钢板表面缺陷在线视觉检测系统关键技术研究
|
摘要
钢板表面缺陷在线检测技术已成为钢铁生产企业向现代化制造业高效率、自动化与智能化方向发展的制约因素,同时也是国内外学者研究的热点领域。本文依托科技部科研院所专项基金项目——“钢板表面缺陷计算机视觉在线检测系统研制”,针对系统宽幅面、简单性、模块化、先进性等技术要求,结合国内外表面缺陷检测技术发展方向,确立了以计算机视觉检测技术线阵CCD扫描法为检测原理的钢板表面缺陷检测系统研制方案,并对检测系统关键技术进行讨论。本文主要研究内容与完成工作如下:
1.设计了基于线阵CCD扫描、幅面分割的钢板表面缺陷在线视觉检测系统方案,以满足高速、宽幅面、高分辨率的检测要求,同时针对钢板表面缺陷特点,通过优化配置明、暗域成像模型,以检出各类形态缺陷;
2.为解决高速运动场景下光源照明问题,设计了狭缝式高频荧光灯光源,其具有亮度高、均匀性好、稳定性高及成本低等特点;
3.针对钢板表面缺陷特点及系统指标要求,充分讨论了钢板表面缺陷图像处理算法流程,并针对各处理步骤给出了实现算法。系统可检出钢板主要缺陷,如孔洞、夹杂、划痕、氧化铁皮、斑点等。通过算法优化及采用多线程程序结构,在满足精度指标要求情况下,其处理速度能满足钢板2m/s的运行速度要求;
4.在仔细分析钢板表面缺陷特点基础上,本文定义了缺陷特征参数空间,并讨论了决策树、贝叶斯分类器和神经网络分类算法,重点讨论了BP神经网络算法,其缺陷识别率达到90%。由于各种分类算法的局限性,本文也重点讨论了集成分类器,集成分类器通过各种分类器的优势互补,可有效分类各种缺陷;
5.提出了整套软件系统框架结构设计方案,即采用多进程架构、基于流水线工作原理和实时采集+准实时处理融合的技术方案。采用优化的多线程程序结构设计采集应用进程,使其数据采集率达到100Mbps,完全满足系统检测要求。为减轻图像准实时处理系统的负荷,实时采集应用进程不仅完成图像数据采集,而且同时进行ROI(Region of Interest)检测;准实时处理应用进程处理ROI图像文件,并提取各个缺陷的特征数据以进行模式分类;
6.设计并实现了两套实验样机系统:平动低速模拟系统与高速转动模拟系统,实验中运行的最高速度为1.5m/s。最后通过实验验证了系统方案的可行性。本课题在2007年1月顺利通过国家科技部专家组验收。
The technique of on-line surface defects detection for steel plate has become the restriction of the Steel and Iron production enterprises developing to the modernized manufacturing industry with high efficiency, intellectualization and automation, so it’s been a hot field researched by foreign and domestic scholars. Sponsored by scientific research academe specific fund of NSTS, the project is developed to detect surface defects for steel plate based on computer vision. In view of systematic specifications, such as broad width, simplicity, modularization, advancement etc, and combining with the latest development of relevant theory and technology, the scheme of linear CCD scanning method based on computer vision is brought forward to realize on-line non-destructive surface inspection for steel plate, and key technology of system is discussed. The main work included in the dissertation is shown as follows:
1. In order to satisfy the requirements of high speed, broad width and high resolution, the linear CCD scanning scheme is put forward to detect the surface defects of steel plate based on width division using on-line computer vision. Taking the characteristics of surface defects into account, optimal configuration of receiving mode containing bright-field and dark-field is analyzed to make defects effectively detected;
2. The slit-type high-frequency fluorescent lamp is designed, solving the problem of luminance under high speed movement, and this light source has some excellent characteristics, such as high brightness, good uniformity, high stability and low cost and so on;
3. With a view to the characteristics of surface defects for steel plate and the demand of system performance, the algorithm flow of image-processing applied to the surface defect of steel plate is fully discussed, and feasible algorithm is presented at each processing step in the paper, Main surface defects such as hole, inclusion, rolling skin, scratch and roll-mark can be detected. Under the condition of meeting the precision, the application is realized using the optimized algorithm and multi-thread procedure structure, so its processing speed could satisfy the 2m/s running rate of steel plate.
4. The dissertation not only defines spatial distribution of surface defects based on its speciality, but also discusses some pattern recognition methods, such as decision tree, Bayes classifier, nervous network means, and it also makes a specific exposition about BPNN that the rate of classifying defects is more than 90%. Because of the limitation of each classifier, compositive classifier is mainly discussed in the paper, making use of each others' advantages to effectively classify defects.
5. Adopted multi-process scheme including real-time gathering system + near-real time processing system, and based on pipe-line theory, software structure is proposed in this paper. The optimized multi-thread procedure structure is introduced to the capturing application to realize the high speed acquiring, and the rate of capturing data reaches to 100Mbps, so it meets the requirement of system. In order to reduce the load of image-processing application, the real-time application not only captures image data, but also simultaneously detects ROI (Region of Interest) data. Near-real time processing system processes ROI file, and extracts special data of defects to distinguish the type of defect.
