智能制造中的计算机视觉应用瓶颈问题

雷林建; 孙胜利; 向玉开; 张悦; 刘会凯

doi:10.11834/jig.190446

综述 | 浏览量 : 0 下载量: 451 CSCD: 0

PDF
导出
分享
收藏
专辑

智能制造中的计算机视觉应用瓶颈问题
Bottleneck issues of computer vision in intelligent manufacturing
2020年25卷第7期页码：1330-1343
收稿：2019-09-26，

修回：2019-12-12，

录用：2019-12-19，

纸质出版：2020-07-16
DOI： 10.11834/jig.190446
稿件说明：

移动端阅览

雷林建, 孙胜利, 向玉开, 张悦, 刘会凯. 智能制造中的计算机视觉应用瓶颈问题[J]. 中国图象图形学报, 2020,25(7):1330-1343. DOI： 10.11834/jig.190446.

Linjian Lei, Shengli Sun, Yukai Xiang, Yue Zhang, Huikai Liu. Bottleneck issues of computer vision in intelligent manufacturing[J]. Journal of Image and Graphics, 2020, 25(7): 1330-1343. DOI： 10.11834/jig.190446.

摘要

计算机视觉在智能制造工业检测中发挥着检测识别和定位分析的重要作用，为提高工业检测的检测速率和准确率以及智能自动化程度做出了巨大的贡献。然而计算机视觉在应用过程中一直存在技术应用难点，其中3大瓶颈问题是：计算机视觉应用易受光照影响、样本数据难以支持深度学习、先验知识难以加入演化算法。这些瓶颈问题使得计算机视觉在智能制造中的应用无法发挥最佳效能。因此，需要系统地加以分析和解决。本文总结了智能制造和计算机视觉的概念及其重要性，分析了计算机视觉在智能制造工业检测领域的发展现状和需求。针对计算机视觉应用存在的3大瓶颈问题总结分析了问题现状和已有解决方法。经过深入分析发现：针对受光照影响大的问题，可以通过算法和图像采集两个环节解决；针对样本数据难以支持深度学习的问题，可以通过小样本数据处理算法和样本数量分布平衡方法解决；针对先验知识难以加入演化算法的问题，可以通过机器学习和强化学习解决。上述解决方案中的方法不尽相同，各有优劣，需要结合智能制造中具体应用研究和改进。

Abstract

Computer vision plays an important role in detection

recognition

and location analysis in intelligent manufacturing

especially in industry inspection. It has made great contributions to improve the inspection rate

the accuracy of industrial inspection

and the degree of intelligent automation. However

the popularity of computer vision technology is insufficient in intelligent manufacturing because of its several technical application difficulties. Dealing with these problems has become a top priority in the popularization of computer vision in intelligent manufacturing. The three key application bottlenecks are the illumination impacts

sample data that cannot support deep learning

and prior knowledge that cannot support evolutionary algorithms. These bottlenecks make computer vision in intelligent manufacturing inefficient and cannot be applied in several fields. Therefore

these bottlenecks need to be systematically analyzed and resolved. We first summarized the concepts of intelligent manufacturing and computer vision. Then

the development of computer vision in intelligent manufacturing and the demand of intelligent manufacturing for computer vision technology were presented. We elaborated that computer vision could increase the inspection accuracy and rate and provide many details that cannot be found by human beings by comparing it with traditional methods. On the basis of the development status and needs of computer vision in intelligent manufacturing inspection

we proposed three critical bottlenecks in computer vision applications

namely

1) In the actual industrial situation

uneven illumination is easily obtained because the environment is complex

and the light source is simple. Thus

The problem where the image quality is immensely impacted by illumination should be explored. 2) Obtaining uniform sample data of more than 10 000 levels in the actual industry is difficult. The problem where the sample data cannot support computer vision detection task based on deep learning should be given great importance. 3) Computer judgment cannot achieve the accuracy of professional judgment. Rational addition of human prior knowledge into evolutionary algorithms to reduce the difficulty of deep learning algorithms should be deeply analyzed. Then

