Journal of Textile Research ›› 2020, Vol. 41 ›› Issue (05): 66-71.doi: 10.13475/j.fzxb.20190601606

• Textile Engineering • Previous Articles     Next Articles

Visual feature coding and wrinkle assessment of repeatedly laundered fabrics

XU Pinghua1,2(), MAO Hailin3, SHEN Hongying4, DING Xuemei4   

  1. 1. School of Fashion Design & Engineering, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, China
    2. Clothing Engineering Research Center of Zhejiang Province, Hangzhou, Zhejiang 310018, China
    3. Jiangsu Yihai Clothing Co., Ltd., Nantong, Jiangsu 226007, China
    4. College of Fashion and Design,Donghua University, Shanghai 200051, China
  • Received:2019-06-10 Revised:2020-01-22 Online:2020-05-15 Published:2020-06-02

Abstract:

In order to improve the consistency between subjective and objective ratings for the repeatedly laundered fabrics, an automatic method of wrinkling assessment based on visual feature coding and multi-classification support vector machine (SVM) was proposed. 450 representative wrinkled fabric images including 6 standard samples were selected as the training set. In addition, the human visual focusing mechanism was simulated, and the sparse coding method was utilized to extract the feature vector chain codes from 9 half-level image sub-databases. 200 wrinkled images as testing samples in this experiment were classified by linear multi-classification SVM. Results show that consistency between subjective and objective rating reaches 95.1%, rating precision is 0.1 and rating speed for single sample is less than 6 seconds, which meet the current commercial rating requirement for effective evaluations of fabric finishing, detergent products and care equipment.

Key words: smoothness appearance, visual feature, sparse coding, subjective and objective rating, fabric appearance

CLC Number: 

  • TS107.4

Fig.1

Hardware of image acquisition"

Fig.2

Partial fabric sample images. (a) Grade 1;(b) Grade 1.5; (c) Grade 2 (d) Grade 2.5;(e) Grade 3; (f) Grade 3.5; (g) Grade 4;(h) Grade 4.5; (i) Grade 5"

Fig.3

Pipeline of D-SIFT feature extraction"

Fig.4

Visual feature coding vocabulary. (a) Grade 1; (b) Grade 1.5; (c) Grade 2; (d) Grade 2.5; (e) Grade 3; (f) Grade 3.5; (g) Grade 4; (h) Grade 4.5; (i) Grade 5"

Fig.5

Output of sub-obj rating consistency"

[1] 徐志凤, 范伟超, 刘尊峰, 等. 滚筒洗涤中护理剂对织物洗后性能的影响研究[J]. 中国洗涤用品工业, 2018 (4):34-40.
XU Zhifeng, FAN Weichao, LIU Zunfeng, et al. The influence of fabric softener on textile properties using a domestic front-loading washer[J]. China Cleaning Industry, 2018(4):34-40.
[2] YU X C, FAN W C, WEI Y H, et al. The wrinkling mechanism of woven cotton fabrics during domestic tumble drying[J]. Drying Technology, 2017,36(6):1-9.
[3] SHIN EH, SEO M H, JEON B S, et al. Wrinkle components analysis using AATCC smoothness appearance replica[J]. Textile Science & Engineering, 2012,49(1):26-34.
[4] 袁建荣, 李兆君, 吴雄英, 等. 家庭滚筒洗衣机洗涤温度对机织物外观平整性的影响[J]. 纺织学报, 2014,35(7):74-78.
YUAN Jianrong, LI Zhaojun, WU Xiongying, et al. Effect of washing temperature on smoothness appearance of woven fabrics during domestic tumble laundering[J]. Journal of Textile Research, 2014,35(7):74-78.
[5] 徐平华, 丁雪梅, 王荣武, 等. 洗后织物外观平整度客观评级中的若干问题[J]. 纺织学报, 2014,35(12):159-164.
XU Pinghua, DING Xuemei, WANG Rongwu, et al. Exploration of several issues about evaluation of fabric smoothness appearance after laundering[J]. Journal of Textile Research, 2014,35(12):159-164.
[6] YU W R, XU B G. A sub-pixel stereo matching algorithm and its applications in fabric imaging[J]. Machine Vision and Applications, 2009,20(4):261-270.
[7] LIU C X. New method of fabric wrinkle measurement based on image processing[J]. Fibers & Textiles in Eastern Europe, 2014,103(1):51-55.
[8] YAMAZAKI K, INABA M. Image-based classification of everyday clothing based on cloth-overlaps, wrinkles, and fabrics[J]. Transactions of the Society of Instrument & Control Engineers, 2013,49(7):661-669.
[9] JAVUER S B, JOAQUIN B S, RUBEN P L, et al. Garment smoothness appearance evaluation through computer vision[J]. Textile Research Journal, 2012,82(3):299-309.
[10] SUN J J, YAO M, XU B G, et al. Fabric wrinkle characterization and classification using modified wavelet coefficients and support-vector-machine classifiers[J]. Textile Research Journal, 2011,81(9):902-913.
[11] XIN B J, LI Y M, QIU J X. Texture modelling of fabric appearance evaluation based on image analysis[J]. Fibres & Textiles in Eastern Europe, 2012,91(2):48-52.
[12] XU P H, DING X M, WANG R W, et al. Feature-based 3D reconstruction of fabric by binocular stereo-vision[J]. Journal of The Textile Institute, 2016,107(1):12-22.
[13] GEOFFREY E H, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786):504-507.
pmid: 16873662
[14] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110.
doi: 10.1023/B:VISI.0000029664.99615.94
[15] KARAKASIS E G, AMABATIADIS A, GASTERATOS A, et al. Image moment invariants as local features for content based image retrieval using the Bag-of-Visual-Words model[J]. Pattern Recognition Letters, 2015,55:22-27.
doi: 10.1016/j.patrec.2015.01.005
[16] WANG J, YANG J, KAI Y, et al. Locality-constrained linear coding for image classification [C]//23th IEEE conference on computer vision and pattern recognition. San Francisco: Computer Vision and Pattern Recognition Ltd, 2010: 3360-3367.
[17] 刘国军, 高丽霞, 陈丽奇. 广义平均的全参考型图像质量评价池化策略[J]. 光学精密工程, 2017,25(3):742-748.
LIU Guojun, GAO Lixia, CHEN Liqi. Pooling strategy for full-reference IQA via general means[J]. Optics and Precision Engineering, 2017,25(3):742-748.
doi: 10.3788/OPE.
[1] . Effect of washing temperature on smoothness appearance of woven fabric during domestic tumble laundering [J]. JOURNAL OF TEXTILE RESEARCH, 2014, 35(7): 74-0.
[2] CHEN Huimin;GU Hongbo;ZHANG Weiyuan. Digital analysis of fabric smoothness appearance on point-sampled model [J]. JOURNAL OF TEXTILE RESEARCH, 2008, 29(9): 38-42.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!