7. Two kinds of prototype, including low speed translational prototype and high speed rotary prototype simulation systems, are developed. The highest speed is 1.5m/s in the experiment. Feasibility and validation is verified through experiments.
This project was checked and accepted smoothly by Ministry of Science and Technology at January 2007.
1.设计了基于线阵CCD扫描、幅面分割的钢板表面缺陷在线视觉检测系统方案,以满足高速、宽幅面、高分辨率的检测要求,同时针对钢板表面缺陷特点,通过优化配置明、暗域成像模型,以检出各类形态缺陷;
2.为解决高速运动场景下光源照明问题,设计了狭缝式高频荧光灯光源,其具有亮度高、均匀性好、稳定性高及成本低等特点;
3.针对钢板表面缺陷特点及系统指标要求,充分讨论了钢板表面缺陷图像处理算法流程,并针对各处理步骤给出了实现算法。系统可检出钢板主要缺陷,如孔洞、夹杂、划痕、氧化铁皮、斑点等。通过算法优化及采用多线程程序结构,在满足精度指标要求情况下,其处理速度能满足钢板2m/s的运行速度要求;
4.在仔细分析钢板表面缺陷特点基础上,本文定义了缺陷特征参数空间,并讨论了决策树、贝叶斯分类器和神经网络分类算法,重点讨论了BP神经网络算法,其缺陷识别率达到90%。由于各种分类算法的局限性,本文也重点讨论了集成分类器,集成分类器通过各种分类器的优势互补,可有效分类各种缺陷;
5.提出了整套软件系统框架结构设计方案,即采用多进程架构、基于流水线工作原理和实时采集+准实时处理融合的技术方案。采用优化的多线程程序结构设计采集应用进程,使其数据采集率达到100Mbps,完全满足系统检测要求。为减轻图像准实时处理系统的负荷,实时采集应用进程不仅完成图像数据采集,而且同时进行ROI(Region of Interest)检测;准实时处理应用进程处理ROI图像文件,并提取各个缺陷的特征数据以进行模式分类;
6.设计并实现了两套实验样机系统:平动低速模拟系统与高速转动模拟系统,实验中运行的最高速度为1.5m/s。最后通过实验验证了系统方案的可行性。本课题在2007年1月顺利通过国家科技部专家组验收。
The technique of on-line surface defects detection for steel plate has become the restriction of the Steel and Iron production enterprises developing to the modernized manufacturing industry with high efficiency, intellectualization and automation, so it’s been a hot field researched by foreign and domestic scholars. Sponsored by scientific research academe specific fund of NSTS, the project is developed to detect surface defects for steel plate based on computer vision. In view of systematic specifications, such as broad width, simplicity, modularization, advancement etc, and combining with the latest development of relevant theory and technology, the scheme of linear CCD scanning method based on computer vision is brought forward to realize on-line non-destructive surface inspection for steel plate, and key technology of system is discussed. The main work included in the dissertation is shown as follows:
1. In order to satisfy the requirements of high speed, broad width and high resolution, the linear CCD scanning scheme is put forward to detect the surface defects of steel plate based on width division using on-line computer vision. Taking the characteristics of surface defects into account, optimal configuration of receiving mode containing bright-field and dark-field is analyzed to make defects effectively detected;
2. The slit-type high-frequency fluorescent lamp is designed, solving the problem of luminance under high speed movement, and this light source has some excellent characteristics, such as high brightness, good uniformity, high stability and low cost and so on;
3. With a view to the characteristics of surface defects for steel plate and the demand of system performance, the algorithm flow of image-processing applied to the surface defect of steel plate is fully discussed, and feasible algorithm is presented at each processing step in the paper, Main surface defects such as hole, inclusion, rolling skin, scratch and roll-mark can be detected. Under the condition of meeting the precision, the application is realized using the optimized algorithm and multi-thread procedure structure, so its processing speed could satisfy the 2m/s running rate of steel plate.
4. The dissertation not only defines spatial distribution of surface defects based on its speciality, but also discusses some pattern recognition methods, such as decision tree, Bayes classifier, nervous network means, and it also makes a specific exposition about BPNN that the rate of classifying defects is more than 90%. Because of the limitation of each classifier, compositive classifier is mainly discussed in the paper, making use of each others' advantages to effectively classify defects.
5. Adopted multi-process scheme including real-time gathering system + near-real time processing system, and based on pipe-line theory, software structure is proposed in this paper. The optimized multi-thread procedure structure is introduced to the capturing application to realize the high speed acquiring, and the rate of capturing data reaches to 100Mbps, so it meets the requirement of system. In order to reduce the load of image-processing application, the real-time application not only captures image data, but also simultaneously detects ROI (Region of Interest) data. Near-real time processing system processes ROI file, and extracts special data of defects to distinguish the type of defect.
7. Two kinds of prototype, including low speed translational prototype and high speed rotary prototype simulation systems, are developed. The highest speed is 1.5m/s in the experiment. Feasibility and validation is verified through experiments.
