首页 > 论文 > 激光与光电子学进展 > 56卷 > 13期(pp:131006--1)

基于机器视觉的聚氯乙烯管材表面缺陷检测

Surface Defect Detection of Polyvinyl Chloride Pipes Based on Machine Vision

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对人工肉眼检测聚氯乙烯(PVC)管材表面缺陷效果差、效率低下等问题,设计了一种基于机器视觉的PVC管材表面缺陷检测算法,并将其用于工业生产。该算法主要包含图像预处理和缺陷检测两部分,图像预处理包括边缘遍历、条纹检测和Gamma变换等步骤;缺陷检测主要包括水平与垂直投影、快速区域生长法连通域标记和分块处理等步骤。该算法对Gamma变换以及区域生长法作加速处理,同时能够最大限度地检测出PVC管材表面缺陷并避免误检。实验及工厂实地检测结果表明,该算法检测准确率为97.6%,实时检测速度超过60 m/min,缺陷最小检测面积为0.05 mm 2,而且管材运行中单边抖动不超过5 mm时无误报警现象发生,管材在运行速度为45 m/min时漏检率为0,因而能满足实际生产需要。

Abstract

This study proposes a machine vision-based surface defect detection algorithm to enhance the effect and efficiency of detecting surface defects in polyvinyl chloride (PVC) pipes for industrial production. The algorithm performs image preprocessing and defect detection. Image preprocessing includes steps such as edge traversal, fringe detection, and Gamma transformation. Defect detection mainly includes horizontal and vertical projection, fast region growing for connected region marking, and block processing. The proposed algorithm accelerates the Gamma transformation and region growing, and it can also be used to optimally detect surface defects in PVC pipes, while avoiding false detection. Results of tests and actual factory inspections suggest that the proposed algorithm achieves a detection accuracy of 97.6%, with a real-time detection speed of >60 m/min, and a minimum defect detection area of 0.05 mm 2. Moreover, a unilateral jitter of <5 mm does not cause any false alarms and the missed detection rate is 0 when the pipe runs at a speed of 45 m/min, which meets actual production needs.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.131006

所属栏目:图像处理

基金项目:国家自然科学基金、河北省引进留学人员资助项目、教育部春晖计划项目、河北省研究生创新资助项目;

收稿日期:2018-12-27

修改稿日期:2019-01-28

网络出版日期:2019-07-01

作者单位    点击查看

李书华:河北工业大学电子信息工程学院天津市电子材料与器件重点实验室, 天津 300401
周亚同:河北工业大学电子信息工程学院天津市电子材料与器件重点实验室, 天津 300401
王丹:河北工业大学电子信息工程学院天津市电子材料与器件重点实验室, 天津 300401
何静飞:河北工业大学电子信息工程学院天津市电子材料与器件重点实验室, 天津 300401
张忠伟:北京市安视中电科技有限公司, 北京 100871

联系人作者:周亚同(zyt@hebut.edu.com)

备注:国家自然科学基金、河北省引进留学人员资助项目、教育部春晖计划项目、河北省研究生创新资助项目;

【1】Li C W and Zuo J C. Technology status-quo and development direction of PVC pipes. Contemporary Chemical Industry. 44(4), 711-714(2015).
李成吾, 左继成. 国内外PVC管技术现状及发展方向. 当代化工. 44(4), 711-714(2015).

【2】Lu R S, Wu A, Zhang T D et al. Review on automated optical (visual) inspection and its applications in defect detection. Acta Optica Sinica. 38(8), (2018).
卢荣胜, 吴昂, 张腾达, 视觉 等. 检测技术及其在缺陷检测中的应用综述. 光学学报. 38(8), (2018).

【3】Yuan W Q, Li S L and Li D J. Detection of ice cream stick crack defects based on texture mainlobe and sidelobe features. Chinese Journal of Scientific Instrument. 38(11), 2779-2787(2017).
苑玮琦, 李绍丽, 李德健. 基于纹理主、旁瓣特征的雪糕棒裂缝缺陷检测. 仪器仪表学报. 38(11), 2779-2787(2017).

【4】Li K B, Yu H Y and Zhou S J. Surface scratch detection of mechanical parts based on morphological features. Acta Optica Sinica. 38(8), (2018).
李克斌, 余厚云, 周申江. 基于形态学特征的机械零件表面划痕检测. 光学学报. 38(8), (2018).

【5】Zheng H, Jiang B and Lu H F. An adaptive neural-fuzzy inference system (ANFIS) for detection of bruises on Chinese bayberry (Myrica rubra) based on fractal dimension and RGB intensity color. Journal of Food Engineering. 104(4), 663-667(2011).

