油封表面缺陷自动在线图像检测关键技术研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着工业生产自动化程度的不断提高,如何实现对多品种、大批量生产过程的实时在线检测一直是工业领域的难题和企业生产追求的目标。本课题结合油封企业的生产现状,依据企业产品质量标准,针对其提出的油封产品在线检测具体指标要求,设计搭建了油封缺陷的在线图像检测系统,以图像拼接与ROI分割、缺陷边缘检测以及缺陷分类识别为主线,对油封表面缺陷的图像检测技术理论与方法进行了系统深入的研究,提出了一系列针对性的、快速可靠的图像处理算法,形成了较为完整的油封缺陷在线检测的方法体系,并通过实验进行了对比分析。本文的主要研究工作如下:
     1)结合油封外观质量标准及企业生产要求,制定了油封在线图像检测系统的性能量化指标;设计了基于工业面阵CCD相机的远心光路图像采集系统、LED环形低角度照明系统以及油封夹持旋转机构,实现油封幅面圆周等分割成像采集,以满足高速、宽尺寸范围、高分辨率的检测要求,解决了成像视场范围和分辨力与系统硬件要求之间的优化配置问题。
     2)研究了图像配准和融合不同技术方法,针对油封环带等分子图像采集过程特点,借助旋转机构精密传动子系统的先验知识,通过刚性变换实现大尺寸油封的序列子图像的完整无缝拼接;考虑到油封不同环带区域的质量要求不一样,同一类型缺陷的量化指标差异较大,结合圆参数拟合和先验知识实现对油封图像ROI分割,以便后续图像处理。
     3)针对油封表面缺陷的特点及系统指标要求,研究了油封缺陷边缘检测的不同方法,并做了对比分析。利用小波变换的良好时频分析特性,提出了改进阈值的小波局部模极大值油封边缘检测方法;同时由于彩色图像的包含更多的边缘信息,提出了基于不同彩色空间的油封缺陷边缘检测方法;不同方法有着不同的特性表现。
     4)在分析油封表面不同类型缺陷的特点的基础上,定义了各类缺陷的不同特征参数空间,利用主分量分析方法对油封缺陷进行了有效特征抽取;研究探讨了支持向量机分类识别方法,对油封端面及唇口区域分别构建分类器,实现油封表面缺陷分类识别。
With the continuous improvement of the degree of industrial productionautomation, how to achieve the real-time online testing in the process of multi-species,mass production has long been the problem in industrial fields and the goal pursuedby production enterprises. Reference to product quality standards and combining withthe actual production situation of enterprises, this project is developed to detectsurface defects for oil seal based on image inspection technique. In view of thespecific requirements of oil seal online production and testing, a computer visioninspection system is set up, the theory and method of image detection technology foroil seal surface defects is discussed detailly, including ROI segmentation, imagemosaic, defect edge detection, defects classification and identification, etc. The mainwork included in the dissertation is shown as follows:
     1) According to oil seal surface quality standards and production requirements,the performance of oil seal defects testing system is quantified concretely. An onlineimage inspection system is designed and built, mainly including the image acquisitionsystem baed on telecentric lens and industrial CCD camera, the low angle ring LEDlighting system, and the oil seal clamp rotation mechanism. This scheme can achieveoil seal circumference equal portions image acquisition, fit the testing requirements ofhigh-speed, wide size range and high resolution, and optimize configuration of fieldof view, resolution and hardware.
     2) With a view to the characteristics of oil seal image decile acquisition process,a simple method is taken to realize oil seal sub-images mosaic with priori knowledgeand rigid transformation. Taking into account the difference of the qualityrequirements of oil seal different ring regions, that is the same type of defect indifferent region being quantified differently, oil seal ROI segmentation can solve theproblem and simply the following image processing.
     3) Considering the particularity of oil seal surface defects and systemspecifications, a few different approaches to detect oil seal defects’ edge are putforward in detail and their effects comparison are analyzed. An improved thresholdwavelet local modulus maxima edge detection method is presented owing to thetime-frequency performance of wavelet transform. Meanwhile because of color imagecontaining more edge information, the oil seal surface defects detection methods based on different color space are advanced. Different oil seal defects’ edge detectionapproaches have their own particularity.