This project was checked and accepted smoothly by Ministry of Science and Technology at January 2007.
引文
[1]徐光佑,计算机视觉,北京:清华大学出版社,1999.11
[2] Marr D.,视觉计算理论,科学出版社,1988
[3]张洪涛,荫罩板计算机视觉检测系统研究:[硕士学位论文],天津;天津大学,2002
[4]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
[5]李金宗,模式识别导论,北京:高等教育出版社,2000
[6]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
[7]王庆有,图像传感器应用技术,北京:电子工业出版社,2003
[8]刘凌,胡永生,数字信号处理的FPGA实现,北京:清华大学出版社,2003
[9] W.S.Wilson, The role of vision in a dimensional control strategy, Proc. of the Society of Manufacturing Engineers Conf. on Vision Section 7, 1985: 43～55
[10] Carpenter G A, Grossberg S. Neural network for vision and image processing[M]. Lexington: MIT Press, 1992
[11] Simonis M P,余永桂译,频闪法在带钢表面检查中的应用,世界钢铁,1994,23(4):65～68
[12]胡学雄,陶军,黎润民,涡流检测技术在宝钢热轧轧辊上的应用,2004,21(5)::65~67
[13]吴平川,带钢表面自动检测系统研究现状与展望,钢铁,2000,36(6):70～75
[14] Hiroshi Maki., Magnetic on-line defect inspection system for strip steel, Iron and Steel Engineer, 1993(1):56～59
[15] Okamoto Y, Kaminaga F, Osakabe Metal.,Detection of surface flaw by infrared radiation sensor. The 7th Sensor Symposium, Tokyo: Institution of Electric Engineers of Japan, 1988:107～112
[16] M.M.Landman, S.J.Roberton, A flexible industrial system for automated three-dimensional inspection, SPIE, 1986, 728:203～209
[17] Reinhard Rinn, Michael Becker, Ralph Foehr, Friedrich Luecking. Steel Mill Defect Detection and Classification of 3000ft./min. Using Mainstream Technology.1998, SPIE Vol.3303 0277～786
[18]何秩,超声波传感器在宝钢钢卷检测中的应用,电工技术,2003,10:64～65
[19] Suresh BR, Fundakowski RA, Levitt TS etal. A realtime automated visual inspection system for hot steel slabs. IEEE Trans Pattern Anal Machine Intell, 1983,PAMI-5(6):563～572
[20] Reinhard Rinn,Scott A.Thompson., One year of experience with the new generation of automatic hot mill inspection systems.ASIE Steel Technology, June 2000:56～61
[21]孟宪超,轧制带钢表面缺陷的检测及识别方法的研究:[硕士学位论文],哈尔滨:哈尔滨工业大学,1996
[22] McManus, George J., Automatic Surface Inspection of Sheet, Iron and steel Engineer, March 1999:56～58
[23]罗志勇等,带钢表面缺陷检测系统的发展,钢铁,1996增刊:127～131
[24] Fred Treiber., On-line Automatic Defect Detection and Surface Roughness Measurement of Steel Strip. Iron and Steel Engineer, 1989, 66(9):26～33
[25]吴平川,机器视觉与钢板表面缺陷的无损检测,无损检测,2000,22(l):13～16
[26]吴平川,带钢表面缺陷机器视觉识别方法的研究:[博士学位论文],哈尔滨:哈尔滨工业大学,2000
[27] Chris A.Carisetti,Theodore Y.Fong,Charles Fromm,iLearn self- learning defect classifier. Iron and Steel Engineer,1998,75(8):50～53
[28]罗志勇,用线列CCD测量钢板宽度和检测孔洞缺陷的信号处理,1991.12(1):37～41
[29]胡亮,线阵CCD实现钢板表面缺陷在线检测关键技术及其应用研究:[博士学位论文],天津:天津大学,2006
[30] Mike Muehlemann. Standardizing Defect Detection for the Surface Inspection of Large Web Steel. Illumination Technologies ,Inc .2000
[31] Parsytec Computer Corp . Software controlled on-line surface inspection.Steel Times International,1998,22(3):30~34
[32]皮敏捷,徐科,基于多条激光线的钢板表面缺陷三维检测方法,机电产品开发与创新,2007,20(2):123～125
[33]宋强,徐科,徐金梧,基于结构谱的中厚板表面缺陷识别方法,北京科技大学学报,2007,29(3):342~345
[34]吴平川,路同浚,钢板表面缺陷的无损检测技术与应用,无损检测,2000,22(7):312～315
[35]杨洲,李明君,高磊,浅析压力容器应力腐蚀及其控制措施,石油化工设备,2007,36(B08):41～43
[36]周家齐,热轧钢板表面缺陷浅析,重钢技术,1991,2(34):32～36
[37]徐科等,冷轧带钢表面自动监测系统的研究,钢铁,2000,35(10):63
[38] K. Wiltschi, A. Pinz, T. Lindeberg, Automatic assessment scheme for steel quality inspection, Machine Vision and Applications,2000(12):113～128