we focused on summarizing and analyzing the status

source

and existing solutions of the three problems in sequence. Several widely-accepted or effective methods were analyzed and compared in the sections. We conducted make a feasibility analysis through the qualitative analysis of data and principles to prove that they can be used in intelligent manufacturing. A thorough analysis indicates that: illumination can be solved through some algorithms used in image acquisition; the sample data that cannot support deep learning can be solved using a small sample data processing algorithm and a sample quantity distribution balance method; for prior knowledge that cannot support evolutionary algorithms can be solved through machine learning and reinforcement learning. The methods in the above solutions are numerous and different. Each of them has its own advantages and disadvantages and needs to be researched and improved in specific applications in intelligent manufacturing. This overview summarizes the bottlenecks of computer vision applications in intelligent manufacturing

analyzes the corresponding solutions

and provides specific example methods. The application feasibility of these methods in intelligent manufacturing is also analyzed. The methods described in this paper can be applied to intelligent manufacturing. We propose new ideas for solving bottleneck problems. This paper provides certain reference values for readers and scholars using computer vision in intelligent manufacturing.

关键词

Keywords

references

Aloimonos Y. 1993. Introduction:Active Vision Revisited. Maryland, University of Maryland, College Park

An Q, Li Z C, Ji C Y and Zhou J. 2009. Agricultural robot vision navigation algorithm based on illumination invariant image. Transactions of the Chinese Society of Agricultural Engineering, 25(11):208-212

安秋, 李志臣, 姬长英, 周俊. 2009.基于光照无关图的农业机器人视觉导航算法.农业工程学报, 25(11):208-212)[DOI:10.3969/j.issn.1002-6819.2009.11.037]

Bai R L, Zhang Z Y, Jiang L J and Li X. 2014. Method for reducing dimensions of texture features for surface defect detection on basis of machine vision. CN, 103544499A

白瑞林, 张振尧, 姜利杰, 李新. 2014.一种基于机器视觉的表面瑕疵检测的纹理特征降维方法.中国, 103544499A

Bianchi R A, Ribeiro C H and Costa A H. 2008. Accelerating autonomous learning by using heuristic selection of actions. Journal of Heuristics, 14(2):135-168[DOI:10.1007/s10732-007-9031-5]

Chawla N V, Bowyer K W, Hall L O and Kegelmeyer W P. 2002. SMOTE:synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16(1):321-357[DOI:10.1613/jair.953]

Deng J, Dong W, Socher R, Li L J, Li K and Li F F. 2009. ImageNet: a large-scale hierarchical image database//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA: IEEE: 248-255[ DOI: 10.1109/CVPR.2009.5206848 http://dx.doi.org/10.1109/CVPR.2009.5206848 ]

Du C J and Cheng Q F. 2014. Computer vision//O'Donnell C P, Fagan C and Cullen P J, eds. Process Analytical Technology for the Food Industry. New York: Springer: 157-181[ DOI: 10.1007/978-1-4939-0311-5_7 http://dx.doi.org/10.1007/978-1-4939-0311-5_7 ]

Du C X, Gao Y and Zhang W. 2005. Q-learning with prior knowledge in multi-agent systems. Journal of Tsinghua University (Science and Technology), 45(7):981-984

杜春侠, 高云, 张文. 2005.多智能体系统中具有先验知识的Q学习算法.清华大学学报(自然科学版), 45(7):981-984)[DOI:10.3321/j.issn:1000-0054.2005.07.031]

Duan F, Wang Y N, Lei X F, Wu L Z and Tan W. 2002. Machine vision technologies. Automation Panorama, 19(3):59-61

段峰, 王耀南, 雷晓峰, 吴立钊, 谭文. 2002.机器视觉技术及其应用综述.自动化博览, 19(3):59-61)[DOI:10.3969/j.issn.1003-0492.2002.03.020]

