纺织学报 ›› 2022, Vol. 43 ›› Issue (12): 131-137.doi: 10.13475/j.fzxb.20210702407

• 染整与化学品 • 上一篇    下一篇

基于图像处理的纺织品耐摩擦色牢度评级

安亦锦1,2, 薛文良1,2(), 丁亦1,2, 张顺连3   

  1. 1.东华大学 纺织面料技术教育部重点实验室, 上海 201620
    2.东华大学 纺织学院, 上海 201620
    3.广州检验检测认证集团有限公司, 广东 广州 511447
  • 收稿日期:2021-07-07 修回日期:2022-09-16 出版日期:2022-12-15 发布日期:2023-01-06
  • 通讯作者: 薛文良
  • 作者简介:安亦锦(1997—),女,硕士生。主要研究方向为人工智能在纺织行业的应用。
  • 基金资助:
    国家自然科学基金项目(11804049)

Evaluation of textile color rubbing fastness based on image processing

AN Yijin1,2, XUE Wenliang1,2(), DING Yi1,2, ZHANG Shunlian3   

  1. 1. Key Laboratory of Textile Science & Technology, Ministry of Education, Donghua University, Shanghai 201620, China
    2. College of Textiles, Donghua University, Shanghai 201620, China
    3. Guangzhou Inspection Testing and Certification Group Co., Ltd., Guangzhou, Guangdong 511447, China
  • Received:2021-07-07 Revised:2022-09-16 Published:2022-12-15 Online:2023-01-06
  • Contact: XUE Wenliang

摘要:

为解决目前纺织品色牢度人工评级方式的主观性和繁重工作量,结合深度学习与传统纺织检测,以纺织品检测中的纺织品色牢度评级为对象,研究基于图像处理和深度学习的智能评级创新方法。针对场景与问题,选择利用图像处理技术进行采样图像的预处理和分割,在小样本、多分类的实际条件下搭建数据库,利用深度学习完成对摩擦沾色试样色牢度的迅速评级。结果表明,所选择的图像处理技术对图像的处理效果良好,对后续深度学习准确率的提高有辅助效果;深度学习对耐摩擦沾色试样色牢度的评级准确率达到87.5%,高效、客观且准确率高,实现评级操作简易化,利用神经网络达到代替人眼评级过程,提高准确度和改善目前方法的不足。

关键词: 图像处理, 多分类, 深度学习, 纺织品色牢度评级, 耐摩擦沾色色牢度

Abstract:

In order to objectively evaluate textile color fastness and eliminate the heavy workload in manual color evaluation, this paper reports on research into evaluation of textile color rubbing fastness using image processing technology. In view of the scenes and problems, image processing technology was used to treat and segment the sampled images. A database was built for small samples from multiple categories, and deep learning was used to achieve the rapid rating of the color fastness of rubbed samples which was necessary for stain removal. The results show that the selected image processing technique works well and has an auxiliary effect on the subsequent improvement of the accuracy of deep learning. The rating accuracy reaches 87.5%, which is efficient, objective and accurate. The rating operation was simplified, and the neural network was used to replace the human eye rating process, improving the accuracy and overcoming the shortcomings of the current method.

Key words: image processing, multi-category, deep learning, textile color fastness rating, color rubbing fastness

中图分类号: 

  • TS197

图1

图像的读取"

图2

求取结果图"

图3

填充图像的透视"

图4

图像分割结果"

图5

测试集结果图"

图6

误差样本图"

