Journal of Textile Research ›› 2020, Vol. 41 ›› Issue (01): 110-117.doi: 10.13475/j.fzxb.20180906008

Previous Articles     Next Articles

Elements classification of vein patterns using convolutional neural networks for blue calico

JIA Xiaojun1, YE Lihua1, DENG Hongtao2, LIU Zihao1, LU Fengjie3   

  1. 1. College of Mathematics, Physics and Information Engineering, Jiaxing University, Jiaxing, Zhejiang 314001, China;
    2. College of Design, Jiaxing University, Jiaxing, Zhejiang 314001, China; 3. Zhejiang Hanpu Power Technology Co., Ltd., Jiaxing, Zhejiang 314300, China
  • Received:2018-09-25 Revised:2019-10-27 Online:2020-01-15 Published:2020-01-14

Abstract:

To inherit and innovate the traditional blue calico vein patterns making use of the digital technology, the image elements constituting blue calico vein patterns were extracted to form a structured database for vein pattern elements. A classification method based on convolutional neural networks was proposed. The pattern elements were firstly extracted from the captured 128 images of blue calico to form an image sample database with a total of 21 212 images. Secondly, 80% of image samples in the database were randomly selected as the training set and the rest 20% as the testing set. The training samples were convoluted by a 5 × 5 convolutional kernel size, and the obtained feature maps were pooled. After computing through 3 convoluting layers, 3 pooling layers and 2 full connection layers, 12 classification types were obtained by using Softmax classifier. Eventually, the optimal network model parameters were acquired and ideal classification results were obtained through deep learning of the image element samples. The experimental results show that the 12 types of vein pattern elements of blue calico, produced by the convolutional neural networks model, are proved to be with an average accuracy of 99. 61%, and detection accuracy of 98. 5%. This work provides new ideas for studying blue calico vein patterns.

Key words: blue calico, classification of vein pattern elements, convolutional neural network, digital textile

CLC Number: 

[1] SUN Jie, DING Xiaojun, DU Lei, LI Qinman, ZOU Fengyuan. Research progress of fabric image feature extraction and retrieval based on convolutional neural network [J]. Journal of Textile Research, 2019, 40(12): 146-151.
[2] . Modeling and reconstruction of blue calico patterns [J]. Journal of Textile Research, 2019, 40(03): 153-159.
[3] . Extract of image elements for blue calico based on contour fitting [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(08): 150-157.
[4] . Yarn-dyed fabric defect detection based on deep-convolutional neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(02): 68-74.
[5] . Innovative design of blue calico based on digital technology [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(5): 100-106.
[6] PAN Chunyu;GAO Weidong. Applications of happening color in Chinese blue calico’s innovative design [J]. JOURNAL OF TEXTILE RESEARCH, 2009, 30(01): 88-90.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] . [J]. JOURNAL OF TEXTILE RESEARCH, 1982, 3(09): 4 .
[2] . [J]. JOURNAL OF TEXTILE RESEARCH, 1982, 3(09): 10 .
[3] . [J]. JOURNAL OF TEXTILE RESEARCH, 1984, 5(08): 47 -48 .
[4] PAN Xu-wei;GU Xin-jian;HAN Yong-sheng;CHENG Yao-dong. Research on quick response of apparel supply chain for collaboration[J]. JOURNAL OF TEXTILE RESEARCH, 2006, 27(1): 54 -57 .
[5] JIANG Ying;LIU Guo-lian. Study on consumer′s perceptual demand for the image of T-shirt[J]. JOURNAL OF TEXTILE RESEARCH, 2006, 27(2): 98 -100 .
[6] DAI Jian-guo;CHEN Min-zhi;HE Ying. Draping technology and the applicability analysis[J]. JOURNAL OF TEXTILE RESEARCH, 2006, 27(3): 117 -120 .
[7] . [J]. JOURNAL OF TEXTILE RESEARCH, 2004, 25(03): 84 -86 .
[8] . [J]. JOURNAL OF TEXTILE RESEARCH, 2003, 24(06): 35 -36 .
[9] . [J]. JOURNAL OF TEXTILE RESEARCH, 2003, 24(06): 109 -620 .
[10] . [J]. JOURNAL OF TEXTILE RESEARCH, 2004, 25(03): 76 -77 .