【6】Cohen F S, Fan Z and Attali S. Automated inspection of textile fabrics using textural models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 13(8), 803-808(1991).

【7】Chao S M and Tsai D M. Anisotropic diffusion with generalized diffusion coefficient function for defect detection in low-contrast surface images. Pattern Recognition. 43(5), 1917-1931(2010).

【8】Tsai D M and Hsieh C Y. Automated surface inspection for directional textures. Image and Vision Computing. 18(1), 49-62(1999).

【9】Hu G H and Wang Q H. Fabric defect detection via un-decimated wavelet decomposition and Gumbel distribution model. Journal of Engineered Fibers and Fabrics. 13(1), 15-32(2018).

【10】Wang Q X, Li D, Zhang W J et al. Unsupervised defect detection for gold surface of flexible printed board. Optics and Precision Engineering. 18(4), 981-987(2010).
王庆香, 李迪, 张舞杰 等. 软性电路板金面缺陷的无监督检测. 光学精密工程. 18(4), 981-987(2010).

【11】Wang Z R, Fang Y M, Feng H L et al. Method for wooden knot detection and localization. Laser & Optoelectronics Progress. 55(5), (2018).
王泽润, 方益明, 冯海林 等. 木材节子缺陷检测与定位方法. 激光与光电子学进展. 55(5), (2018).

【12】Jeong Y S, Kim S J and Jeong M K. Automatic identification of defect patterns in semiconductor wafer maps using spatial correlogram and dynamic time warping. IEEE Transactions on Semiconductor Manufacturing. 21(4), 625-637(2008).

【13】Chen G F, Guan G Y and Wei X. Online stamping parts surface defects detection based on machine vision. Laser & Optoelectronics Progress. 55(1), (2018).
陈广锋, 管观洋, 魏鑫. 基于机器视觉的冲压件表面缺陷在线检测研究. 激光与光电子学进展. 55(1), (2018).

【14】Ma Y. The application research of PVC product inspection by edge detection. Hangzhou: Zhejiang University of Technology. 19-27(2004).
马艳. 边缘检测技术在PVC型材产品检测中的应用研究. 杭州: 浙江工业大学. 19-27(2004).

【15】Long X W. PVC surface defect detection method based on image vision and application. Changsha: Central South University. 9-19(2007).
龙晓薇. 基于图像视觉的PVC表面缺陷检测方法及应用. 长沙: 中南大学. 9-19(2007).

【16】Long X W, Yang C H and Long Y H. Research and design on surface defect detection system for PVC building materials. Computing Technology and Automation. 29(2), 46-50(2010).
龙晓薇, 阳春华, 龙永红. PVC建材表面缺陷检测系统研究与设计. 计算技术与自动化. 29(2), 46-50(2010).

【17】Dehghan Tezerjani A, Mehrandezh M and Paranjape R. Optimal spatial resolution of omnidirectional imaging systems for pipe inspection applications. International Journal of Optomechatronics. 9(4), 261-294(2015).

【18】Prabuwono A S, Sulaiman R, Hamdan A R et al. Development of intelligent visual inspection system (IVIS) for bottling machine. [C]∥TENCON 2006 - 2006 IEEE Region 10 Conference, November 14-17,2006, Hong Kong, China. New York: IEEE. 343887, (2006).

【19】Zhang Z, Wang Y P and Xue G X. Digital image processing and machine vision: implementation of Visual C++ and Matlab. 70-72(2014).
张铮, 王艳萍, 薛桂香. 数字图像处理与机器视觉: Visual C++与Matlab实现. 70-72(2014).

【20】Jiang X X, Zhang Z J, Wang Y N et al. PET full bottle fast detection based on gradient diffusion of gray projection. Journal of Electronic Measurement and Instrumentation. 30(8), 1152-1159(2016).
蒋笑笑, 张振军, 王耀南 等. 基于灰度投影梯度扩散的PET满瓶快速检测. 电子测量与仪器学报. 30(8), 1152-1159(2016).

【21】Gao H B and Wang W X. New connected component labeling algorithm for binary image. Computer Applications. 27(11), 2776-2777, 2785(2007).
高红波, 王卫星. 一种二值图像连通区域标记的新算法. 计算机应用. 27(11), 2776-2777, 2785(2007).

引用该论文

Shuhua Li, Yatong Zhou, Dan Wang, Jingfei He, Zhongwei Zhang. Surface Defect Detection of Polyvinyl Chloride Pipes Based on Machine Vision[J]. Laser & Optoelectronics Progress, 2019, 56(13): 131006

李书华, 周亚同, 王丹, 何静飞, 张忠伟. 基于机器视觉的聚氯乙烯管材表面缺陷检测[J]. 激光与光电子学进展, 2019, 56(13): 131006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF