Detecting Surface Defects of Transparent Parts with Computer Vision
-
摘要: 随着现代科技的发展,透明件几乎运用于各个行业并起着不可或缺的作用,透明件表面质量是衡量其合格与否的一个重要指标,同时机器视觉技术因具有速度快、精度高、成本低、稳定性好等优点被广泛用于透明件表面缺陷的检测。本文主要从图像采集、图像处理和缺陷识别几个环节来介绍透明件表面缺陷的检测,对检测系统的类型,采集图像的处理方法以及实验数据的整理进行深入的研究,结合图像特征与深度学习方法对透明件表面缺陷进行归类,探讨机器视觉检测透明件技术发展近状及现存问题。进一步,本文阐述了机器视觉检测透明件的最新进展,并对未来可能发展趋势进行预测,为后续研究工作提供基础理论参考。Abstract: The surface quality of transparent parts is an important indicator to measure whether they are qualified or not. Computer vision technology is widely used in the detection of surface defects of transparent parts because of its advantages such as high speed, high precision, low cost and good stability. This paper mainly introduces the detection of the surface defects of transparent parts with image acquisition, image processing and defect recognition. This paper uses the image feature method and the deep learning method to classify the surface defects of transparent parts and discusses the recent developments and existing problems of computer vision technology for detecting surface defects of transparent parts.
-
Key words:
- omputer vision /
- transparent parts /
- surface defect /
- detection system /
- image processing
-
图 4 Halcon软件对玻璃瓶样品进行缺陷分析[38]
表 1 各类常用光源的性质
名称 耗电量/W 亮度 响应速度 协调控制 发热量 可靠性 使用寿命/h 钨丝灯 15~200 较量 慢 高 高 低 3 000 卤素灯 100 亮 慢 高 极高 低 3 000 荧光灯 50~100 较量 慢 较高 较高 较好 5 000 镁氖灯 16 较量 较快 高 较高 较好 6 000 LED灯 极低 多个LED达到很亮 快 多种形式 极低 较高 10 000 表 2 图像分割在透明件表面缺陷检测中的应用情况
-
[1] CHANG M, CHEN B C, Gabayno J L, et al. Development of an optical inspection platform for surface defect detection in touch panel glass[J]. International Journal of Optomechatronics, 2016, 10(2):63-72 doi: 10.1080/15599612.2016.1166304 [2] 徐振飞, 刘尧峰, 徐卫.基于机器视觉的手机白玻璃缺陷检测方法研究[J].互联网应用, 2019(4):120-121 https://www.cnki.com.cn/Article/CJFDTOTAL-TXWL201904093.htmXU Z F, LIU Y F, XU W. Research on defect detection method of mobile phone white glass based on machine vision[J]. Internet Application, 2019(4):120-121 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TXWL201904093.htm [3] 段峰, 王耀南, 雷晓峰, 等.机器视觉技术及其应用综述[J].自动化博览, 2002, 19(3):59-61 doi: 10.3969/j.issn.1003-0492.2002.03.020DUAN F, WANG Y N, LEI X F, et al. Machine vision technologies[J]. Automation Panorama, 2002, 19(3):59-61 (in Chinese) doi: 10.3969/j.issn.1003-0492.2002.03.020 [4] 李青, 袁凤玲.机器视觉技术在玻璃基板缺陷检测设备中的应用[J].玻璃与搪瓷, 2016, 44(3):26-31 https://www.cnki.com.cn/Article/CJFDTOTAL-BLTC201603009.htmLI Q, YUAN F L. The application of machine vision technology in defect inspection of LCD substrate glass[J]. Glass & Enamel, 2016, 44(3):26-31 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BLTC201603009.htm [5] 杨杰, 卢盛林, 赵晓芳.机器视觉在钢化玻璃缺陷检测中的应用研究[J].计算机技术与发展, 2013, 23(3):211-214 https://www.cnki.com.cn/Article/CJFDTOTAL-WJFZ201303054.htmYANG J, LU S L, ZHAO X F. Application and research of machine vision in tempered glass defect inspection[J]. Computer Technology and Development, 2013, 23(3):211-214 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-WJFZ201303054.htm [6] BI X, XU X P, SHEN J H. An automatic detection method of Mura defects for liquid crystal display using real Gabor filters[C]//Proceedings of the 8th International Congress on Image and Signal Processing. Shenyang, China: IEEE, 2015 [7] LI D, LIANG L Q, ZHANG W J. Defect inspection and extraction of the mobile phone cover glass based on the principal components analysis[J]. The International Journal of Advanced Manufacturing Technology, 2014, 73(9-12):1605--614 doi: 10.1007/s00170-014-5871-y [8] FOGLIA P, PRETE C A, ZANDA M. An inspection system for pharmaceutical glass tubes[J]. WSEAS Transactions on Systems, 2015, 14:123-136 [9] MARTÍNEZ S S, ORTEGA J G, GÁMEZ GARCÍA J, et al. A machine vision system for defect characterization on transparent parts with non-plane surfaces[J]. Machine Vision and Applications, 2012, 23(1):1-13 doi: 10.1007/s00138-010-0281-0 [10] CABRAL J D D, DE ARAúJO S A. An intelligent vision system for detecting defects in glass products for packaging and domestic use[J]. The International Journal of Advanced Manufacturing Technology, 2015, 77(1-4):485-494 doi: 10.1007/s00170-014-6442-y [11] 刘焕军, 王耀南, 段峰.机器视觉中的图像采集技术[J].电脑与信息技术, 2003, 11(1):18-21 https://www.cnki.com.cn/Article/CJFDTOTAL-DNXJ200301004.htmLIU H J, WANG Y N, DUAN F. Image capture in machine vision[J]. Computer and Information Technology, 2003, 11(1):18-21 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DNXJ200301004.htm [12] 谭刚, 董祥龙, 徐继, 等.基于机器视觉的玻璃瓶表面缺陷检测[J].上海工程技术大学学报, 2009, 23(2):111-114 doi: 10.3969/j.issn.1009-444X.2009.02.004TAN G, DONG X L, XU J, et al. Defect detection of empty bottle surface based on machine-vision[J]. Journal of Shanghai University of Engineering Science, 2009, 23(2):111-114 (in Chinese) doi: 10.3969/j.issn.1009-444X.2009.02.004 [13] 王飞, 崔凤奎, 刘建亭, 等.基于机器视觉的玻璃表面缺陷检测系统的研究[J].玻璃与搪瓷, 2009, 37(5):6-10 doi: 10.3969/j.issn.1000-2871.2009.05.002WANG F, CUI F K, LIU J T, et al. A Study on the glass surface defect inspection system based on machine vision[J]. Glass & Enamel, 2009, 37(5):6-10 (in Chinese) doi: 10.3969/j.issn.1000-2871.2009.05.002 [14] MARTÍNEZ S S, ORTEGA J G, GÁMEZ GARCÍA J, et al. An industrial vision system for surface quality inspection of transparent parts[J]. The International Journal of Advanced Manufacturing Technology, 2013, 68(5-8):1123-1136 doi: 10.1007/s00170-013-4904-2 [15] 石兵华, 金永, 王召巴, 等.基于数字光栅投影的浮法玻璃缺陷检测方法研究[J].光电子·激光, 2014, 25(3):521-525 https://www.cnki.com.cn/Article/CJFDTOTAL-GDZJ201403018.htmSHI B H, JIN Y, WANG Z B, et al. Research on defects detection for float glass based on digital grating projection[J]. Journal of Optoelectronics·Laser, 2014, 25(3):521-525 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GDZJ201403018.htm [16] 李长有, 刘遵, 李帅涛.小型平板玻璃表面缺陷检测系统[J].计算机应用, 2017, 37(S2):167-170, 182 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY2017S2040.htmLI C Y, LIU Z, LI S T. Surface defect detection system for small-scale flat-panel glass[J]. Journal of Computer Applications, 2017, 37(S2):167-170, 182 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY2017S2040.htm [17] 韩九强, 胡怀忠.机器视觉技术及应用[M].北京:高等教育出版社, 2009:72-106HAN J Q, HU H Z. Machine vision application technology[M]. Beijing: Higher Education Press, 2009:72-106 (in Chinese) [18] 余发山, 田西方, 韩超超, 等.玻璃生产缺陷在线检测技术研究[J].河南理工大学学报, 2013, 32(4):476-480 doi: 10.3969/j.issn.1673-9787.2013.04.020YU F S, TIAN X F, HAN C C, et al. Research on on-line defect detection technology for glass production[J]. Journal of Henan Polytechnic University, 2013, 32(4):476-480 (in Chinese) doi: 10.3969/j.issn.1673-9787.2013.04.020 [19] 沈红雷.基于机器视觉技术的塑料制品缺陷检测研究[J].塑料科技, 2016, 44(8):89-92 https://www.cnki.com.cn/Article/CJFDTOTAL-SLKJ201608042.htmSHEN H L. Plastic products defect detection based on machine vision[J]. Plastics Science and Technology, 2016, 44(8):89-92 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SLKJ201608042.htm [20] LIU Y H, LIN S H, HSUEH Y L, et al. Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble[J]. Expert Systems with Applications, 2009, 36(2):1978-1998 doi: 10.1016/j.eswa.2007.12.015 [21] LI J, ZHAO F, ZHANG T F, et al. Research on robot vision detection method for scratch defects of flat glass based on area array CCD[C]//Proceedings of the 3rd Asia-Pacific Conference on Intelligent Robot Systems. Singapore: IEEE, 2018: 35-39 [22] LIU H G, CHEN Y P, PENG X Q, et al. A classification method of glass defect based on multiresolution and information fusion[J]. The International Journal of Advanced Manufacturing Technology, 2011, 56(9-12):1079-1090 doi: 10.1007/s00170-011-3248-z [23] 罗时光.基于机器视觉的玻璃瓶口缺陷检测方法[J].包装工程, 2018, 39(3):183-187 https://www.cnki.com.cn/Article/CJFDTOTAL-BZGC201803037.htmLUO S G. Glass-bottle defect detection method based on machine vision[J]. Packaging Engineering, 2018, 39(3):183-187 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BZGC201803037.htm [24] 周显恩, 王耀南, 朱青, 等.基于机器视觉的瓶口缺陷检测方法研究[J].电子测量与仪器学报, 2016, 30(5):702-713 https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201605009.htmZHOU X E, WANG Y N, ZHU Q, et al. Research on defect detection method for bottle mouth based on machine vision[J]. Journal of Electronic Measurement and Instrumentation, 2016, 30(5):702-713 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201605009.htm [25] ADAMO F, ATTIVISSIMO F, DI NISIO A, et al. An online defects inspection system for satin glass based on machine vision[C]//Proceedings of 2009 IEEE Instrumentation and Measurement Technology Conference. Singapore: IEEE, 2009 [26] 王世豪, 蔡延光, 蔡颢.玻璃表面缺陷检测算法研究[J].东莞理工学院学报, 2018, 25(1):45-49 https://www.cnki.com.cn/Article/CJFDTOTAL-DGLG201801009.htmWANG S H, CAI Y G, CAI H. The research on glass surface defect detection algorithm[J]. Journal of Dongguan University of Technology, 2018, 25(1):45-49 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DGLG201801009.htm [27] BI X, ZHUANG C G, DING H. A new mura defect inspection way for TFT-LCD using level set method[J]. IEEE Signal Processing Letters, 2009, 16(4):311-314 doi: 10.1109/LSP.2009.2014113 [28] ÖZTÜRK, AKDEMIR B. Comparison of edge detection algorithms for texture analysis on glass production[J]. Procedia-Social and Behavioral Sciences, 2015, 195:2675-2682 doi: 10.1016/j.sbspro.2015.06.477 [29] 简川霞, 高健.