Eisert P and Girod B. 2002. Model-based enhancement of lighting conditions in image sequences//Proceedings of SPIE 4671, Visual Communications and Image Processing 2002. San Jose, California, United States: International Society for Optics and Photonics: #4671[ DOI: 10.1117/12.453065 http://dx.doi.org/10.1117/12.453065 ]

Fang C. 2007. Machine vision and its application in industry inspection. Automation Panorama, 24(4):46-48

房超. 2007.机器视觉及其在工业检测中的应用.自动化博览, 24(4):46-48)[DOI:10.3969/j.issn.1003-0492.2007.04.013]

Finn C, Abbeel P and Levine S. 2017. Model-agnostic meta-learning for fast adaptation of deep networks[EB/OL].[2019-8-18] . https://arxiv.org/pdf/1703.03400.pdf https://arxiv.org/pdf/1703.03400.pdf

Garcia V and Bruna J. 2018. Few-shot learning with graph neural networks[EB/OL]. 2017-11-10[2019-03-20] . https://arxiv.org/pdf/1711.04043.pdf https://arxiv.org/pdf/1711.04043.pdf

Goldberg D E. 1989. Genetic Algorithms in Search, Optimization and Machine Learning. Boston, MA:Addison-Wesley, 13(7):2104-2116

Guan R H, Cao C M and Chen H. 2001. Study of defects in the equipment's inner wall by means of infrared thermal diagnosis. Laser and Infrared, 31(4):228-229

关荣华, 曹春梅, 陈衡. 2001.工业设备内部缺陷的红外热诊断研究.激光与红外, 31(4):228-229)[DOI:10.3969/j.issn.1001-5078.2001.04.012]

Guo X X, Singh S, Lee H, Lewis R and Wang X S. 2014. Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning//Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, MA: ACM: 3338-3346

Hartley R and Zisserman A. 2000. Multiple View Geometry in Computer Vision. Cambridge University Press

He H B and Garcia E A. 2009. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9):1263-1284[DOI:10.1109/tkde.2008.239]

He J J, Shi L, Xiao J L, Cheng J and Zhu Y. 2010. Size detection of firebricks based on machine vision technology//Proceedings of 2010 International Conference on Measuring Technology and Mechatronics Automation. Changsha City, China: IEEE: 394-397[ DOI: 10.1109/ICMTMA.2010.798 http://dx.doi.org/10.1109/ICMTMA.2010.798 ]

Heckerman D, Geiger D and Chickering D M. 1995. Learning Bayesian networks:the combination of knowledge and statistical data. Machine Learning, 20(3):197-243[DOI:10.1023/A:1022623210503]

Hinton G E and Salakhutdinov R R. 2006. Reducing the dimensionality of data with neural networks Science, 313(5786): 504-507[ DOI: 10.1126/science.1127647 http://dx.doi.org/10.1126/science.1127647 ]

Hu X S and Zhang R J. 2013. Clustering-based subset ensemble learning method for imbalanced data//Proceedings of 2013 International Conference on Machine Learning and Cybernetics. Tianjin, China: IEEE: 35-39[ DOI: 10.1109/ICMLC.2013.6890440 http://dx.doi.org/10.1109/ICMLC.2013.6890440 ]

Huang Z F. 2005. Face Size Examination Machine Vision System Research. Hangzhou:Zhejiang University of Technology

黄正福. 2005.面向尺寸检测的机器视觉系统研究.杭州:浙江工业大学

Karan S and Dholay S. 2016. Machine vision based approach to analyze street surface anomalies//Proceedings of 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication. Jalgaon, India: IEEE: 241-246[ DOI: 10.1109/ICGTSPICC.2016.7955305 http://dx.doi.org/10.1109/ICGTSPICC.2016.7955305 ]

Khan D. 2018. Deep Learning Based Power Switch Detection and State Recognition. Chengdu:University of Electronic Science and Technology (Khan D. 2018.

