基于变异系数法的工业产品表面缺陷快速检测应用研究

doi:10.11949/j.issn.0438-1157.20171486

化工学报 ›› 2018, Vol. 69 ›› Issue (3): 1238-1243.DOI: 10.11949/j.issn.0438-1157.20171486

基于变异系数法的工业产品表面缺陷快速检测应用研究

李澄非, 田果, 董超俊, 吉登清

五邑大学信息工程学院, 广东江门 529020

收稿日期:2017-11-07 修回日期:2017-11-21 出版日期:2018-03-05 发布日期:2018-03-05
通讯作者: 李澄非
基金资助:
2012广东省科技厅第一批产业技术研究与开发资金计划项目（2012B010100016）；2015广东省教育厅特色创新类项目（2015GXJK148，2015GXJK151）；2015广东省研究生教育创新计划项目（2015SFKC39）；2017年广东省教育厅—思科公司产学合作协同育人项目（粤教高[2017]153号）；五邑大学2017本科教学质量与教学改革工程建设项目（JX2017001）；2017年广东省科技发展专项资金（2017A010101019，2017A010101034）。

Application of variation coefficient to fast detection on surface defects of industrial products

LI Chengfei, TIAN Guo, DONG Chaojun, JI Dengqing

Wuyi University, School of Information Engineering, Jiangmen 529020, Guangdong, China

Received:2017-11-07 Revised:2017-11-21 Online:2018-03-05 Published:2018-03-05
Supported by:
supported by the First Batch of Industrial Technology Research and Development Funds Plan Project of Department of Science and Technology of Guangdong(2012B010100016), the Characteristics Innovation Projects of Department of Education of Guangdong (2015GXJK148, 2015GXJK151), the Graduate Education Innovation Project of Department of Education of Guangdong(2015SFKC39), the Department of Education-Cisco Company Production and Cooperation Education Project of Guangdong (2017, No.153), the 2017 Undergraduate Teaching Quality and Teaching Reform Project Construction Project of Wuyi University(JX2017001) and the 2017 Special Project for Science and Technology Development of Guangdong (2017A010101019, 2017A010101034).

摘要/Abstract

摘要：

为了提高工业产品质量控制中表面缺陷检测的准确性和快速性，提出了一种基于机器视觉的工业产品表面缺陷快速检测方法。方法引用变异系数的概念，通过待检测图像和模板图像进行差运算得到差影图像，并通过计算其变异系数以确定阈值，利用分割定位缺陷，从而实现缺陷的快速检测。壁纸表面缺陷检测实验结果表明，本方法提高了图像检测系统的准确性和鲁棒性，误检率大大降低。

关键词: 缺陷检测, 机器视觉, 变异系数, 差影图像

Abstract:

To improve accuracy and speed of quality control detection on surface defects of industrial products, a novel fast detection approach was proposed based on machine visualization. With introduction of variation coefficient, a difference image was obtained by image differencing analysis of the test image and the model image. Threshold was determined by variation coefficient of the difference image and then defects were located by image dicing. Experimental results on wallpaper surface defect detection show that the proposed method improved accuracy and robustness of image detection and reduced false detection rate greatly.

Key words: defect detection, machine visualization, coefficient of variation, difference image

中图分类号:

TP274

李澄非, 田果, 董超俊, 吉登清. 基于变异系数法的工业产品表面缺陷快速检测应用研究[J]. 化工学报, 2018, 69(3): 1238-1243.

LI Chengfei, TIAN Guo, DONG Chaojun, JI Dengqing. Application of variation coefficient to fast detection on surface defects of industrial products[J]. CIESC Journal, 2018, 69(3): 1238-1243.