[1] 于伟东. 纺织材料学[M]. 北京: 中国纺织出版社, 2006:5.
YU Weidong. Textile materials science[M]. Beijing: China Textile & Apparel Press, 2006:5.
[2] 魏金玉, 商素平. 谈如何保持色牢度评级目光的准确和稳定[J]. 科技前沿, 2008(4):56-57.
WEI Jinyu, SHANG Suping. Talk about how to maintain the accuracy and stability of the color fastness ratings[J]. Frontiers of Science and Technology, 2008(4):56-57.
[3] 柳淑英. 纺织品—色牢度实验A02部分:颜色变化评定灰色标度[J]. 标准化报道, 1996(6):62-63.
LIU Shuying. Textiles-color fastness experiment part A02: evaluation of gray scale for color cange[J]. Standardization Report, 1996(6): 62-63.
[4] 章秋平. GB/T 3920与AATCC 8试验方法之比较[J]. 纺织标准与质量, 2007(1):40-41.
ZHANG Qiuping. Comparison of GB/T 3920 and AATCC 8 test methods[J]. Textile Standards and Quality, 2007(1): 40-41.
[5] 孔凡明, 张广丽. 色差定量分析与色牢度仪器评级的探讨[J]. 中国纤检, 2004(11):18-19,26.
KONG Fanming, ZHANG Guangli. Quantitative analysis of color difference and discussion of color fastness instrument rating[J]. China Fiber Inspection, 2004(11):18-19,26.
[6] 刘蒙蒙, 杨汝慧, 李姗姗. 纺织品耐摩擦色牢度试验方法改进研究[J]. 山东纺织科技, 2020, 61(5):31-32.
LIU Mengmeng, YANG Ruhui, LI Shanshan. Research on improvement of textile color fastness to rubbing[J]. Shandong Textile Science and Technology, 2020, 61(5): 31-32.
[7] 张向丽, 刘锦瑞, 孙丽霞, 等. 纺织品色牢度自动评级系统性能的研究[J]. 现代纺织技术, 2019, 27(6):86-90.
ZHANG Xiangli, LIU Jinrui, SUN Lixia, et al. Research on the performance of textile color fastness automatic rating system[J]. Advanced Textile Technology, 2019, 27(6): 86-90.
[8] 胡梦坤, 岑琴, 郭霞. 色牢度目测评级与仪器评级的探讨[J]. 农业科技与装备, 2019(2):84-85.
HU Mengkun, CEN Qin, GUO Xia. Discussion on visual evaluation of color fastness and instrument evaluation[J]. Agricultural Science and Technology and Equipment, 2019(2): 84-85.
[9] 张勇, 车江宁. 纺织品色差和色牢度的数码影像技术评级[J]. 印染, 2011, 37(21):37-40.
ZHANG Yong, CHE Jiangning. Digital imaging technology rating of textile color difference and color fastness[J]. China Dyeing & Finishing, 2011, 37(21): 37-40.
[10] 邵金鑫, 张宝昌, 曹继鹏. 基于图像处理与深度学习方法的棉纤维梳理过程纤维检测识别技术[J]. 纺织学报, 2020, 41(7):40-46.
SHAO Jinxin, ZHANG Baochang, CAO Jipeng. Fiber detection and recognition technology for cotton fiber carding process based on image processing and deep learning methods[J]. Journal of Textile Research, 2020, 41(7): 40-46.
[11] 朱安民, 张艺, 李观强. 基于计算机视觉的纺织品色牢度检测[J]. 深圳大学学报(理工版), 2018, 35(4):420-425.
ZHU Anmin, ZHANG Yi, LI Guanqiang. Textile color fastness detection based on computer vision[J]. Journal of Shenzhen University (Science and Technology Edition), 2018, 35(4): 420-425.
[12] 孙芳. 纺织品色牢度及色差智能判别装置的可行性研究[J]. 中国纤检, 2017(10):86-87.
SUN Fang. The feasibility study of an intelligent discrimination device for textile color fastness and color difference[J]. China Fiber Inspection, 2017(10): 86-87.
[13] 张思萌. 印染织物色牢度测试过程中应注意的问题[J]. 四川纺织科技, 2002(6):47.
ZHANG Simeng. Issues that should be paid attention to in the process of testing the color fastness of printed and dyed fabrics[J]. Sichuan Textile Technology, 2002(6):47.
[14] 宋丛珊. 纺织品色牢度评定分析系统的开发与探讨[J]. 湖北农机化, 2012(4):55-57.
SONG Congshan. Development and discussion of textile color fastness evaluation and analysis system[J]. Hubei Agricultural Mechanization, 2012(4):55-57.
[15] 孙飞, 张胜文, 方喜峰. 纺织品色牢度计算机辅助测试系统的研制[J]. 自动化与仪表, 2007(2):70-73.
SUN Fei, ZHANG Shengwen, FANG Xifeng. Development of a computer-aided testing system for textile color fastness[J]. Automation and Instrumentation, 2007(2): 70-73.
[16] 刘锦瑞, 袁园园, 张向丽, 等. 纺织品色牢度智能评级系统的研制[J]. 棉纺织技术, 2019, 47(5):41-44.
LIU Jinrui, YUAN Yuanyuan, ZHANG Xiangli, et al. Development of an intelligent rating system for textile color fastness[J]. Cotton Textile Technology, 2019, 47(5): 41-44.