基于深度学习的电力开关检测与状态识别.成都:电子科技大学

Knox W B and Stone P. 2009. Interactively shaping agents via human reinforcement: the TAMER framework//Proceedings of the 5th International Conference on Knowledge Capture. California, USA: ACM: 9-16[ DOI: 10.1145/1597735.1597738 http://dx.doi.org/10.1145/1597735.1597738 ]

Koch G, Zemel R and Salakhutdinov R. 2016. Siamese neural networks for one-shot image recognition[EB/OL].[2019-03-22] . https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf

Krizhevsky A, Sutskever I and Hinton G E. 2012. ImageNet classification with deep convolutional neural networks//Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook, NY: ACM: 1097-1105[ DOI: 10.1145/3065386 http://dx.doi.org/10.1145/3065386 ]

Lai S H. 2000. Robust image matching under partial occlusion and spatially varying illumination change. Computer Vision and Image Understanding, 78(1):84-98[DOI:10.1006/cviu.1999.0829]

Li C and Wang W. 2012. Prior knowledge support vector machine and its applications in medical image segmentation. Electronic Design Engineering, 20(12):180-183

李晨, 王巍. 2012.基于先验知识的支持向量机在图像分割中的应用研究.电子设计工程, 20(12):180-183)[DOI:10.3969/j.issn.1674-6236.2012.12.061]

Li C X, Cao L, Zhang Y L, Chen X L, Zhou Y H and Duan L W. 2017. Knowledge-based deep reinforcement learning:a review. Systems Engineering and Electronics, 39(11):2603-2613

李晨溪, 曹雷, 张永亮, 陈希亮, 周宇欢, 段理文. 2017.基于知识的深度强化学习研究综述.系统工程与电子技术, 39(11):2603-2613)[DOI:10.3969/j.issn.1001-506X.2017.11.30]

Li W H, Shan W P and Zeng X Q. 2016. Bearing fault identification based on deep belief network. Journal of Vibration Engineering, 29(2):340-347

李巍华, 单外平, 曾雪琼. 2016.基于深度信念网络的轴承故障分类识别.振动工程学报, 29(2):340-347)[DOI:10.16385/j.cnki.issn.1004-4523.2016.02.020]

Lin L Z, Ni X P, Zhou L S and Qian Z Q. 2011. Research on real-time measuring method of dynamic deformation based on machine vision and its application. Applied Mechanics and Materials, 130-134:3572-3576[DOI:10.4028/www.scientific.net/AMM.130-134.3572]

Lin T Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P and Zitnick C L. 2014. Microsoft COCO: Common objects in context//Proceedings of the 13th conference on Computer Vision-ECCV 2014. Zurich, Switzerland: Springer: 740-755[ DOI: 10.1007/978-3-319-10602-1_48 http://dx.doi.org/10.1007/978-3-319-10602-1_48 ]

Liu N Y, Liu J, She X Y and Fu Q S. 2016. The research of steel image segmentation algorithm under conditions of uneven illumination. Laser Journal, 37(3):46-49

刘南艳, 刘菁, 厍向阳, 付秋实. 2016.光照不均条件下的钢管图像分割算法研究.激光杂志, 37(3):46-49)[DOI:10.14016/j.cnki.jgzz.2016.03.046]

Luo G J. 2009. Coordination of Illumination and Camerain Computer Vision System. Hangzhou:Zhejiang University of Technology

骆广娟. 2009.计算机视觉中的光照协调技术.杭州:浙江工业大学, 2009

Ma Y Z, Hu L, Fang Z Q and Cao S Z. 2004. Development and application research of computer vision detection technique. Journal of Jinan University (Science and Technology), 18(3):222-227

马玉真, 胡亮, 方志强, 曹素芝. 2004.计算机视觉检测技术的发展及应用研究.济南大学学报(自然科学版), 18(3):222-227)[DOI:10.3969/j.issn.1671-3559.2004.03.011]

Marr D. 1982. Vision:a Computational Investigation into the Human Representation and Processing of Visual Information. New York:W.H. Freeman and Company