     4) In connect with the speciality of various surface defects of oil seal, thedissertation not only defines the feature parameter space of defects’ type, but alsotakes advantage of the principal component analysis method to extract effectivefeatures for oil seal defects classification. Meanwhile the project explores the supportvector machine classification and recognition method detailedly, builds classifiers foroil seal upper end area and lip area respectively, and fufills oil seal surface defectsclassification and identification.
引文
[1]谷口庆治,数字图像处理,北京:科学技术出版社,2002
    [2]冈萨雷斯著,阮秋琦等译,数字图像处理,北京:电子工业出版社,2003
    [3]朱志刚,石定机,数字图像处理,北京:电子工业出版社,2002
    [4] Marr D.,视觉计算理论,北京:科学出版社,1988
    [5]徐光佑,计算机视觉,北京:清华大学出版社,1999
    [6]贾云德,机器视觉,北京:科学出版社,2000
    [7]林学訚,王宏,计算机视觉——一种现代方法,北京:电子工业出版社,2004
    [8]章毓晋,图像工程:图像理解与计算机视觉,北京:清华大学出版社,2000
    [9]郑南宁,计算机视觉与模式识别,北京:国防工业出版社,1998
    [10] R. M. H, L.G. Shapire, Glossary of computer vision terms, Pattern Recognition,1991,24(1):63-93
    [11] A. D. Marshall, R. R. Martin, Computer Vision Models and Inspection,1992
    [12]崔杨,图像检测技术在皮革缺陷检测中的应用研究,博士学位论文,浙江大学,2004
    [13] D. German, Vision aided inspection techniques for the automotive industry, Proc.of the Society of Manufacturing Engineers Conf. on Vision,1985:1-7
    [14] W. J. Pastorius, Vision measures up in automated assembly, Manufacturing Eng.,1989,4:81~83
    [15]陈世哲,微电子产品视觉检测中关键技术研究,博士学位论文,哈尔滨工业大学,2006
    [16]陈向伟,机械零件计算机视觉检测关键技术的研究,博士学位论文,吉林大学,2005
    [17]孙长库,叶声华,激光测量技术,天津大学出版社,2000
    [18]王庆有,图像传感器应用技术,北京:电子工业出版社,2003
    [19] W. A. Perkins, A computer vision system which learn to inspect parts, IEEETrans, PAMI-5:584-592
    [20]朱铮涛,基于计算机视觉图像精密测量的关键技术研究,博士学位论文,华南理工大学,2004
    [21]孙双花,视觉测量关键技术及在自动检测中的应用,博士学位论文,天津大学,2007
    [22] L. Angrisani, P. Daponte, A. Pietrosanto, etal, An image-based measurementsystem for the characterization of automotive gaskets, Measurement,1999,25:169-181
    [23] T. J. Kang, S. H. Choi, S. M. Kim, Automatic structure analysis and objectiveevaluation of woven fabric using image analysis,Textile Res,2001,71(3):261-270
    [24]赵彦玲,基于图像技术的钢球表面缺陷分析与识别,博士学位论文,哈尔滨理工大学,2008
    [25]顾妍午,李平,陶文华等,基于改进BP神经网络的手写邮政编码识别,辽宁石油化工大学学报,2008,28(1):52-54
    [26]高一凡,王选仓,条形码在交通管理中的应用,交通与计算机,1996,14(2):53-58
    [27]刘君,郭晓然,晏克俊,基于IMAQ Vision的小模数直齿圆柱齿轮测量方法研究,仪器仪表学报,2008,29(5):1044-1048
    [28]张洪涛,钢板表面缺陷在线视觉检测系统关键技术研究,博士学位论文,天津大学,2008
    [29] J. J. Eillis, W. J. Hill, Automatic inspection of cold rolled stee1strip, Proc. IEEEInt. Conf. on Image Processing,1982:134-138
    [30] J. F. Bremner, Automatic vision inspection system for the inspection of shapescut in sheet material, Proc. On Image Processing,1986:40-43