[39] Obeso,F,Gonzalez J A,Brown A.Intelligent on-line Surface Inspection on A Skinpass.Iron and Steel ,1997(10):29～35
[40] http://www.parsytec.de/77_894.html
[41]相泽均等著,周源译.冷轧带钢表面缺陷检测系统,世界钢铁,1994,21(2):66～73
[42] Ceracki, P., Lücking, F., Reizig, H.-J., On-line defect recognition in hot strip by automatic surface inspection, Stahl und Eisen, 1999, 4: 77～81
[43] Tony WA., Automated inspection of metal products not quite ready for prime time. Iron & Steel Making, 1992,19(1):14～19
[44]罗志勇,刘栋玉,江涛等.新型冷轧带钢表面缺陷在线检测系统.华中理工大学学报,1996,24(1):75～78
[45] Yngve Strom., Automatic surface inspection of continuously cast billets. Iron and Steel Engineer, 1992,69(5):29～33
[46] Fred Treiber. On-line automatic defect detection and surface roughness measurement of steel strip. Iron and Steel Engineer, 1989, 66(9):26～33
[47] Thomas F Porter, Robert A Sytvester, Theodore W Bouyoucas et al. Automatic strtp surface defect detection system. Iron and Steel Engineer, 1988,65(12):17～20
[48]开发合同技术书,天津大学,2002.6
[49]骆文博,王广志,丁海曙等,基于线阵CCD的高精度位置检测,清华大学学报(自然科学版),2002,42(9):1139～1143
[50] John C Badger, Sean T Enright., Automated surface inspection system. Iron and Steel Engineer, 1996, 73 (3):48～51
[51] David G Park,Martin P Levoi,Haneghem AI van.Practical application of on-line hot strip inspection system at hoogovens . Iron and Steel Engineer,1995,72(7): 40～43
[52]阳运平,镀锡板表面缺陷在线检测方法与系统的研究:[硕士学位论文],北京:清华大学,1997
[53]郁道银等,工程光学,北京:机械工业出版社,1998
[54]郝允祥等,光度学,北京:北京师范大学出版社,1987
[55]周斌,刘秉琦,面阵CCD用于光场能量探测的研究,军械工程学院学报,2004,16(3):29～32
[56]何梓滨,视觉检测系统光学照明系统设计:[学士学位论文],天津:天津大学,2006
[57] P2-04k30 User Manual, Dalsa Inc., Cananda
[58] Ryuji Suyama,Kei Tanemoto,Yoshinari Kobayashi et al.,Autofocusing system of optical microscope utilizing electrostric-tive actuators.JpnJAppl Phys.,1991,30(6):1290～1294
[59] Fernandez, C., Platero, C., Campoy, P., Aracil, R.. Vision System for On-line Surface Inspection in Aluminum Casting Process. Industrial Electronics, Control, and Instrumentation, 1993(3):1854～1859
[60]吕红军,罗志勇,冷轧带钢表面缺陷检测的信号处理,华中理工大学学报,1992,4(20):175～178
[61]张以谟,应用光学,天津:天津大学出版社,1982
[62]徐科,基于图像处理的冷轧带钢表面监测系统的研究与实现,博士后研究工作报告,北京:北京科技大学,2000
[63]章毓晋,图像工程,北京:清华大学出版社,2003
[64]张大鹏,模式识别与图像处理并行计算机系统设计,哈尔滨:哈尔滨工业大学出版社,1998
[65]苏光大,图像并行处理技术,北京:清华大学出版社, 2002
[66] Kumar, A., Inspection of surface defects using optimal FIR filters, Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on Vol.2, Apr.2003: II-241～244
[67] Stratix Handbook Data Sheet,Altera Inc.,2005
[68]宋万杰,罗丰,吴顺君,CPLD技术及其应用,西安:西安电子科技大学出版社,1999
[69]张雄伟曹铁勇,DSP芯片的原理与开发应用,北京:电子工业出版社,2000
[70]边肇棋、张学工,模式识别,北京:清华大学出版社,2000
[71]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
[72]肖健华,智能模式识别,广州:华南理工大学,2006
[73]戴葵等译,神经网络设计――计算机科学丛书,北京:机械工业出版社,2005
[74]胡亮,段发阶,丁克勤等,基于线阵CCD钢板表面缺陷在线检测系统的研究,计量学报,2005.26(3):200～203
[75]陈黎,图像处理技术及其在带钢表面缺陷检测中的应用研究:[硕士学位论文],武汉:华中科技大学,2002
[76]何滢,强反射表面缺陷检测技术:[硕士学位论文],天津:天津大学,2002
[77]郭芳,图像处理技术在表面检测系统中的应用:[硕士学位论文],北京:北京科技大学,2001
[78]艾海舟,机器视觉及其应用,科学中国人,1997(9):23～25
[79] [美]Kenneth R. Castleman著,数字图像处理,朱志刚,林学訚,石定机译,北京:电子工业出版社,1998
[80]冈萨雷斯,数字图像处理,北京:机械工业出版社,2003
[81]孙即祥,图像处理,北京:科学出版社,2004
[82]钟玉琢,乔秉新,李树青,机器人视觉技术,北京:国防工业出版社,1994
[83]陈祖爵陈潇君何鸿,基于改进的混合高斯模型的运动目标检测,中国图像图形学报,2007.12(9):1585～1589
[84]赵竞,两点校正法的正确选择,辽宁城乡环境科技,2006,26(4):22～23.