Mataric M J. 1994. Reward functions for accelerated learning//Proceedings of the 16th International Conference on Machine Learning. New Branswick, NJ: Elsevier: 181-189[ DOI: 10.1016/13978-1-55860-335-6.50030-1 http://dx.doi.org/10.1016/13978-1-55860-335-6.50030-1 ]

Ng A Y, Harada D and Russell S J. 1999. Policy invariance under reward transformations: theory and application to reward shaping//Proceedings of the 16th International Conference on Machine Learning. San Francisco, CA: ACM: 278-287

Paulsen M R and McClure W F. 1986. Illumination for computer vision systems. Transactions of the ASAE, 29(5):1398-1404[DOI:10.13031/2013.30328]

Poggio T and Bizzi E. 2004. Generalization in vision and motor control. Nature, 431(14):768-774[DOI:10.1038/nature03014]

Randløv J and Alstrøm P. 1998. Learning to drive a bicycle using reinforcement learning and shaping//Proceedings of the 15th International Conference on Machine Learning. San Francisco, CA: ACM: 463-471

Ren H, Qu J F, Chai Y, Tang Q and Ye X. 2017. Deep learning for fault diagnosis:the state of the art and challenge. Control and Decision, 32(8):1345-1358

任浩, 屈剑锋, 柴毅, 唐秋, 叶欣. 2017.深度学习在故障诊断领域中的研究现状与挑战.控制与决策, 32(8):1345-1358)[DOI:10.13195/j.kzyjc.2016.1625]

Sha Z J. 1995. Intelligent Infrared Industrial Flaw Detection System. Beijing:Institute of Electrics, Chinese Academy of Sciences

沙正金. 1995.智能红外线工业探伤系统.北京:中国科学院电子学研究所

Shen W, Zhou M, Yang F, Yang C Y and Tian J. 2015. Multi-scale convolutional neural networks for lung nodule classification//Proceedings of the 24th International Conference on Information Processing in Medical Imaging. Sabhal Mor Ostaig, Isle of Skye, UK: Springer: 588-599[ DOI: 10.1007/978-3-319-19992-4_46 http://dx.doi.org/10.1007/978-3-319-19992-4_46 ]

Shi H, Wang C J, Zhu H and Wu J. 2015. Clear reflection of shooing of assembly line goods appearance of making a video recording. CN, 204795419U

石焕, 王楚君, 朱弘, 吴矩. 2015.一种流水线货物清晰拍照的反射摄像仪.中国, 204795419U

Snell J, Swersky K and Zemel R S. 2017. Prototypical networks for few-shot learning[EB/OL].[2019-08-18] . https://arxiv.org/pdf/1703.05175.pdf https://arxiv.org/pdf/1703.05175.pdf

Song C. 2017. Egg Appearance Defect Detection Based on Deep Learning. Guiyang:Guizhou University

宋超. 2017.基于深度学习的鸡蛋外观缺陷检测算法.贵阳:贵州大学

Song K Y, Petrou M and Kittler J. 1995. Texture crack detection. Machine Vision and Applications, 8(1):63-75[DOI:10.1007/bf01213639]

Sui W T. 2011. Study on the Feature Extraction and Diagnosis for Surface Damage of Rolling Element Bearings. Jinan:Shandong University

隋文涛. 2011.滚动轴承表面损伤故障的特征提取与诊断方法研究.济南:山东大学

Sun C, Shrivastava A, Singh S and Gupta A. 2017. Revisiting unreasonable effectiveness of data in deep learning era//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE: 843-852[ DOI: 10.1109/ICCV.2017.97 http://dx.doi.org/10.1109/ICCV.2017.97 ]

Tang B, Kong J Y and Wu S Q. 2017. Review of surface defect detection based on machine vision. Journal of Image and Graphics, 22(12):1640-1663

汤勃, 孔建益, 伍世虔. 2017.机器视觉表面缺陷检测综述.中国图象图形学报, 22(12):1640-1663)[DOI:10.11834/jig.160623]

