 5.1 0
4 1.2 1.2 0
5 0.6 0.6 0
6 0 0 0
1 127.3 87.6 45.32
2 13.6 13.2 3.03
2# 3 1.3 1.3 0
4 0 0 0
5 0 0 0
6 0 0 0
1 75.5 67.3 12.18
2 10.1 8.7 16.09
3# 3 0.9 0.9 0
4 0.2 0.2 0
5 0.1 0.1 0
6 0 0 0
1 107.8 92.3 16.79
2 20.1 18.8 6.91
4# 3 2.8 2.8 0
4 0.3 0.3 0
5 0.1 0.1 0
6 0 0 0
1 117.3 86.7 35.29
2 23.1 19.6 17.86
5# 3 2.6 2.6 0
4 0.2 0.2 0
5 0 0 0
6 0 0 0
1 76.3 63.8 19.59
2 12.8 11.3 13.27
6# 3 5.2 5.1 1.96
4 0.3 0.3 0
5 0 0 0
6 0 0 0
[1] WANG Y Y, HUANG Q L, YANG G Y. The application of intelligent laser sensor on yarn quality inspection[J]. Soft Magnetic Materials, 2011,298:35-39.
[2] SUN Y Y, PAN R R, ZHOU J, et al. Analysis of detectable angles of yarn hairiness in optical measurements[J]. Textile Research Journal, 2017,87(11):1297-1307.
[3] OH S, LEE M S, KIM S. Automatic measurement of yarn crimp using image analysis[J]. Journal of Testing and Evaluation, 2014,42(2):291-297.
[4] HUANG Z, YANG YANG, An image analysis method for studing yarn cross-sectional structure[J]. Advanced Measurement and Test, 2011, 301-303: 41-48.
[5] SULE I. The determination of the twist level of the Chenille yarn using novel image processing methods: Extraction of axial grey-level characteristic and multi-step gradient based thresholding[J]. Digital Signal Processing, 2014,29:78-99.
[6] 孙银银, 潘如如, 高卫东. 基于数字图像处理的纱线毛羽检测[J]. 纺织学报, 2013,34(6):102-106.
SUN Yinyin, PAN Ruru, GAO Weidong. Detection of yarn hairiness based on digital image processing[J]. Journal of Textile Research, 2013,34(6):102-106.
[7] NATERI A S, EBRAHIMI F, SADEGHZADE N. Evaluation of yarn defects by image processing tech-nique[J]. Optik, 2014,125(20):5998-6002.
[8] FABIJAŃSKA A, JACKOWSKA-STRUMIŁŁO L. Image processing and analysis algorithms for yarn hairiness determination[J]. Machine Vision and Applications, 2012,23(3):527-540.
[9] KOLAREVIC D, VUJASINOVIC T, KANJER K, et al. Effects of different preprocessing algorithms on the prognostic value of breast tumour microscopic images[J]. Journal of Microscopy, 2018,270(1):17-26.
doi: 10.1111/jmi.12645 pmid: 28940426
[10] YANG L, ZHANG Y Z, GULDNER I H, et al. Fast background removal in 3D fluorescence microscopy images using one-class learning[J]. Medical Image Computing and Computer-Assisted Intervention, 2015,9351(3):292-299.
[11] CELIK H I. Development of a machine vision system for yarn bobbin inspection[J]. Industria Textile, 2016,67(5):292-296.
[12] ASGARI H, MOKHTARI F, LATIFI M, et al. Characterizing cotton yarn appearance due to yarn-to-yarn abrasion by image processing[J]. Journal of The Textile Institute, 2014,105(5):477-482.
[13] HLADNIK A, PAVKO-CUDEN A, FARAJIKHAH S. Image segmentation based determination of elastane core yarn diameter[J]. Fibres & Textiles in Eastern Europe, 2016,24(2):29-36.
[14] JING J F, HUANG M Y, LI P F, et al. Automatic measurement of yarn hairiness based on the improved MRMRF segmentation algorithm[J]. Journal of The Textile Institute, 2018,109(6):740-749.
[1] ZHANG Zhengye, XIN Binjie, DENG Na, CHEN Yang, XING Wenyu. Research and application of algorithm for measuring hemp fiber cross-sectional parameters based on boundary tracking [J]. Journal of Textile Research, 2020, 41(02): 39-43.
[2] LI Pengfei, YAN Kai, ZHANG Huanhuan, JING Junfeng. Hairiness detection based on maximum entropy and density clustering [J]. Journal of Textile Research, 2019, 40(07): 158-162.
[3] WU Yilun, LI Zhongjian, PAN Ruru, GAO Weidong, ZHANG Ning. Weft knitted fabric appearance simulation using colored spun yarn image [J]. Journal of Textile Research, 2019, 40(06): 111-116.
[4] HUANG Jiajun, KE Wei, WANG Jing, DENG Zhongmin. Color shading detection and rating system for denim based on computer vision [J]. Journal of Textile Research, 2019, 40(05): 163-169.
[5] CAI Yichao, ZHOU Xiao, SONG Mingfeng, MOU Xin'gang. Defect detection of cheese yarn based on multi-scale multi-direction template convolution [J]. Journal of Textile Research, 2019, 40(04): 152-157.
[6] . Detection and evaluation on yarn hairiness of blackboard with image processing [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(08): 144-149.
[7] . Position recognition of spinning yarn breakage based on convolution neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(06): 136-141.
[8] . Detecting method of foreign fibers in seed cotton based on deep-learning [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(06): 131-135.
[9] . Reducing yarn hairiness by wetting in ring spinning [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(05): 108-112.
[10] . Spinning breakage detection based on optimized hough transform [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(04): 36-41.
[11] . Application of algorithm with improved frequency-tuned salient region [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(03): 154-160.
[12] . On-line yarn cone defects detection system based on machine vision [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(01): 139-145.
[13] . Automatic extraction on embroidered patterns [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(09): 120-126.
[14] . Tracking measurement of yarn hairiness skeleton and length [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(08): 32-38.
[15] . Rapid identification method of cashmere and wool based on bag-of-visual-word [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(07): 130-134.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号
Copyright 2021 © Editorial office of Journal of Textile Research
Supported by Beijing Magtech Co.Ltd