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

• Dyeing and Finishing & Chemicals • 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:2019-06-29 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: 

  • TP391.7

Fig.1

Vein pattern elements. (a) Circle; (b) Rice;(c) Column; (d) Shell;(e) Rhombus;(f) Tortoise shell;(g) Triangle;(h) Crescent;(i) Four-leaf;(j) Fish-scale;(k) Mountain;(l) Three-section"

Fig.2

Extracting vein pattern elements from blue calico. (a) Plant vein pattern; (b) Contours with serial number;(c) Sub images of vein pattern elements"

Fig.3

Network model structure of improved CifarNet"

Fig.4

Variation of testing accuracy rate (a), training loss and testing loss (b) in process of training"

Tab.1

Performance comparison of 4 classification methods"

方法 平均分类准确率/% 训练时间/min
LeNet-5 97.32 12.3
CifarNet 98.03 22.9
SVM 99.12 26.6
本文方法 99.61 28.1

Tab.2

Recognition rates of four methods%"

基元类别 LeNet-5 CifarNet SVM 本文方法
圆形纹 97 97 97 97
米粒纹 94 96 97 98
柱形纹 96 97 97 98
贝壳纹 96 98 98 97
菱形纹 98 98 99 100
龟背纹 96 96 97 97
三角纹 99 99 99 100
月形纹 96 98 99 100
四叶纹 96 98 97 97
鱼鳞纹 99 99 100 100
山形纹 99 99 100 100
三节纹 96 97 98 98
平均值 96.83 97.67 98.17 98.5
[1] 奚燕锋, 梁惠娥. 南通蓝印花布的历史和现状以及发展优势思索[J]. 纺织学报, 2012,33(2):98-103.
XI Yanfeng, LIANG Hui'e. Nantong's blue print cloth: yesterday, today, and tomorrow[J]. Journal of Textile Research, 2012,33(2):98-103.
[2] 徐舫. 蓝印花布纹样与丝巾图案设计[J]. 丝绸, 2012,49(8):43-47.
XU Fang. The pattern design of blue calico and silk scarf[J]. Journal of Silk, 2012,49(8):43-47.
[3] 李学伟. 齐鲁民间蓝印花布的风格特征与传承发展[J]. 纺织学报, 2012,33(3):113-118.
LI Xuewei. Characteristics and inheritance of Qilu folk blue printed cloth[J]. Journal of Textile Research, 2012,33(3):113-118.
[4] 陆晓云. 南通非物质文化遗产的艺术特征[J]. 南通大学学报(社会科学版), 2014,30(2):87-92.
LU Xiaoyun. Artistic features of intangible cultural heritages in Nantong[J]. Journal of Nantong Univer-sity (Social Science Edition), 2014,30(2):87-92.
[5] 鲍小龙, 刘月蕊. 基于数码技术的蓝印花布图案创新设计研究[J]. 纺织学报, 2013,34(5):100-106.
BAO Xiaolong, LIU Yuerui. Innovative design of blue calico based on digital technology[J]. Journal of Textile Research, 2013,34(5):100-106.
[6] 王宏付, 姜丽丽. 蓝印花布花版纹样与剪纸纹样的比较分析[J]. 纺织学报, 2013,34(8):120-126.
WANG Hongfu, JIANG Lili. Comparative analysis of paper-cut design and stencil design of blueprint cloth[J]. Journal of Textile Research, 2013,34(8):120-126.
[7] 姜丽丽, 王宏付. 蓝印花布与木版年画纹样的比较分析[J]. 丝绸, 2013,50(1):43-48.
JIANG Lili, WANG Hongfu. Comparative analysis on patterns of blue printed cloth and wood engraving new year pictures[J]. Journal of Silk, 2013,50(1):43-48.
[8] ZHOU Bolei, LAPEDRIZA Agata, XIAO Jianxiong, et al. Learning deep features for scene recognition using places database [C]//International conference on neural information processing systems (NIPS). NewYork: NIPS, 2014:487-495.
[9] YANN LeCun, YOSHUA Bengio. Geoffrey hinton deep learning[J]. Nature, 2015,521:436-444.
doi: 10.1038/nature14539 pmid: 26017442
[10] WEI Yuanwang, SHEN Wei, ZENG Dan, et al. Multi-oriented text detection from natural scene images based on a CNN and pruning non-adjacent graph edges[J]. Signal Processing: Image Communication, 2018,64:89-98.
doi: 10.1016/j.image.2018.02.016
[11] 张婷, 李玉鑑, 胡海鹤, 等. 基于跨连卷积神经网络的性别分类模型[J]. 自动化学报, 2016,42(6):858-865.
doi: 10.16383/j.aas.2016.c150658
ZHANG Ting, LI Yujian, HU Haihe, et al. A gender classification model based on cross-connected convolutional neural networks[J]. Acta Automatica Sinica, 2016,42(6):858-865.
doi: 10.16383/j.aas.2016.c150658
[12] 杜剑, 胡炳樑, 张周锋. 基于卷积神经网络与显微高光谱的胃癌组织分类方法研究[J]. 光学学报, 2018. DOI: 10.3788/AOS201838.0617001.
DU Jian, HU Bingliang, ZHANG Zhoufeng. Gastric carcinoma classification based on convolutional neural network and micro-hyperspectral imaging[J]. Acta Optica Sinica, 2018, DOI: 10.3788/AOS201838.0617001.
[13] RONAO Charissa Ann, CHO Sung Bae. Human activity recognition with smartphone sensors using deep learning neural networks[J]. Expert Systems with Applications, 2016,59:235-244.
doi: 10.1016/j.eswa.2016.04.032
[14] 杜剑, 胡炳樑, 刘永征, 等. 基于卷积神经网络与光谱特征的夏威夷果品质鉴定研究[J]. 光谱学与光谱分析, 2018,38(5):1514-1519.
DU Jian, HU Bingliang, LIU Yongzheng, et al. Study on quality identification of macadamia nut based on convolutional neural networks and spectral features[J]. Spectroscopy and Spectral Analysis, 2018,38(5):1514-1519.