Tang H R, Houthooft R, Foote D, Stooke A, Chen X, Duan Y, Schulman J, De Turck F and Abbeel P. 2017. Exploration: a study of count-based exploration for deep reinforcement learning[EB/OL].[2019-08-18] . https://arxiv.org/pdf/1611.04717.pdf https://arxiv.org/pdf/1611.04717.pdf

Tenenbaum J B, Kemp C, Griffiths T L and Goodman N D. 2011. How to grow a mind:statistics, structure, and abstraction. Science, 331(6022):1279-1285[DOI:10.1126/science.1192788]

Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K and Wierstra D. 2016. Matching networks for one shot learning//Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook, NY: ACM: 3630-3638

Wang H H. 2016. Illumination Processing Based on Phonglode and Its Application in Defects Detection for Bille. Wuhan:Wuhan University of Science and Technology

王欢欢. 2016.基于Phong模型的去光照算法及其在钢坯缺陷检测中的应用.武汉:武汉科技大学

Wang H R, Tian Y T and Gu Q. 2009. Adaptive tuning methods for digital camera parameters under variou illuminations. Journal of Jilin University (Engineering and Technology Edition), 39(5):1262-1267

王红睿, 田彦涛, 顾庆. 2009.变光照环境中的数字摄像机参数自适应调整算法.吉林大学学报(工学版), 39(5):1262-1267

Wang X, Jin W P, Zhang C L, Shen J L, Guo G P, Yang D G, Wu D L, Li J W and Guo X W. 2004. Actuality and evolvement of infrared thermal wave nondestructive imaging technology. Nondestructive Testing, 26(10):497-501

王迅, 金万平, 张存林, 沈京玲, 郭广平, 杨党纲, 吴东流, 李建伟, 郭兴旺. 2004.红外热波无损检测技术及其进展.无损检测, 26(10):497-501)[DOI:10.3969/j.issn.1000-6656.2004.10.003]

Wang X, Wang P and Cheng H. 2014. Research of bridge displacement on-line monitoring technique based onmachine vision. Highway Engineering, 39(1):198-201

王翔, 王鹏, 程辉. 2014.基于机器视觉的桥梁形变在线监测技术研究.公路工程, 39(1):198-201

Wang Y. 2007. Application of Computer Vision in Industrial Inspection. Guiyang:Guizhou University

王茵. 2007.计算机视觉在工业检测中的应用研究.贵阳:贵州大学

Wang Z R and Wu Y H. 2011. On-Machine illumination technique in industry machine vision. Advanced Materials Research, 201-203:1582-1585[DOI:10.4028/www.scientific.net/AMR.201-203.1582]

Wei S D and Lai S H. 2006. Robust and efficient image alignment based on relative gradient matching. IEEE Transactions on Image Processing, 15(10):2936-2943[DOI:10.1109/tip.2006.877500]

Xi B, Wang Z L and Qian F. 2006. Development and application of machine vision in industrial detection system. Control Engineering of China, 13(S1):220-222

席斌, 王振雷, 钱锋. 2006.机器视觉工业检测系统的应用与发展.控制工程, 13(S1):220-222

Xuan D M, Wang J Y, Yu H and Zhao J. 2015. Application of prior know ledge in deep learning. Computer Engineering and Design, 36(11):3087-3091

宣冬梅, 王菊韵, 于华, 赵佳. 2015.深度学习中先验知识的应用.计算机工程与设计, 36(11):3087-3091)[DOI:10.16208/j.issn1000-7024.2015.11.041]

Yan X H, Xu P L and Zhao X X. 2018. High precision change detection method based on high resolution remote sensing image. Geomatics and Spatial Information Technology, 41(10):184-186

闫小辉, 徐泮林, 赵晓旭. 2018.基于高分辨率遥感影像的高精度变化检测方法.测绘与空间地理信息, 41(10):184-186)[DOI:10.3969/j.issn.1672-5867.2018.10.056]

Yang H. 2009. Correction of uneven illuminated image for industrial inspection. Control and Automation, 25(21):244-245, 279