[17] FENG Chung, KUO Jeffrey, SHIH Chun-Yang, et al. Color and pattern analysis of printed fabric by an unsupervised clustering method[J]. Textile Research Journal, 2005, 75(1):9-12.
doi: 10.1177/004051750507500103
[18] SHIH Peichung, LIU Chengjun. Comparative assessment of content-based face image retrieval in different color spaces[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2005, 19(7):873-893.
doi: 10.1142/S0218001405004381
[19] WEE G Alvin, DELWIN T Lindsey, KUO Shanglun, et al. Color accuracy of commercial digital cameras for use in dentistry[J]. Dental Materials, 2005, 22(6):553-559.
doi: 10.1016/j.dental.2005.05.011
[20] XU Dongliang, TIAN Zhihong, LAI Rufeng, et al. Deep learning based emotion analysis of microblog texts[J]. Information Fusion, 2020, 64:69-71.
[21] SALMON Landi. Comment on ″Kubelka-Munk function″-Ceram. int. 47 (2021) 8218-8227 and ″Kubelka-Munk equation″-Ceram. int. 47 (2021) 13980-13993[J]. Ceramics International, 2021, 47(19):28055-28055.
doi: 10.1016/j.ceramint.2021.06.103
[22] ALI Moussa. Textile color formulation using linear programming based on Kubelka-Munk and Duncan theories[J]. Color Research & Application, 2021, 46(5): 1046-1056.
[23] WU Jie, TANG Tang, CHEN Ming, et al. A Study on adaptation lightweight architecture based deep learning models for bearing fault diagnosis under varying working conditions[J]. Expert Systems with Applications, 2020, 160:53-55.
[24] MEIJS Midas, MEIJER Frederick J A, PROKOP Mathias, et al. Image-level detection of arterial occlusions in 4D-CTA of acute stroke patients using deep learning[J]. Medical image analysis, 2020, 66:112-114.
[25] 王彬, 高嘉平, 司耸涛. 基于卷积神经网络的图像分类及应用[J]. 电子与封装, 2021, 21(5):76-80.
WANG Bin, GAO Jiaping, SI Songtao. Image classification and application based on convolutional neural network[J]. Electronics and Packaging, 2021, 21(5): 76-80.
[26] 钱立辉, 王斌, 郑云飞, 等. 基于图像深度预测的景深视频分类算法[J]. 浙江大学学报(理学版), 2021, 48(3):282-288.
QIAN Lihui, WANG Bin, ZHENG Yunfei, et al. Depth-of-field video classification algorithm based on image depth prediction[J]. Journal of Zhejiang Univer-sity (Science Edition), 2021, 48(3): 282-288.
[27] 刘颖, 车鑫. 基于图网络优化及标签传播的小样本图像分类算法[J/OL]. 信号处理:1-11[2021-05-26]. http://kns.cnki.net/kcms/detail/11.2406.TN.20210511.1826.014.html.
LIU Ying, CHE Xin. Small sample image classification algorithm based on graph network optimization and label propagation[J/OL]. Signal Processing: 1-11 [2021-05-26]. http://kns.cnki.net/kcms/detail/11.2406.TN.20210511.1826.014.html.
[1] 张东剑, 甘学辉, 杨崇倡, 韩阜益, 刘香玉, 谈渊, 廖壑, 王松林. 纺丝过程中非接触式纤维张力检测技术研究进展[J]. 纺织学报, 2022, 43(11): 188-194.
[2] 陈金广, 李雪, 邵景峰, 马丽丽. 改进YOLOv5网络的轻量级服装目标检测方法[J]. 纺织学报, 2022, 43(10): 155-160.
[3] 袁嫣红, 曾洪铭, 茅木泉. 基于图像处理的选针器检测系统[J]. 纺织学报, 2022, 43(10): 176-182.
[4] 邓中民, 胡灏东, 于东洋, 王文, 柯薇. 结合图像频域和空间域的纬编针织物密度检测方法[J]. 纺织学报, 2022, 43(08): 67-73.
[5] 马运娇, 王蕾, 潘如如, 高卫东. 基于平面镜成像的纱线条干三维合成校准方法[J]. 纺织学报, 2022, 43(07): 55-59.
[6] 周其洪, 彭轶, 岑均豪, 周申华, 李姝佳. 基于机器视觉的细纱接头机器人纱线断头定位方法[J]. 纺织学报, 2022, 43(05): 163-169.
[7] 张荣根, 冯培, 刘大双, 张俊平, 杨崇倡. 涤纶工业长丝毛丝在线检测系统的研究[J]. 纺织学报, 2022, 43(04): 153-159.
[8] 熊晶晶, 杨雪, 苏静, 王鸿博. 基于图像技术的织物导湿性能测试方法[J]. 纺织学报, 2021, 42(12): 70-75.
[9] 江慧, 马彪. 基于服装风格的款式相似度算法[J]. 纺织学报, 2021, 42(11): 129-136.
[10] 吕文涛, 林琪琪, 钟佳莹, 王成群, 徐伟强. 面向织物疵点检测的图像处理技术研究进展[J]. 纺织学报, 2021, 42(11): 197-206.
[11] 杨争妍, 薛文良, 张传雄, 丁亦, 马颜雪. 基于生成式对抗网络的用户下装搭配推荐[J]. 纺织学报, 2021, 42(07): 164-168.
[12] 夏旭文, 孟朔, 潘如如, 高卫东. 基于改进帧间差分法的经纱撞筘拥纱在线检测[J]. 纺织学报, 2021, 42(06): 91-96.
[13] 江燕婷, 严庆帅, 辛斌杰, 高琮, 施楣梧. 纺织品单向导水性能测试方法分析[J]. 纺织学报, 2021, 42(05): 51-58.
[14] 李东洁, 郭帅, 杨柳. 基于改进图像阈值分割算法的纱线疵点检测[J]. 纺织学报, 2021, 42(03): 82-88.
[15] 唐千惠, 王蕾, 高卫东. 基于图像处理的织物保形性检测[J]. 纺织学报, 2021, 42(03): 89-94.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!