[85]郭显久,庄严,王珂等,基于高斯滤波器的尺度相乘边缘检测算法,计算机工程与应用,2005,41(3):70～71
[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]狄岚林意须文波,一种带脉冲噪声图像的图像分割方法,计算机应用研究,2007,24(9):315～316
[88]杨晖,曲秀杰,图像分割方法综述,电脑开发与应用,2005,18(3):21～23
[89]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
[90]杨润玲,高新波,介军,一种基于模糊聚类的快速图像分割算法,西安建筑科技大学学报,2007,39(2):280～285
[91]万建,王继成,基于ISODATA算法的彩色图像分割,计算机工程,2002,28(5):135～136
[92]刘峰孙超李斌,一种改进的C均值法初始类划分方法,计算机工程与设计,2005,26(2):465～466
[93]沙芸,刘玉树,王军等,一种非刚体目标的视频分割算法,计算机工程与应用,200,39(22):1～2
[94] Roberts, L.G.,Machine perception of 3D solids, J.T. Tippet etal eds., Optical and Electrooptical Information Processing, MIT Press, 1965: 159～197
[95] Prewitt,J.M.S.,Object enhancement and extraction, Academic Press, 1970,New York
[96]周学海,张伍,基于Sobel算子的多尺度边缘提取算法,微电子学与计算机,2006,23(12):12～14
[97]黄光华倪国强张彬,一种基于视觉阈值特性的图像融合方法,北京理工大学学报,2006,26(10):907～911
[98] Haralick, R.M., Shanmugam, K., Dinstein, I.,Texture Feature for Image Classification, IEEE Transactions on Systems, Man and Cybernetics, Vol. SMC-3, No 6,November: 610～620
[99] Marr,D.,Hildreth,E., Theory of edge detection, Proc.R. Soc.Lond. B207, 187～217
[100]吕俊白,基于快速Kirsch与边缘点概率分析的边缘提取,计算机应用,2001,21(2):33～35
[101] J.Canny.A computational approach to edge detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1986,8 (6):679-698
[102]付忠良,图像阈值选取方法的构造,中国图像图形学报,2000,30(4):427～441
[103]吴一全,朱兆达,图像处理中阈值选取方法30年(1962-1992)的进展(一),数据采集与处理,1993,8:268～282
[104]吴一全,朱兆达,图像处理中阈值选取方法30年(1962-1992)的进展(二),数据采集与处理,1993,8:193～201
[105] Huang L K.Wang M JJ.Image Thresholding by Minimizing the Measure of Fuzziness. Pattern Recognition.1995,28(1):41~51
[106]刘健庄,栗文清,灰度图像的二维Ostu自动阈值分割法,自动化学报,1993,19(1):101～105
[107] J.S.Weska. A survey of Threshold Selection Techniques, CGIP, 1978, 7:259～265
[108] F. J. Chang, J. C. Yen and S. Chang. A new criterion for automatic multilevel thresholding. IEEE Trans. Image Process, 1995,4:370～378
[109] J.S.Weszka,A., Rosenfeld.Histogram modification for threshold selection., IEEE Trans. Syst.Man.Cybern.,1979,9:38～52
[110] G.Corneloup.Moysan.J.Maynin I E. IISCAN Image Segmentation by Thresholding Using Concurrence Matrix Analysis. Pattern Recognition. 1996, 29(2):281~296
[111] Li.L,Gong J,Chen W.Grey-Level Image Thresholding Based on Fisher Linear Projection of Two-Dimensinal Histogram. Pattern Recognition. 1997, 30(5) :743~750
[112] Prasanna K.Sahoo,Gurdial Aror.A thresholding method based on two-Dimensional Renyi's entropy[J].Pattern Recognition 2004,37:1149~1161
[113] Brink A D. Thresholding Digital Images Using two-Dimensional Entropics. Pattern Recognition, 1992, 25(8): 803-808
[114]严学强等,顺序形态学在图像边缘检测中的应用.信号处理,1997,13(4):357～362
[115] Heijmans H J A M, Ronse C., The algebraic basis of mathematical morphology, I. Dilations and Erosions., Computer Vision, Graphics, and Image Processing. 1990,3:245～295
[116]崔屹,图像处理与分析——数学形态学方法与应用,北京:科学出版社,2000
[117] Vincent L,Soille P.Wartersheds in digital space:Aefficient algorithms based on immersion simulation[j].IEEE Transactions on Pattern Analysis and Machine Intelligence 1991,13(6): 583~598
[118] Richard O.Duda,Peter E.Hart David G.Stork,Pattern Classification Second Edition,北京:工业出版社,2006
[119] KanalL., RaghavanS .,HybridSystetr.KeytoIntelligent Patern Recognition, Proceedings of International Joint Conference on Neural Networks,1992,4:177~183