参考文献 32

[1]	IPUNG H P, TJANDRASA H. Urban road materials identification using narrow near infrared vision system[J]. International Journal of Electrical & Computer Engineering, 2017, 7(3):1171-1179.
[2]	YOU F, LI Y H, HUANG L, et al. Monitoring drivers' sleepy status at night based on machine vision[J]. Multimedia Tools & Applications, 2017, 76(13):1-18.
[3]	CHU M, GONG R, WANG A. Strip steel surface defect classification method based on enhanced twin support vector machine[J]. Transactions of the Iron & Steel Institute of Japan, 2014, 54(1):119-124.
[4]	ZHOU J, ZHANG R. Classification of apple surface defect based on active thermal imaging technology[J]. Journal of East China Jiaotong University, 2012, 9(4):221-224.
[5]	ZHANG Z, NAKAMURA I, LI C J. Metal plating surface defect detection by template matching using morpholocal processing[J]. Image & Vision Computing, 2011, 22(14):1157-1164.
[6]	ZHANG H, XIE F, CAO M, et al. A steel ball surface quality inspection method based on a circumferential eddy current array sensor[J]. Sensors, 2017, 17(7):1536-1537.
[7]	HE B, ZHANG Y, TONG K J, et al. Curved surface imaging theory and defect detection for sealing rings used in aerospace systems[J]. Optics & Precision Engineering, 2015, 23(11):3051-3060.
[8]	WU Z, SUN C, LIU J. Oil-seal surface defect automatic detection and recognition method based on image processing[J]. Chinese Journal of Scientific Instrument, 2013, 34(5):1093-1099.
[9]	OUYANG Q, ZHANG L Z, ZHAO L M, et al. Experimental study on quantitative surface defect depth detection based on laser scanning technology in continuous casting[J]. Ironmaking & Steelmaking, 2011, 38(5):363-368.
[10]	HAO X, BIN L I. Detection of rail track surface defects based on machine vision[J]. Journal of Beijing Jiaotong University, 2015, 39(2):28-34.
[11]	ZHANG Y, LI T, LI Q. Defect detection for tire laser shearography image using curvelet transform based edge detector[J]. Optics & Laser Technology, 2013, 47(4):64-71.
[12]	SIOD?AK D. Building large molecular models with plastic screw-on bottle caps and sturdy connectors[J]. Journal of Chemical Education, 2017, 94(2):256-259.
[13]	KO J S, RHEEM J Y. Defect detection of polycrystalline solar wafers using local binary mean[J]. International Journal of Advanced Manufacturing Technology, 2016, 82(9/10/11/12):1753-1764.
[14]	CHENG X, TAO Z, HUANG J. System design of containment external defects detection[J]. Journal of Geomatics, 2017, 42(2):71-75.
[15]	王震宇. 基于机器视觉钢板表面缺陷检测技术研究[J]. 计算机与现代化, 2013, (7):130-134. WANG Z Y. Research on surface defect detection technology based on machine vision[J]. Computer and Modernization, 2013, (7):130-134.
[16]	CAI Z, XIAO J, WEN L, et al. Algorithm of defect segmentation for AFP based on prepregs[J]. Journal of Aeronautical Materials, 2017, 37(2):21-27.
[17]	LIU L, ZENG L. Defect segmentation in digital radiography images of castings on a railway freight car[J]. Insight:Non-Destructive Testing and Condition Monitoring, 2011, 53(7):372-376.
[18]	FALQUE R, VIDALCALLEJA T, MIRO J V. Defect detection and segmentation framework for remote field eddy current sensor data[J]. Sensors, 2017, 17(10):2276-2278.
[19]	YONG D C. Automated inspection algorithm for thick plate using dual light switching lighting method[J]. World Academy of Science Engineering & Technology, 2012, 6(12):1475-1478.
[20]	BAI X, WANG P, ZHOU F. Pedestrian segmentation in infrared images based on circular shortest path[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(8):2214-2222.
[21]	YASNOFF W A. Error measures for scene segmentation in automated cytology[J]. Pattern Recognition, 1977, 9(4):217-231.
[22]	DE SOLORZANO C O, CHIN K, CHOU W S, et al. Measurement of genetic instability in breast cancer by confocal microscopy and 3D image analysis[J]. Annual International Conference of the IEEE Engineering in Medicine and Biology. 1999, 2(2):822-826.
[23]	马义德, 苏茂君, 陈锐. 基于PCNN的图像二值化及分割评价方法[J]. 华南理工大学学报(自然科学版), 2009, 37(5):49-53. MA Y D, SU M J, CHEN R. Image binarization and segmentation evaluation method based on PCNN[J]. Journal of South China University of Technology(Natural Science Edition), 2009, 37(5):49-53.
[24]	闵超波, 张俊举, 常本康, 等. 无需先验知识的红外显著性目标分割评价准则[J]. 模式识别与人工智能, 2013, 26(12):1106-1114. MIN C B, ZHANG J J, CHANG B K, et al. No prior knowledge of infrared significance target segmentation evaluation criterion[J]. Pattern Recognition and artificial Intelligence, 2013, 26(12):1106-1114.
[25]	WEBER E U, SHAFIR S, BLAIS A R. Predicting risk sensitivity in humans and lower animals:risk as variance or coefficient of variation[J]. Psychological Review, 2004, 111(2):430-431.
[26]	王义文, 屈冠彤, 刘献礼, 等. 钢球表面缺陷的图像差分检测算法[J]. 计算机辅助设计与图形学学报, 2016, 28(10):1699-1704. WANG Y W, QU G D, LIU X L, et al. Image difference detection algorithm for steel ball surface defects[J]. Journal of Computer Aided Design and Graphics, 2016, 28(10):1699-1704.
[27]	MAZHIR S N, ALI A H, HADI F W, et al. Studying the effect of dielectric barrier discharges on the leukemia blood cells using digital image processing[J]. Iosr Journal of Pharmacy & Biological Sciences, 2017, 12(2):6-12.
[28]	DAVROS W. Digital image processing for medical applications[J]. Medical Physics, 2010, 37(2):948-949.
[29]	王平, 魏征, 崔卫红, 等. 一种基于统计学习理论的最小生成树图像分割准则[J]. 武汉大学学报(信息科学版), 2017, 42(7):877-883. WANG P, WEI Z, CUI W H, et al. A minimum spanning tree image segmentation criterion based on statistical learning theory[J]. Journal of Wuhan University (Information Science), 2017, 42(7):877-883.
[30]	施铃泉, 蒋爱民, 朱昌平, 等. 基于稀疏表示的离散系数FIR滤波器设计[J]. 科学技术与工程, 2014, 14(1):205-208. SHI L Q, JIANG A M, ZHU C P, et al. Design of FIR filters with discrete coefficients based on sparse representation[J]. Science Technology and Engineering, 2014, 14(1):205-208.
[31]	TOLBA A S. Fast defect detection in homogeneous flat surface products[J]. Expert Systems with Applications, 2011, 38(10):12339-12347.
[32]	TSAI D M, CHEN M C, LI W C, et al. A fast regularity measure for surface defect detection[J]. Machine Vision & Applications, 2012, 23(5):869-886.