    [31] N. Aleixos, J. Blasco, F. Navarron, etal, Multispectral inspection of citrus inreal-time using machine vision and digital signal processors, Computer andElectronics in Agriculture,2002,33:121-137
    [32] W. S. Wilson, The role of vision in a dimensional control strategy, Proc. of theSociety of Manufacturing Engineers Conf. on Vision Section7,1985:43-55
    [33] M. M. Landman, S. J. Roberton, A flexible industrial system for automatedthree-dimensional inspection, SPIE,1986:203-209
    [34] T. S. Newman, A. K. Jain, A system for3D cad-based inspection using rangeimages, Pattern Recognition,1995,28(10):1555-1574
    [35]张变莲,车辆牌照识别系统关键技术研究,硕士学位论文,中国科学院西安光学精密机械研究所,2006
    [36]李超,基于视觉的合金圆锯片锯齿角度测量方法研究,硕士学位论文,天津大学,2009
    [37]彭向前,产品表面缺陷在线检测方法研究及系统实现,博士学位论文,华中科技大学,2008
    [38]雷良育,周晓军,潘明清,基于机器视觉的轴承内外径尺寸检测系统,农业机械学报,2005,36(3):131-134
    [39]黄俊敏,吴庆华,周金山等,基于机器视觉的二维高精度手机玻璃屏尺寸测量仪,计算机测量与控制,2009,17(9):1863-1865
    [40] F. Lahajnar, R. Bernard, F. Pernus, etal. Machine vision system for inspectingelectric plates, Computer in Industry,2002,47(1):113-122
    [41] Q.Z. Li, M.H. Wang, etal. Computer vision based system for apple surface defectdetection, Computers and Electronics in Agriculture,2002,36(3):215-223
    [42] H.Zheng, L.X.Kong, etal. Automatic inspection of metallic surface defects usinggenetic algorithms, Journal of Materials Proeessing Technology,2002,125-126:427-433
    [43]张进,微型零件高精度影像测量系统中关键技术研究,博士学位论文,天津大学,2010
    [44]刘斌,微小三维尺寸自动光学检测系统的关键技术研究,博士学位论文,天津大学,2010
    [45] Dimitrios, Kosmopoulos, etal, Automated inspection of gaps on the automobileproduction line through stereo vision and specular reflection, Computer inIndustry,2001,46:49-63
    [46]刘常杰,邾继贵,杨学友等,汽车白车身在线激光视觉检测站,仪器仪表学报,2004,25(4):671-672
    [47]叶声华,王仲,精密测试技术展望,中国机械工程,2000,11(3):262-263
    [48] R. S. Lu, On-line measurement of the straightness of seamless steel pipes usingmachine vision technique, Sensors and Actuators,2001,94:417-427
    [49] Q. Dajle, On-line inspection of extruded profile geometry, Vision ‘90,1990:1-17
    [50] C. C. Mu, Roundness measurement for discontinuous perimeters via machinevision, Computer in Industry,2002,4:185-197
    [51]牟洪波,基于BP和RBF神经网络的木材缺陷检测研究,博士学位论文,东北林业大学,2010
    [52]杨铁滨,基于机器视觉的陶瓷球表面缺陷自动检测技术研究,博士学位论文,哈尔滨工业大学,2007
    [53]赵铁成,张银桥,徐伟勇,新型火焰图像检测器及其着火判据,仪器仪表学报,2002,23(1):98-100
    [54]胡涛涛,樊祥,马东辉等,基于时空域融合的红外弱小目标检测算法,弹箭与制导学报,2011,31(2):225-227
    [55]崔扬,周泽魁,数字图像处理在无人值守变电站智能监控中的应用,电站系统工程,2004,20(3):47-49
    [56]张云辉,谭庆昌,田原嫄,图像测量系统精度影响因素的研究,微计算机信息,2008,24(8-3):271-273
    [57]于殿泓,图像检测与处理技术,西安:西安电子科技大学出版社,2006
    [58]郁道银,谈恒英,工程光学,北京:机械工业出版社,2000
    [59]孔祥伟,组合光源与图像处理算法在工件表面缺陷检测中的应用,硕士学位论文,天津大学,2007