[15] 刘德营, 王家亮, 林相泽, 等. 基于卷积神经网络的白背飞虱识别方法[J]. 农业机械学报, 2018,49(5):51-56.
LIU Deying, WANG Jialiang, LIN Xiangze, et al. Automatic identification method for sogatella furcifera based on convolutional neural network[J]. Journal of Agricultural Machinery, 2018,49(5):51-56.
[16] 孙俊, 何小飞, 谭文军, 等. 空洞卷积结合全局池化的卷积神经网络识别作物幼苗与杂草[J]. 农业工程学报, 2018,34(11):159-165.
SUN Jun, HE Xiaofei, TAN Wenjun, et al. Recognition of crop seedling and weed recognition based on dilated convolution and global pooling in CNN[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(11):159-165.
[17] 景军锋, 范晓婷, 李鹏飞, 等. 应用深度卷积神经网络的色织物缺陷检测[J]. 纺织学报, 2017,38(2):68-74.
JING Junfeng, FAN Xiaoting, LI Pengfei, et al. Yarn-dyed fabric defect detection based on deep-convolutional neural network[J]. Journal of Textile Research, 2017,38(2):68-74.
[18] 王飞, 靳向煜. 应用卷积网络及深度学习理论的羊绒与羊毛鉴别[J]. 纺织学报, 2017,38(12):150-156.
WANG Fei, JIN Xiangyu. Identification of cashmere and wool based on convolutional neuron networks and deep learning theory[J]. Journal of Textile Research, 2017,38(12):150-156.
[19] 何晓昀, 韦平, 张林, 等. 基于深度学习的籽棉中异性纤维检测方法[J]. 纺织学报, 2018,39(6):131-135.
HE Xiaoyun, WEI Ping, ZHANG Lin, et al. Detection method of foreign fibers in seed cotton based on deep-learning[J]. Journal of Textile Research, 2018,39(6):131-135.
[20] 王雯雯, 高畅, 刘基宏. 应用卷积神经网络的细纱断纱锭位识别[J]. 纺织学报, 2018,39(6):136-141.
WANG Wenwen, GAO Chang, LIU Jihong. Position recognition of spinning yarn breakage based on convolution neural network[J]. Journal of Textile Research, 2018,39(6):136-141.
[21] 汪珊娜, 张华熊, 康锋. 基于卷积神经网络的领带花型情感分类[J]. 纺织学报, 2018,39(8):117-123.
WANG Shanna, ZHANG Huaxiong, KANG Feng. Emotion classification of necktie pattern based on convolution neural network[J]. Journal of Textile Research, 2018,39(8):117-123.
[22] ALEX Krizhevsky, GEOFFREY Hinton. Learning multiple layers of features from tiny images[D]. Toronto:University of Toronto, 2009:3-21.
[23] 贾小军, 邓洪涛, 滕姿, 等. 应用轮廓线拟合提取蓝印花布图案基元[J]. 纺织学报, 2018,39(8):50-57.
JIA Xiaojun, DENG Hongtao, TENG Zi, et al. Using contour fitting to extract image elements for blue calico[J]. Journal of Textile Research, 2018,39(8):50-57.
[24] KETKAR Nikhil. Deep learning with python[M]. Berkeley, CA: Apress, 2017:113-132.
[25] SATURNINO Maldonado-Bascon, SERGIO Lafuente-Arroyo, PEDRO Gil-Jimenez, et al. Road-sign detection and recognition based on support vector machines[J]. IEEE Transactions on Intelligent Transportation Systems, 2007,8(2):264-278.
doi: 10.1109/TITS.2007.895311
[1] WANG Yiwen, LUO Ronglei, KANG Yuzhe. Automatic measurement of key dimensions for Han-style costumes based on use of convolutional neural network [J]. Journal of Textile Research, 2020, 41(12): 124-129.
[2] SHAO Jinxin, ZHANG Baochang, CAO Jipeng. Fiber detection and recognition technology in cotton fiber carding process based on image processing and deep learning [J]. Journal of Textile Research, 2020, 41(07): 40-46.
[3] WANG Zexia, CHEN Ge, CHEN Zhenzhong. Surface defect recognition of chemical fiber yarn packages based on improved convolutional neural network [J]. Journal of Textile Research, 2020, 41(04): 39-44.
[4] WANG Xiaohua, YAO Weiming, WANG Wenjie, ZHANG Lei, LI Pengfei. Sewing gesture recognition based on improved YOLO deep convolutional neural network [J]. Journal of Textile Research, 2020, 41(04): 142-148.
[5] ZHOU Jiu, LU Shuangyi. Design principal and practice of layered-combination mode for digital jacquard fabric [J]. Journal of Textile Research, 2020, 41(02): 58-63.
[6] 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.
[7] TAO Chen, DUAN Yafeng, XU Rongrong, YANG Jianping, ZHOU Jiu. Modeling and reconstruction of blue calico patterns [J]. Journal of Textile Research, 2019, 40(03): 153-159.
[8] . Extract of image elements for blue calico based on contour fitting [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(08): 150-157.
[9] . Yarn-dyed fabric defect detection based on deep-convolutional neural network [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(02): 68-74.
[10] . Innovative design of blue calico based on digital technology [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(5): 100-106.
[11] 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   
No Suggested Reading articles found!