纺织学报 ›› 2019, Vol. 40 ›› Issue (01): 153-158.doi: 10.13475/j.fzxb.20171206406

• 管理与信息化 • 上一篇    下一篇

应用Canny算子的织物疵点检测改进算法

胡克满1,2, 罗少龙1(), 胡海燕3   

  1. 1.宁波职业技术学院 电子信息工程学院, 浙江 宁波 315800
    2.澳门科技大学 资讯科技学院, 澳门 999078
    3.宁波职业技术学院 科技与产学合作处, 浙江 宁波 315800
  • 收稿日期:2017-12-29 修回日期:2018-09-26 出版日期:2019-01-15 发布日期:2019-01-18
  • 通讯作者: 罗少龙
  • 作者简介:胡克满(1980—),男,博士生。主要研究方向为计算机视觉、机器学习。
  • 基金资助:
    国家自然科学基金项目(11771226);浙江省教育厅科研项目(Y201738411)

Improved algorithm for fabric defect detection based on Canny operator

HU Keman1,2, LUO Siolong1(), HU Haiyan3   

  1. 1. Department of Electronics & Information Engineering, Ningbo Polytechnic, Ningbo, Zhejiang 315800, China
    2. Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China
    3. Technology and Academia-Industry Cooperation Office, Ningbo Polytechnic, Ningbo, Zhejiang 315800, China
  • Received:2017-12-29 Revised:2018-09-26 Online:2019-01-15 Published:2019-01-18
  • Contact: LUO Siolong

RichHTML

6

PDF (PC)

200

摘要：

为克服当前Canny算子在织物疵点边缘检测中存在的阈值设定、滤波参数选择等自适应问题,提出一种基于Canny算子的改进算法。通过分析不同种类的织物疵点特征,选择不同参数的高斯滤波器,对织物疵点图像进行滤波处理;采用自适应形式获取图像边缘信息的阈值,避免了因阈值取值过高或过低而无法获得较好织物疵点的边缘信息的问题,同时还可根据不同织物疵点类型选择不同的滤波参数。结果表明,改进后的Canny算法可有效地检测到织物疵点的边缘细节,具有较好的自适应能力,并且提高了算法的有效性。同时对典型的织物疵点进行检测并与传统算法比较,其检测效果更优。

关键词: Canny算子, 自适应, 织物疵点, 滤波参数, 边缘信息

Abstract:

In order to solve the self-adaption problem that current Canny operator needs to set threshold and to choose the filtering parameters in the fabric defect edge detection, an improved algorithm based on the original Canny operator was proposed. Firstly different filter parameters were chosen according to the type of the fabric flaw, and then self-adaption was used to obtain the threshold and the parameters of the filter, which avoids the wrong choosing of threshold leading to the lack or redundant edge information, and different filter parameters were chosen according to the type of the fabric flaw. The results showed that the improved Canny algorithm can detect the edge detail of fabric defects, and has good self-adaption capability. Compared to the conventional algorithm, the improved algorithm has better detection results.

Key words: Canny operator, self-adaption, fabric defect, parameter of filter, edge detail

中图分类号: 

  • TP391.4

图1

高斯滤波器 (a) 3-D of Gauss filter; (b) 2D of Gauss filter"

图2

滤波处理图 (a)Original image; (b) Filtered image"

图3

水平方向能量响应值"

图4

垂直能量响应值"

图5

高阈值400检测结果 (a)Tight warp;(b)Loose warp;(c) Floating selvedge; (d)Result of tight warp; (e)Result of loose warp; (f)Result of floating selvedge"

图6

高阈值50检测结果 (a)Tight warp; (b)Loose warp; (c) Floating selvedge; (d)Result of tight warp; (e)Result of loose warp; (f)Result of floating selvedge"

图7

本文算法结果 (a)Original image; (b)Gray image; (c) Image binarization; (d)Result of original image"