杨欢. 2009.应用于工业检测的光照不均匀图像的校正.微计算机信息, 25(21):244-245, 279)[DOI:10.3969/j.issn.1008-0570.2009.21.099]

Yang Y and Zhang W S. 2015. Image auto-annotation based on deep learning. Journal of Data Acquisition and Processing, 30(1):88-98

杨阳, 张文生. 2015.基于深度学习的图像自动标注算法.数据采集与处理, 30(1):88-98)[DOI:10.16337/j.1004-9037.2015.01.008]

Zhang H D. 2006. The Research on the Development of Fingerprint Identification System and Image Illumination Adjustment for Computer Vision. Dalian:Dalian University of Technology

张海东. 2006.指纹识别系统开发及视觉图像光照调整技术的研究.大连:大连理工大学

Zhang J J, Hu H L, Liu Z Y and Xie X S. 2011. Research and application of image enhancement algorithm in uneven brightness pipeline. Computer Engineering, 37(16):227-229

张建军, 胡惠灵, 刘征宇, 解新胜. 2011.光照不均管道内图像增强算法的研究与应用.计算机工程, 37(16):227-229)[DOI:10.3969/j.issn.1000-3428.2011.16.077]

Zhang J T. 2008. Diagnosis of Defects in the Inner Wall of Heat Equipment Based on Infrared Temperature Measurement. Chongqing:Chongqing University

张建涛. 2008.基于红外测温技术的工业热设备内部缺陷诊断方法.重庆:重庆大学

Zhang L N. 2016. Research on Image Correction and Fault Detection Algorithms for Non-uniform Illumination of Conveyor Belt. Tianjin:Tiangong University

张凌宁. 2016.输送带非均匀光照图像校正和故障检测算法研究.天津:天津工业大学

Zhang P and Zhu Z H. 2007. Machine vision technique and its application to automation of mechanical manufacture. Journal of Hefei University of Technology, 30(10):1292-1295

张萍, 朱政红. 2007.机器视觉技术及其在机械制造自动化中的应用.合肥工业大学学报(自然科学版), 30(10):1292-1295)[DOI:10.3969/j.issn.1003-5060.2007.10.016]

Zhang W. 2006. Development of machine vision and its industrial applications. Infrared, 27(2):11-17

章炜.机器视觉技术发展及其工业应用.红外, 27(2):11-17)[DOI:10.3969/j.issn.1672-8785.2006.02.003]

Zhang X L, Chen X W, Li F and Yang T. 2017. Change detection method for high resolution remote sensing images using deep learning. Acta Geodaetica et Cartographica Sinica, 46(8):999-1008

张鑫龙, 陈秀万, 李飞, 杨婷. 2017.高分辨率遥感影像的深度学习变化检测方法.测绘学报, 46(8):999-1008)[DOI:10.11947/j.AGCS.2017.20170036]

Zheng Y. 2017. Research on Surface Defect Detection System of Bearing Inner Ring Based on Machine Vision. Shenyang:Shenyang University of Technology

郑越. 2017.基于机器视觉的轴承内圈表面缺陷检测系统研究.沈阳:沈阳工业大学

Zhou S, Chang J M, Li D, Chen X, Wu M and Gan X L. 2017. Research on the positioning and recognition of industrial components based on computer vision. Ship Electronic Engineering, 37(9):114-116

周胜, 常君明, 李洞, 陈曦, 吴冕, 甘祥麟. 2017.基于计算机视觉的贴片元件定位检测算法研究.舰船电子工程, 37(9):114-116)[DOI:10.3969/J.ISSN.1672-9730.2017.09.025]

Zhou Z W, Shin J, Zhang L, Gurudu S, Gotway M and Liang J M. 2017. Fine-tuning convolutional neural networks for biomedical image analysis: actively and incrementally//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE: 4761-4772[ DOI: 10.1109/CVPR.2017.506 http://dx.doi.org/10.1109/CVPR.2017.506 ]