[120]王连亮、陈怀新,图像识别的RSTC不变矩,数据采集与处理,2006,21(2): 225~229
[121]李艳双,曾珍香,主成分分析法在多指标综合评价方法中的应用,河北工业大学学报,1999,l28(1):94~97
[122] Rautaruukki New Technology Corp. Defect classification in surface inspection of strip steel.Steel Times International,1992,16(5):214～216
[123]赵松青等,基于神经网络的带钢表面孔洞检测系统研究,华中科技大学学报增刊,2004,24(10):220～222
[124] Keinosuke Fukunaga, Raymond R Hayes., Effect of sample size in classifier design, IEEE Trans Pattern and Machine,1989,11(8):873～885
[125] D.Rohrmus,Invariant texture features for web defect detection and classification,in:SPIE Proceedings on Machine Vision Systems for Inspection and Metrology VIII, Vol. 3836, Boston,MA, 1999, 144～155
[126]肖柳青,周石鹏,实用最优化方法,上海:上海交通大学出版社,2000
[127] V.M.Preciado, D. Guinea, J.Vicente.M.C. Garcia-Alegre and A. Ribeiro.,Automatic CNN Multi-template Tree Generation, Proc. of CNNA 2000,Catania, Italy, 2000
[128] Kanal Laveen N., On Pattern Categories, and Alternate Realities, Pattern Recognition Leters,1993,14 :241~245
[129] Kanal.L.,Raghavan.S.,HybridSystetr.KeytoIntelligent Pattern Recognition, Proceedings of International Joint Conference on Neural Networks,1992,4:177~183
[130]叶萝芸,戚飞虎,朱国吸,一种多级分类器集成的字符识别方法,电子学报,1998,26(11):15～19
[131] Tin Kan Ho, Decision Combination in Multiple Classifier Systems, IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(1): 66~75
[132] Christine Nadal, Complementary Algorithms for the Recognition of Totally Unconstrained Handwritten Numerals,10th International Conferenceon Patern Recognition,1990,1 :443~449
[133] Kimra F., Shridhar M., Handwritten Numerical Recognition Based on Multiple Algorithms, Pattern Recognition,1991,24(10) : 969~983
[134]乔进,潘保昌,赵学军,基于多级分类器的自由手写数字在线识别,重庆大学学报,1999,22(3):127~132
[135] Tung Cheng-Huang, Lee Hsi-Jian, Increasing Character Recognition Accuracy by Detection and Correction of Eroneously Identified Characters, Pattern Recognition,1994,27(9):1259～1266
[136] SinhaR .M .K,Hybrid Contextual Text Recognition with String Matching,IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(9): 915~925
[137] Paul Gader, Recognition of Handwriten Digits Using Template and Model Matching , Pattern Recognition,1991,24(5):421~431
[138]温昱,软件架构设计,北京:电子工业出版社,2007
[2] Marr D.,视觉计算理论,科学出版社,1988
[3]张洪涛,荫罩板计算机视觉检测系统研究:[硕士学位论文],天津;天津大学,2002
[4]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
[5]李金宗,模式识别导论,北京:高等教育出版社,2000
[6]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
[7]王庆有,图像传感器应用技术,北京:电子工业出版社,2003
[8]刘凌,胡永生,数字信号处理的FPGA实现,北京:清华大学出版社,2003
[9] W.S.Wilson, The role of vision in a dimensional control strategy, Proc. of the Society of Manufacturing Engineers Conf. on Vision Section 7, 1985: 43～55
[10] Carpenter G A, Grossberg S. Neural network for vision and image processing[M]. Lexington: MIT Press, 1992
[11] Simonis M P,余永桂译,频闪法在带钢表面检查中的应用,世界钢铁,1994,23(4):65～68
[12]胡学雄,陶军,黎润民,涡流检测技术在宝钢热轧轧辊上的应用,2004,21(5)::65~67
[13]吴平川,带钢表面自动检测系统研究现状与展望,钢铁,2000,36(6):70～75
[14] Hiroshi Maki., Magnetic on-line defect inspection system for strip steel, Iron and Steel Engineer, 1993(1):56～59
[15] Okamoto Y, Kaminaga F, Osakabe Metal.,Detection of surface flaw by infrared radiation sensor. The 7th Sensor Symposium, Tokyo: Institution of Electric Engineers of Japan, 1988:107～112
[16] M.M.Landman, S.J.Roberton, A flexible industrial system for automated three-dimensional inspection, SPIE, 1986, 728:203～209
