Journal of Textile Research ›› 2019, Vol. 40 ›› Issue (11): 50-56.doi: 10.13475/j.fzxb.20181104307

• Textile Engineering • Previous Articles     Next Articles

Objective smoothness evaluation of fabric based on Fourier spectral features

SHI Kangjun, WANG Jing'an, GAO Weidong()   

  1. Key Laboratory of Eco-Textiles (Jiangnan University), Ministry of Education, Wuxi, Jiangsu 214122, China
  • Received:2018-11-19 Revised:2019-03-28 Online:2019-11-15 Published:2019-11-26
  • Contact: GAO Weidong E-mail:gaowd3@163.com

RichHTML

7

PDF (PC)

158

Abstract:

In order to solve the problems that the manual evaluation of fabric smoothness is subjective and the existing objective evaluation has low accuracy, a fabric smoothness evaluation method based on Fourier transform, spectral feature extraction and support vector machine was proposed. Firstly, the images of the standard replicas and fabric samples were acquired; the obtained images were preprocessed and transformed to the Fourier frequency domain; and a set of low-pass filters were constructed in the frequency domain, and the frequency interval of the wrinkle information in the spectrogram was determined by frequency domain filtering and inverse Fourier transformation, which is called the wrinkle contribution interval. The wrinkle contribution interval was divided into several feature subintervals, and the spectral amplitude in each interval was integrated, which is constructed into the feature vector. The feature vector set was constructed by the feature vectors of all training samples, and utilized to train the support vector machine, which can objectively evaluate the fabric smoothness. The total number of the adopted fabric samples is 132, among which 24 and standard template images are taken as the training set, and the rest are taken as the test set. The results show that the algorithm performs well on fabric smoothness evaluation, and the evaluation accuracy rate is up to 96.30%.

Key words: smoothness, objective evaluation, fabric wrinkle, Fourier transform, support vector machine

CLC Number: 

  • TS941.2

Fig.1

System of capturing sample"

Fig.2

Images of AATCC template"

Fig.3

Contrast diagram before and after equalization. (a) Image before equalization;(b) Image after equalization"

Fig.4

Transformed images of AATCC template by 2D-FFT"

Fig.5

Spectrum amplitude total of AATCC template"

Fig.6

Each filter and its inverse transformed image"

Fig.7

Spectra amplitude total of each feature subinterval"

Fig.8

Schematic diagram of fabric amplitude distribution of each grade"

Fig.9

Comparison of different resolutions fabric spectra. (a) High resolution twill fabrics and local magnification; (b) Fabric spectrum of (a); (c) Low resolution twill fabrics and local magnification; (d) Fabric spectrum of (c)"

Tab.1

Classification accuracy of different segmentation steps"

分割步长 特征子区间数 分类准确率/% 训练平均时间/s
5 36 85.19 1.774 1
7 15 88.89 1.628 6
9 10 88.89 1.606 7
11 6 96.30 1.589 8
13 6 92.60 1.580 6
15 3 94.44 1.579 2

Tab. 2

Classification accuracy of different pretreatment conditions"

预处理方式 分类准确率/% 支持向量机参数
[0, 1]归一化 93.52 ‘-t 1 -c 1 -g 1/6’
[-1, 1]归一化 39.81 ‘-t 1 -c 1 -g 1/6’
原始数据 81.48 ‘-t 1 -c 1 -g 1/6’

Tab.3

Classification accuracy of different parameter selection"

组号 惩罚系数c 核函数宽度g 分类准确率/%
1 1.00 0.170 0 93.52
2 2.78 0.002 6 38.89
3 0.04 0.620 0 25.93
4 0.23 0.091 0 96.30

Fig.10

Images of fabric for different light angles"

Tab.4

Classification accuracy of different light angles"

光源角度/(°) 0 45 90 135 180 225 270 315
准确率/% 96.30 94.44 85.19 88.89 92.59 88.89 72.22 70.37

Tab.5

Classification accuracy of different light intensities and different incident elevation angles%"