    [60] S. K. Kopparapu, Lighting design for machine vision application, Image andVision Computing,2006,24:720-726
    [61]申晓彦,用于视觉检测的光源照明系统分析,灯与照明,2009,33(3):7-9
    [62] M. Vriesenga, G. Healey, K. Peleg, etal, Controlling illumination color toenhance object discriminability, Computer Vision and Pattern Recognition,1992,Proceedings CVPR’92.,1992IEEE Computer Society Conference on
    [63]解凯,郭恒业,张田文,图像Mosaics技术综述,电子学报,2004,32(4):630-634
    [64]于明言,一种基于时域和频域特征的图像拼接方法,硕士学位论文,大连理工大学,2006
    [65] G. B. Lisa, A survey of image registration techniques, ACM ComPuting Surveys,1992,24(4):325-37
    [66] C. F. Lin, C. L. Lee, An accurate method for image registration, PatternRecognition and Image Analysis,2000,10(3):343-355
    [67]王娟,师军,吴宪祥,图像拼接技术综述,计算机应用研究,2008,25(7):1940-1943
    [68]赵文彬,张艳宁,角点检测技术综述,计算机应用研究,2006,23(10):17-19
    [69]刘小军,周越,基于轮廓特征的SAR图像自动配准,计算机工程,2007,33(4):176-178
    [70] D. G. Lowe, Distinctive image features from scale-invariant keypoints,International Journal of Computer Vision,2004,60(2):91-110
    [71]李忠新,茅耀斌,王执铨,基于对数极坐标映射的图像拼接方法,中国图像图形学报,2005,10(1):59-63
    [72] S. Reddy, J. B. Chatter, An FFT-based technique for translation, rotation, andscale-invariant image registration, IEEE Trans on Image Process,1996,3(8):1266-1270
    [73] G. Woberg, I. S. Zoka, Robust image registration using log-polar transform, Procof IEEE Int Conf on Image Processing, Piscateway: IEEE,2000:493-496
    [74] Y. Keller, A. Averbuch, M. Isael, Pseudopolar based estimation of largetranslations, rotations, and scalings in images, IEEE Trans on Image Processing,2005,14(1):12-22
    [75] H. Z. Liu, B. L. Guo, Z. Z. Feng, Pesudo-log-polar Fourier transform for imageregistration, IEEE Signal Processing Letters,2006,13(1):17-20
    [76] P. Viola, M. Wellsw, A lignment by maximization of mutual information,International Journa l of Computer Vision,1997,24(2):137-154
    [77]肖李,卢凌,黄红星,基于改进IHS变换的图像融合方法,武汉理工大学学报,2003,27(1):41-42
    [78]夏明革,何友,欧阳文等,基于小波分析的图像融合评述,红外与激光工程,2003,32(2):177-181
    [79] W. Ni, B. L. Guo, L. Yang, Data fusion of multisensor remote sensing imagesusing region based Contourlet contrast, Journal of Astronautics,2007,28(2):364-369
    [80]杨翠,图像融合与配准方法研究,博士学位论文,西安电子科技大学,2008
    [81]李志刚,纪玉波,薛全,边界重叠图像的一种快速拼接算法,计算机工程,2000,26(5):37-38
    [82]樊庆文,王小龙,侯力等,基于等距序列图像的快速拼接技术,四川大学学报(工程科学版),2005,37(1):139-14
    [83]吴福,于满川,旋转图像序列的整合,模式识别与人工智能,1999,3(12):249-254
    [84] C.Gonzaez, E.Woods, Digital Image Processing, Publishing House of ElectronicsIndustry,2003
    [85]章毓晋,图像分割,北京:科学出版社,2001
    [86]刘海宾,何希勤,刘向东,基于分水岭和区域合并的图像分割算法,计算机应用研究,2007,24(9):307-308
    [87]段瑞玲,李庆祥,李玉和,图像边缘检测方法研究综述,光学技术,2005,31(3):415-419