[17] Reinhard Rinn, Michael Becker, Ralph Foehr, Friedrich Luecking. Steel Mill Defect Detection and Classification of 3000ft./min. Using Mainstream Technology.1998, SPIE Vol.3303 0277～786
[18]何秩,超声波传感器在宝钢钢卷检测中的应用,电工技术,2003,10:64～65
[19] Suresh BR, Fundakowski RA, Levitt TS etal. A realtime automated visual inspection system for hot steel slabs. IEEE Trans Pattern Anal Machine Intell, 1983,PAMI-5(6):563～572
[20] Reinhard Rinn,Scott A.Thompson., One year of experience with the new generation of automatic hot mill inspection systems.ASIE Steel Technology, June 2000:56～61
[21]孟宪超,轧制带钢表面缺陷的检测及识别方法的研究:[硕士学位论文],哈尔滨:哈尔滨工业大学,1996
[22] McManus, George J., Automatic Surface Inspection of Sheet, Iron and steel Engineer, March 1999:56～58
[23]罗志勇等,带钢表面缺陷检测系统的发展,钢铁,1996增刊:127～131
[24] Fred Treiber., On-line Automatic Defect Detection and Surface Roughness Measurement of Steel Strip. Iron and Steel Engineer, 1989, 66(9):26～33
[25]吴平川,机器视觉与钢板表面缺陷的无损检测,无损检测,2000,22(l):13～16
[26]吴平川,带钢表面缺陷机器视觉识别方法的研究:[博士学位论文],哈尔滨:哈尔滨工业大学,2000
[27] Chris A.Carisetti,Theodore Y.Fong,Charles Fromm,iLearn self- learning defect classifier. Iron and Steel Engineer,1998,75(8):50～53
[28]罗志勇,用线列CCD测量钢板宽度和检测孔洞缺陷的信号处理,1991.12(1):37～41
[29]胡亮,线阵CCD实现钢板表面缺陷在线检测关键技术及其应用研究:[博士学位论文],天津:天津大学,2006
[30] Mike Muehlemann. Standardizing Defect Detection for the Surface Inspection of Large Web Steel. Illumination Technologies ,Inc .2000
[31] Parsytec Computer Corp . Software controlled on-line surface inspection.Steel Times International,1998,22(3):30~34
[32]皮敏捷,徐科,基于多条激光线的钢板表面缺陷三维检测方法,机电产品开发与创新,2007,20(2):123～125
[33]宋强,徐科,徐金梧,基于结构谱的中厚板表面缺陷识别方法,北京科技大学学报,2007,29(3):342~345
[34]吴平川,路同浚,钢板表面缺陷的无损检测技术与应用,无损检测,2000,22(7):312～315
[35]杨洲,李明君,高磊,浅析压力容器应力腐蚀及其控制措施,石油化工设备,2007,36(B08):41～43
[36]周家齐,热轧钢板表面缺陷浅析,重钢技术,1991,2(34):32～36
[37]徐科等,冷轧带钢表面自动监测系统的研究,钢铁,2000,35(10):63
[38] K. Wiltschi, A. Pinz, T. Lindeberg, Automatic assessment scheme for steel quality inspection, Machine Vision and Applications,2000(12):113～128
[39] Obeso,F,Gonzalez J A,Brown A.Intelligent on-line Surface Inspection on A Skinpass.Iron and Steel ,1997(10):29～35
[40] http://www.parsytec.de/77_894.html
[41]相泽均等著,周源译.冷轧带钢表面缺陷检测系统,世界钢铁,1994,21(2):66～73
[42] Ceracki, P., Lücking, F., Reizig, H.-J., On-line defect recognition in hot strip by automatic surface inspection, Stahl und Eisen, 1999, 4: 77～81
[43] Tony WA., Automated inspection of metal products not quite ready for prime time. Iron & Steel Making, 1992,19(1):14～19
[44]罗志勇,刘栋玉,江涛等.新型冷轧带钢表面缺陷在线检测系统.华中理工大学学报,1996,24(1):75～78
[45] Yngve Strom., Automatic surface inspection of continuously cast billets. Iron and Steel Engineer, 1992,69(5):29～33
[46] Fred Treiber. On-line automatic defect detection and surface roughness measurement of steel strip. Iron and Steel Engineer, 1989, 66(9):26～33
[47] Thomas F Porter, Robert A Sytvester, Theodore W Bouyoucas et al. Automatic strtp surface defect detection system. Iron and Steel Engineer, 1988,65(12):17～20
[48]开发合同技术书,天津大学,2002.6
[49]骆文博,王广志,丁海曙等,基于线阵CCD的高精度位置检测,清华大学学报(自然科学版),2002,42(9):1139～1143
[50] John C Badger, Sean T Enright., Automated surface inspection system. Iron and Steel Engineer, 1996, 73 (3):48～51
[51] David G Park,Martin P Levoi,Haneghem AI van.Practical application of on-line hot strip inspection system at hoogovens . Iron and Steel Engineer,1995,72(7): 40～43