光照强度/lx 光源入射高度角/(°)
50 100 150 200 250 0 27 45 56 63 68
88.89 88.89 94.44 96.30 92.60 24.07 96.30 16.67 9.26 9.26 9.26
[1] YOUNG J N, BEHNAM F D. Assessing wrinkle using image analysis and replicate standard[J]. Textile Research Journal, 1995,65(3):149-157.
doi: 10.1177/004051759506500303
[2] XU B, REED J A. Instrumental evaluation of fabric wrinkle recovery[J]. Journal of The Textile Institute, 1995,86(1):129-135.
doi: 10.1080/00405009508631316
[3] AMIRBAYAT J, ALAGHA M J. Objective assessment of wrinkle recovery by means of laser triangulation[J]. Journal of The Textile Institute, 1996,87(1):349-355.
doi: 10.1080/00405009608659087
[4] KANG T J, CHO D H, KIM S M. A new method for the objective evaluation of fabric surface waviness[J]. AATCC Review, 2002,2(2):38-41.
[5] CHOI C J, KIM H J, JIN Y C, et al. Objective wrinkle evaluation system of fabrics based on 2D FFT[J]. Fibers and Polymers, 2009,10(2):260-265.
doi: 10.1007/s12221-009-0260-0
[6] KANG T J, KIM S C, SUL I H, et al. Fabric Surface Roughness evaluation using wavelet-fractal method[J]. Textile Research Journal, 2005,75(11):751-760.
doi: 10.1177/0040517505058855
[7] 高士忠. 基于灰度共生矩阵的织物纹理分析[J]. 计算机工程与设计, 2008,29(16):4385-4387.
GAO Shizhong. Analysis of fabric texture based on GLCM[J]. Computer Engineering and Design, 2008,29(16):4385-4387.
[8] 陈健敏, 吴兆平, 严灏景. 分形理论在织物褶皱评定中的应用[J]. 中国纺织大学学报, 1999,25(2):34-36.
CHEN Jianmin, WU Zhaoping, YAN Haojing. Application of fractal theory in fabric wrinkle evalua-tion[J]. Journal of China Textile University, 1999,25(2):34-36.
[9] 刘成霞, 甘敏. 织物平整度的特征提取方法对比研究[J]. 丝绸, 2017(3):45-49.
LIU Chengxia, GAN Min. Comparative study of feature extraction for fabric smoothness[J]. Journal of Silk, 2017(3):45-49.
[10] 张宁, 潘如如, 高卫东. 采用图像处理的织物缝纫平整度自动评估[J]. 纺织学报, 2017,38(4):148-149.
ZHANG Ning, PAN Ruru, GAO Weidong. Automatic seam-puckering evaluation using image processing[J]. Journal of Textile Research, 2017,38(4):148-149.
[11] 杨晓波. 基于模糊C均值聚类的织物平整度等级评定[J]. 苏州大学学报(工科版), 2005,25(3):18-21.
YANG Xiaobo. Smoothness evaluation of fabric based of FCMA[J]. Journal of Soochow University (Engineering Science Edition), 2005,25(3):18-21.
[12] RAFAEL C G. 数字图像处理的MATLAB实现[M]. 北京: 清华大学出版社, 2013: 58-59.
RAFAEL C G. MATLAB Implementation of Digital Image Processing [M]. Beijing: Tsinghua University Press, 2013: 58-59.
[13] 郭治成. 基于信号处理描述纹理特征方法[J]. 中国新技术新产品, 2012(21):34.
GUO Zhicheng. A method of texture feature description based on signal processing[J]. China New Technologies and Products, 2012(12):34.
[1] GONG Xue, YUAN Li, LIU Junping, YANG Yali, LIU Muli, KE Zhengtao, YAN Yuchen. Recognition of colored spun fabric interlacing point based on mixed color space and multiple kernel learning [J]. Journal of Textile Research, 2020, 41(05): 58-65.
[2] XU Pinghua, MAO Hailin, SHEN Hongying, DING Xuemei. Visual feature coding and wrinkle assessment of repeatedly laundered fabrics [J]. Journal of Textile Research, 2020, 41(05): 66-71.
[3] . Establishment and application of fabrics attenuated total reflection Fourier transform infrared spectroscopy spectrum library [J]. Journal of Textile Research, 2019, 40(08): 64-68.
[4] . Wet-steaming dyeing prediction model of cotton knitted fabric with reactive dye based on least squares support vector machine [J]. Journal of Textile Research, 2019, 40(07): 169-173.
[5] . Single component textile identification based on continuous projection algorithm and least squares support vector machine [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(08): 46-51.
[6] . Prediction on filtration performance of melt blown nonwoven fabric based on rough set theory and support vector machine [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(06): 142-148.
[7] . Objective evaluation of seaming smoothness for worsted wool garments [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(03): 120-125.
[8] . Visual saliency detection of clothing and accessory design [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(03): 126-131.
[9] . Pilling objective evaluation based Gaussian filtering in wavelet domain [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(09): 155-161.
[10] . Clothing style recognition approach using Fourier descriptors and support vector machines [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(05): 122-127.
[11] . Computer recognition and simulation  of fabric color from matching to standard color chip [J]. Journal of Textile Research, 2016, 37(05): 150-154.
[12] . Automatic recognition and positioning method of fabric slitting zone using one-dimensional Fourier transform [J]. JOURNAL OF TEXTILE RESEARCH, 2016, 37(01): 147-151.
[13] . Variation design and development of patterns of warp figured fabric [J]. Journal of Textile Research, 2015, 36(11): 39-44.
[14] . Study on woven fabric texture using frequency spectrum [J]. Journal of Textile Research, 2015, 36(07): 55-60.
[15] . Evaluation on fabric singeing effect based on change of fabric hairiness characteristics [J]. Journal of Textile Research, 2015, 36(04): 102-106.
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