    [88]曾俊,图像边缘检测技术及其应用研究,博士学位论文,华中科技大学,2011
    [89]姜杭毅,蔡云龙,用于边缘检测的Laplace样条算子,中国科学(A辑),1989,10(1):113-120
    [90] J. Canny, A computational approach to edge detection, IEEE Transactions onPattern Analysis and Machine Intelligence,1986,8(6):679-698
    [91] S. M. Smith, J. M. Brady, SUSAN-A new approach to low level imageprocessing, International Journal of Computer Vision,1997,23(1):45-78
    [92]孙延奎,小波分析及其应用,北京:机械工业出版社,2005
    [93]杨福生,小波变换的工程分析与应用,北京:科学出版社,2000
    [94] S. G. Mallat, A theory for multiresolution signal decomposition: the waveletrepresentation, IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693
    [95] S. G. Mallat, Multifrequency channel decompositions of images and waveletmodels. IEEE Transactions on Acoustics, Speeeh, and Signal Proeessing,1989,37(12):2091-2110
    [96]丁兴号,基于小波分析的视觉检测技术研究,博士学位论文,合肥工业大学,2003
    [97]陈武凡,小波分析及在图像处理中的应用,北京:科学出版社,2002
    [98]陈东,用多尺度变换进行边缘检测算法的研究,计算机工程与设计,1998,19(2):35-37
    [99]王丽荣,基于小波变换的目标检测方法研究,博士学位论文,吉林大学,2006
    [100]连静,基于B样条小波的自适应阈值多尺度边缘检测,吉林大学学报(工学版),2005,35(5):542-546
    [101]唐良瑞,基于小波高频分量的边缘检测算法,北方工业大学学报,2002,3(1):13-16
    [102] T. R. Dowine, B. W. Silverman, The discrete muitiple wavelet transform andthresholding methods, IEEE Transactions on Signal Proeessing,1998,46(9):2558-2561
    [103] M. Stephane, W. L. Hwang, Singularity detection and proeessing with wavelets,IEEE Transactions on Infonnation Theory,1992,38(2):617-643
    [104]赵学智,奇异性信号检测时小波基的选择,华南理工大学学报,2000,28(10):75-80
    [105]袁野,欧宗瑛,基于小波变换和模糊算法医学图像边缘检测算法,大连理工大学学报,2002,7(4):504-508
    [106] X. J. Li, Mathematical morphological edge for noisy image corrupted byimpulses, Journal of Image and Graphics,1998,3(11):903-906
    [107] Z. Hou, T. Koh, Robust edge detection, Pattern Recognition,2003,36(9):2083-2091
    [108] C. E. Hei, D. F. Walnut, Continuous and discrete wavelet transforms, SLAMReview,1989,31(4):628-666
    [109]庄宇飞,小波变换在图像边缘检测中的应用研究,硕士学位论文,哈尔滨工业大学,2007
    [110] M. Jansen, A. Bultheel, Multiple wavelet threshold estimation by generalizedcross validation for images with correlated noise, IEEE Transactions on ImageProeessing,1999,8(7):947-953
    [111] S. Paul, A multivalued image wavelet representation based on multiscalefundamental forms, IEEE Trans., Image Processing,2002,10(5):568-575
    [112]蒋晓悦,赵荣椿,B样条小波在图像边缘检测中的应用,中国视觉学与图像分析,2002,12(7):198-201
    [113] M. User, A. Aldroubi, M. Eden, On the asymptotic convengence of B-splinewavelet to gabor function, IEEE Trans.,1992,38(2):864-872
    [114]张宏群,张雪,肖旺新,小波变换的自适应阈值图像边缘检测方法,红外与激光工程,2003,32(1):164-168
    [115]余见,彩色图像边缘检测和分类,硕士学位论文,厦门大学,2008
    [116]计润生,高隽,范之国等,彩色空间及空间上的彩色图像边缘检测,仪器仪表学报,2006,27(6):724-726