手机玻璃屏表面缺陷视觉检测方法研究[J].包装工程, 2018, 39(5):16-21 https://www.cnki.com.cn/Article/CJFDTOTAL-BZGC201805005.htmJIAN C X, GAO J. Visual detection method for surface defect of mobile phone screen glass[J]. Packaging Engineering, 2018, 39(5):16-21 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BZGC201805005.htm [30] ZHAO J, KONG Q J, ZHAO X, et al. A method for detection and classification of glass defects in low resolution images[C]// Proceedings of the 6th International Conference on Image and Graphics. Hefei, China: IEEE, 2011 [31] 罗根, 倪军.基于机器视觉的手机屏幕玻璃尺寸检测及崩边评价[J].电子测量与仪器学报, 2018, 32(2):92-96 https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201802014.htmLUO G, NI J. Glass size measurement and edge collapse assessment of mobile phone screens based on machine vision[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(2):92-96 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201802014.htm [32] 陈方涵, 赵光宇, 蒋仕龙.基于机器视觉系统的半透明薄膜缺陷检测及厚度测量研究[J].光电子·激光, 2018, 29(7):746-753 https://www.cnki.com.cn/Article/CJFDTOTAL-GDZJ201807010.htmCHEN F H, ZHAO G Y, JIANG S L. Defect inspection and thickness measurement for semi-transparent thin film based on machine vision system[J]. Journal of Optoelectronics·Laser, 2018, 29(7):746-753 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GDZJ201807010.htm [33] PARK N K, YOO S I. Evaluation of TFT-LCD defects based on human visual perception[J]. Displays, 2009, 30(1):1-16 doi: 10.1016/j.displa.2008.03.006 [34] 汤勃, 孔建益, 伍世虔.机器视觉表面缺陷检测综述[J].中国图象图形学报, 2017, 22(12):1640-1663 doi: 10.11834/jig.160623TANG B, KONG J Y, WU S Q. Review of surface defect detection based on machine vision[J]. Journal of Image and Graphics, 2017, 22(12):1640-1663 (in Chinese) doi: 10.11834/jig.160623 [35] MA L, LU Y, NAN X F, et al. Defect detection of mobile phone surface based on convolution neural network[C] //Proceedings of the 2nd International Conference on Manufacturing Science and Information Engineering. 2017 [36] JIN Y, WENG J L, WANG Z B. Conjugate gradient neural network-based online recognition of glass defects[J]. Concurrency and Computation: Practice and Experience, 2017, 29(3):e3768 doi: 10.1002/cpe.3768 [37] 程文博.基于机器视觉的注塑制品尺寸检测及表面缺陷识别[D].武汉: 华中科技大学, 2015CHENG W B. The dimensional inspection and surface defect recognition of injection molded products based on machine vision[D]. Wuhan: Huazhong University of Science and Technology, 2015(in Chinese) [38] 王一冰, 韩顺杰, 袁守彬.基于机器视觉的管制玻璃瓶缺陷检测方法的应用[J].机电信息, 2015(21):134-135, 138 doi: 10.3969/j.issn.1671-0797.2015.21.075WANG Y B, HAN S J, YUAN S B. Application of defect detection method of controlled glass bottle based on machine vision[J]. Mechanical and Electrical Information, 2015(21):134-135, 138 (in Chinese) doi: 10.3969/j.issn.1671-0797.2015.21.075 [39] 关日钊, 吴磊, 许焯基.基于机器视觉的透明塑料件缺陷检测[J].装备制造技术, 2018(3):167-171 doi: 10.3969/j.issn.1672-545X.2018.03.053GUAN R Z, WU L, XU Z J. Defect detection of transparent plastic parts based on machine vision[J]. Equipment Manufacturing Technology, 2018(3):167-171 (in Chinese) doi: 10.3969/j.issn.1672-545X.2018.03.053