[1] 尉苗苗, 李岳阳, 蒋高明, 等. 应用最优Gabor滤波器的经编织物疵点检测[J]. 纺织学报, 2016,37(11):48-49.
YU Miaomiao, LI Yueyang, JIANG Gaoming, et al. Warp knit fabric defect detection method based on optimal Gabor filter[J]. Journal of Textile Research, 2016,37(11):48-49.
[2] 毛兆华, 汪军, 周建, 等. 应用非负字典学习的机织物瑕疵检测算法[J]. 纺织学报, 2016,37(3):144-145.
MAO Zhaohua, WANG Jun, ZHOU Jian, et al. Woven fabric defect detection base on non-negative dictionary learing[J]. Journal of Textile Research, 2016,37(3):144-145.
[3] 王刚, 周建, 汪军, 等. 采用奇异值分解的机织物瑕疵检测算法[J]. 纺织学报, 2014,35(7):61-62.
WANG Gang, ZHOU Jian, WANG Jun, et al. Woven fabric defect detection using singular value decomposition[J]. Journal of Textile Research, 2014,35(7):61-62.
[4] CAMPBELL J G, FRALEY C, MURTAGH F, et al. Linear flaw detection in woven textiles using model based clustering[J]. Pattern Recognition Letters, 1997,18(14):1539-1548.
doi: 10.1016/S0167-8655(97)00148-7
[5] SHI M H, FU R, GUO Y, et al. Fabric defect detection using local contrast deviations[J]. Multimedia Tools and Applications, 2011,52(1):147-157.
doi: 10.1007/s11042-010-0472-8
[6] KUMAR A, PANG G K H. Defect detection in textured materials using Gabor filters[J]. IEEE Transactions on Industry Applications, 2002,38(2):425-440.
doi: 10.1109/28.993164
[7] MIRMEHDI Majid, XIE Xianghua, SURI Jasjit. Handbook of Textile Analysis[M]. London: Imperial College Press, 2008: 101-150.
[8] HEALTH M, SARKAR S, SANOCKI T, et al. Comparison of edge detectors: a methodology and initial study[J]. Computer Vision and Image Understanding, 1998,69(1):38-54.
doi: 10.1006/cviu.1997.0587
[9] 许宏科, 秦严严, 陈会茹. 一种基于改进Canny的边缘检测算法[J]. 红外技术, 2014,36(3):211-212.
XU Hongke, QIN Yanyan, CHEN Huiru. An improve algorithm for edge detection based on canny[J]. Infrared Technology, 2014,36(3):211-212.
[10] 段红燕, 邵豪, 张淑珍, 等. 一种基于Canny 算子的图像边缘检测改进算法[J]. 上海交通大学学报, 2016,50(12):1862-1863.
DUAN Hongyan, SHAO Hao, ZHANG Shuzhen, et al. An improved algorithm for image edge detection based on Canny operator[J]. Journal of Shanghai Jiao Tong University, 2016,50(12):1862-1863.
[11] JOHN CANNY. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986,8(6):679-697.
pmid: 21869365
[12] 景晓军, 李剑峰, 熊玉庆. 静止图像的一种自适应平滑滤波算法[J]. 通信学报, 2002,23(10):8-12.
JING Xiaojun, LI Jianfeng, XIONG Yuqing. An adaptive smooth filter algorithms of still images[J]. Journal of China Institute of Communication, 2002,23(10):8-1.
[13] 薛丽霞, 李涛, 王佐成. 一种自适应的Canny边缘检测算法[J]. 计算机应用研究, 2010,27(9):3588-3589.
XUE Lixia, LI Tao, WANG Zuocheng. Adaptive Canny edge detection algorithm[J]. Application Research of Computers, 2010,27(9):3588-3589.
[1] 朱磊, 任梦凡, 潘杨, 李博涛. 基于相似性定位和超像素分割的织物疵点检测[J]. 纺织学报, 2020, 41(10): 58-66.
[2] 谢子昂, 杜劲松, 赵国华. 衬衫吊挂流水线的自适应动态调度[J]. 纺织学报, 2020, 41(10): 144-149.
[3] 杨恩君, 廖义辉, 刘安东, 俞立. 基于低秩分解的织物疵点检测[J]. 纺织学报, 2020, 41(05): 72-78.
[4] 张缓缓, 马金秀, 景军锋, 李鹏飞. 基于改进的加权中值滤波与K-means 聚类的织物缺陷检测[J]. 纺织学报, 2019, 40(12): 50-56.
[5] 周虎, 刘涛, 高金杰, 周强, 罗滨鸿, 游政, 苏炳望, 巴拉. 手工地毯植绒机轨迹规划及其速度控制优化[J]. 纺织学报, 2019, 40(10): 177-182.
[6] 王文帝 辛斌杰 邓娜 李佳平 刘宁娟. 单一视角下自适应阈值法的纱线毛羽识别及其应用[J]. 纺织学报, 2019, 40(05): 150-156.
[7] 徐洋 朱治潮 盛晓伟 余智祺 孙以泽. 基于机器视觉的鞋面特征点自动识别改进方法[J]. 纺织学报, 2019, 40(03): 168-174.
[8] 杜帅 李岳阳 王孟涛 罗海驰 蒋高明. 基于改进局部自适应对比法的织物疵点检测[J]. 纺织学报, 2019, 40(02): 38-44.
[9] 孙巧妍, 陈祥光, 刘美娜, 孙玉梅, 辛斌杰. 基于毛羽补偿与自适应中值滤波的纱线主体图像识别算法[J]. 纺织学报, 2019, 40(01): 62-66.
[10] 徐启永 胡峰 王传桐 吴雨川. 改进频率调谐显著算法在疵点图像分割中的应用[J]. 纺织学报, 2018, 39(05): 125-131.
[11] 马颜雪 李毓陵 刘梦佳 李雅倩 杨馨. 整体褶裥机织面料的织造新方法[J]. 纺织学报, 2018, 39(04): 42-46.
[12] 向军 张杰 潘如如 韩要宾 张继东 高卫东 . 采用纹理平滑的印花织物图案轮廓提取[J]. 纺织学报, 2017, 38(11): 162-167.
[13] 张波 汤春明. 基于相对总变差模型与自适应形态学的织物瑕疵检测[J]. 纺织学报, 2017, 38(05): 145-149.
[14] 尉苗苗 李岳阳 蒋高明 丛洪莲. 应用最优Gabor滤波器的经编织物疵点检测[J]. 纺织学报, 2016, 37(11): 48-54.
[15] 石美红 张正 郭仙草 陈永当. 基于显著纹理特征的织物疵点检测方法[J]. 纺织学报, 2016, 37(10): 42-049.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号　 京公网安备11010502044800号
版权所有 © 2021 《纺织学报》编辑部
地址： 北京市朝阳区延静里中街3号主楼6层《纺织学报》杂志社　邮政编码：100025　
电话：010-65017711,65917740　传真：010-65016539　Email:fangzhixuebao@vip.126.com
本系统由北京玛格泰克科技发展有限公司设计开发