    [117]王文明,赵荣椿,不同彩色空间的彩色图像边缘检测研究,计算机测量与控制,2006,14(12):1607-1610
    [118]朱方,万百五,梁德群,基于矢量的彩色图像边缘检测,计算机工程与应用,2001,37(23):106-108
    [119]严奉霞,罗建书,一种新的彩色图像边缘检测方法,中国图形图像学报,2003,1(32):27-31
    [120] R. Nevatia, A color edge detector and its use in scene segmentation, IEEE Trans.Systems, Man, and Cybernetics,1977,7(11):820-826
    [121] M. Huekel, An operator which locates edges in digitized pictures, J.ACM,1971,18(1):113-125
    [122] A. Koschan, M. Abidi, Detection and classification of edges in color images,IEEE Signal Processing Magazine,2005,22(1):64-73
    [123] A.Cumani, Edge detection in multispectral images, CVGIP: Graphical Modelsand Image Processing,1991,53(1):40-51
    [124] J. Scharcanski, A. N. Venetsanopoulos, Edge detection of color images usingdirectional operators, IEEE Trans. Circuits Syst. Video Technol.,1997,7(2):397-401
    [125] P. E. Trahanias, A. N. Venetsanopoulos, Vector order statistics operators ascolor edge detectors, IEEE Trans. Syst. Man and Cybern.,1996,26:135-143
    [126] H. C. Chen, W. J. Chen, S. J. Wang, Contrast based color image segmentation,IEEE Signal Processing Letters,2004,11(7):641-644
    [127] T. Caroon, P. Lambert, Color edge detector using jointly Hue,Saturation,Intensity, ICIP1994,(3):977-981
    [128]曾俊,李德华,彩色图像SUSAN边缘检测方法,计算机工程与应用,2011,47(15):194-196
    [129]吕明忠,罗鹏,高敦岳,一种基于色差的彩色图像的边缘检测方法,华东理工大学学报,2001,27(5):561-564
    [130]边肇祺,张学工,模式识别,北京:清华大学出版社,2002
    [131]王萍,杨培龙,罗颖昕译,统计模式识别,北京:电子工业出版社,2004
    [132]杨帆,数字图像处理与分析,北京:北京航空航天大学出版社,2007
    [133]何晓群,多元统计分析,北京:中国人民大学出版社,2008
    [134]蒋艳凰,赵强利,机器学习方法,北京:电子工业出版社,2009
    [135] V. Vapnik,The nature of statistical learning theory, New York: Springer Press,1995
    [136]祁享年,支持向量机及其应用研究综述,计算机工程,2004,30(10):6-9
    [137]张学工,关于统计学习理论与支持向量机,自动化学报,2000,26(1):32-42
    [138] S. S. Keerthi, C. T. Lin, Asymptotic behaviors of support vector machines withGaussian kernel, Neural Computation,2003,15(7):1667-1689
    [139]唐发明,王仲东,陈绵云,支持向量机多类分类算法研究,控制与决策,2005,20(7):746-749
    [140]刘志刚,李德仁,秦前清等,支持向量机在多类分类问题中的推广,计算机工程与应用,2004,(7):10-13
    [141] C. Hsu, C. A. Lin, Comparison of methods for multiclass support vectormachines, IEEE Trans. Neural Networks,2002,3(2):415-425
    [142]黄勇,郑春颖,宋忠虎,多类支持向量机算法综述,计算机技术与自动化,2005,24(4):61-63
    [143]陈光英,张千里,李星,特征选择和SVM训练模型的联合优化,清华大学学报(自然科学版),2004,44(1):9-12
    [144]业宁,支持向量机若干基础研究及其在图像识别中的应用,博士学位论文,东南大学,2006
    [145]贺秋伟,王龙山,于忠党等,基于图像处理和支持向量机的微型齿轮缺陷检测,吉林大学学报,2008,38(3):565-569
    [146]刘元祥,张晓光,高顶,基于支持向量机的射线检测焊接图像中缺陷识别,煤矿机械,2006,27(5):773-776
    [147]袁浩,付忠良,程建等,基于支持向量机的纸张缺陷图像分类识别,计算机应用,2008,28(2):330-332
    [148]朱凌云,曹长修,基于支持向量机的缺陷识别方法,重庆大学学报,2002,25(6):42-45

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700