基于变异系数法的工业产品表面缺陷快速检测应用研究

Application of variation coefficient to fast detection on surface defects of industrial products

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价

[1]	翁润滢, 孙斌, 赵玉晓, 张竟月, 文英杰. 基于自适应最优核和卷积神经网络的气液两相流流型识别方法[J]. 化工学报, 2018, 69(12): 5065-5072.
[2]	褚菲, 程相, 代伟, 赵旭, 王福利. 基于过程迁移的间歇过程终点质量预报方法[J]. 化工学报, 2018, 69(6): 2567-2575.
[3]	蒋昕祎, 杜红彬, 李绍军. 基于核慢特征回归与互信息的常压塔软测量建模[J]. 化工学报, 2017, 68(5): 1977-1986.
[4]	刘瑞兰, 刘树云, 戎舟, 江兵, 庞宗强. 基于双阈值AdaBoost算法的4-CBA含量软测量建模[J]. 化工学报, 2017, 68(5): 2009-2015.
[5]	郑蓉建, 潘丰. 基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模[J]. 化工学报, 2017, 68(3): 976-983.
[6]	孙茂伟, 杨慧中. 基于改进Bagging算法的高斯过程集成软测量建模[J]. 化工学报, 2016, 67(4): 1386-1391.
[7]	双翼帆, 顾幸生. 基于改进的快速搜索聚类算法和高斯过程回归的催化重整脱氯前氢气纯度多模型建模方法[J]. 化工学报, 2016, 67(3): 765-772.
[8]	王金萍, 赵忠盖, 刘飞. 一种融合无时滞测量值和含时滞测量值的状态估计方法[J]. 化工学报, 2016, 67(3): 940-946.
[9]	荣冈, 杨胜蓝, 周培杰, 冯毅萍. 一种基于优先级的控制系统性能评估和安全监控系统[J]. 化工学报, 2016, 67(3): 707-714.
[10]	刘瑞兰, 徐艳, 戎舟. 基于稀疏最小二乘支持向量机的软测量建模[J]. 化工学报, 2015, 66(4): 1402-1406.
[11]	李军, 岳文琦. 基于泄漏积分型回声状态网络的软测量动态建模方法及应用[J]. 化工学报, 2014, 65(10): 4004-4014.
[12]	雷瑜, 杨慧中. 基于高斯过程和贝叶斯决策的组合模型软测量[J]. 化工学报, 2013, 64(12): 4434-4438.
[13]	王明旭刘兴高. 基于GMC(1,N)的聚丙烯熔融指数预报[J]. 化工学报, 2013, 64(5): 0-0.
[14]	王明旭刘兴高. 基于GMC(1,N)的聚丙烯熔融指数预报[J]. CIESC Journal, 2013, 64(5): 0-0.
[15]	钱晓山, 阳春华, 徐丽莎. 基于改进差分进化和最小二乘支持向量机的铝酸钠溶液浓度软测量[J]. 化工学报, 2013, 64(5): 1704-1709.