[52]阳运平,镀锡板表面缺陷在线检测方法与系统的研究:[硕士学位论文],北京:清华大学,1997
[53]郁道银等,工程光学,北京:机械工业出版社,1998
[54]郝允祥等,光度学,北京:北京师范大学出版社,1987
[55]周斌,刘秉琦,面阵CCD用于光场能量探测的研究,军械工程学院学报,2004,16(3):29～32
[56]何梓滨,视觉检测系统光学照明系统设计:[学士学位论文],天津:天津大学,2006
[57] P2-04k30 User Manual, Dalsa Inc., Cananda
[58] Ryuji Suyama,Kei Tanemoto,Yoshinari Kobayashi et al.,Autofocusing system of optical microscope utilizing electrostric-tive actuators.JpnJAppl Phys.,1991,30(6):1290～1294
[59] Fernandez, C., Platero, C., Campoy, P., Aracil, R.. Vision System for On-line Surface Inspection in Aluminum Casting Process. Industrial Electronics, Control, and Instrumentation, 1993(3):1854～1859
[60]吕红军,罗志勇,冷轧带钢表面缺陷检测的信号处理,华中理工大学学报,1992,4(20):175～178
[61]张以谟,应用光学,天津:天津大学出版社,1982
[62]徐科,基于图像处理的冷轧带钢表面监测系统的研究与实现,博士后研究工作报告,北京:北京科技大学,2000
[63]章毓晋,图像工程,北京:清华大学出版社,2003
[64]张大鹏,模式识别与图像处理并行计算机系统设计,哈尔滨:哈尔滨工业大学出版社,1998
[65]苏光大,图像并行处理技术,北京:清华大学出版社, 2002
[66] Kumar, A., Inspection of surface defects using optimal FIR filters, Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on Vol.2, Apr.2003: II-241～244
[67] Stratix Handbook Data Sheet,Altera Inc.,2005
[68]宋万杰,罗丰,吴顺君,CPLD技术及其应用,西安:西安电子科技大学出版社,1999
[69]张雄伟曹铁勇,DSP芯片的原理与开发应用,北京:电子工业出版社,2000
[70]边肇棋、张学工,模式识别,北京:清华大学出版社,2000
[71]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
[72]肖健华,智能模式识别,广州:华南理工大学,2006
[73]戴葵等译,神经网络设计――计算机科学丛书,北京:机械工业出版社,2005
[74]胡亮,段发阶,丁克勤等,基于线阵CCD钢板表面缺陷在线检测系统的研究,计量学报,2005.26(3):200～203
[75]陈黎,图像处理技术及其在带钢表面缺陷检测中的应用研究:[硕士学位论文],武汉:华中科技大学,2002
[76]何滢,强反射表面缺陷检测技术:[硕士学位论文],天津:天津大学,2002
[77]郭芳,图像处理技术在表面检测系统中的应用:[硕士学位论文],北京:北京科技大学,2001
[78]艾海舟,机器视觉及其应用,科学中国人,1997(9):23～25
[79] [美]Kenneth R. Castleman著,数字图像处理,朱志刚,林学訚,石定机译,北京:电子工业出版社,1998
[80]冈萨雷斯,数字图像处理,北京:机械工业出版社,2003
[81]孙即祥,图像处理,北京:科学出版社,2004
[82]钟玉琢,乔秉新,李树青,机器人视觉技术,北京:国防工业出版社,1994
[83]陈祖爵陈潇君何鸿,基于改进的混合高斯模型的运动目标检测,中国图像图形学报,2007.12(9):1585～1589
[84]赵竞,两点校正法的正确选择,辽宁城乡环境科技,2006,26(4):22～23.
[85]郭显久,庄严,王珂等,基于高斯滤波器的尺度相乘边缘检测算法,计算机工程与应用,2005,41(3):70～71
[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]狄岚林意须文波,一种带脉冲噪声图像的图像分割方法,计算机应用研究,2007,24(9):315～316
[88]杨晖,曲秀杰,图像分割方法综述,电脑开发与应用,2005,18(3):21～23
[89]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
[90]杨润玲,高新波,介军,一种基于模糊聚类的快速图像分割算法,西安建筑科技大学学报,2007,39(2):280～285
[91]万建,王继成,基于ISODATA算法的彩色图像分割,计算机工程,2002,28(5):135～136
[92]刘峰孙超李斌,一种改进的C均值法初始类划分方法,计算机工程与设计,2005,26(2):465～466
[93]沙芸,刘玉树,王军等,一种非刚体目标的视频分割算法,计算机工程与应用,200,39(22):1～2
[94] Roberts, L.G.,Machine perception of 3D solids, J.T. Tippet etal eds., Optical and Electrooptical Information Processing, MIT Press, 1965: 159～197
[95] Prewitt,J.M.S.,Object enhancement and extraction, Academic Press, 1970,New York
[96]周学海,张伍,基于Sobel算子的多尺度边缘提取算法,微电子学与计算机,2006,23(12):12～14
[97]黄光华倪国强张彬,一种基于视觉阈值特性的图像融合方法,北京理工大学学报,2006,26(10):907～911
[98] Haralick, R.M., Shanmugam, K., Dinstein, I.,Texture Feature for Image Classification, IEEE Transactions on Systems, Man and Cybernetics, Vol. SMC-3, No 6,November: 610～620
[99] Marr,D.,Hildreth,E., Theory of edge detection, Proc.R. Soc.Lond. B207, 187～217
[100]吕俊白,基于快速Kirsch与边缘点概率分析的边缘提取,计算机应用,2001,21(2):33～35
[101] J.Canny.A computational approach to edge detection[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1986,8 (6):679-698
[102]付忠良,图像阈值选取方法的构造,中国图像图形学报,2000,30(4):427～441
[103]吴一全,朱兆达,图像处理中阈值选取方法30年(1962-1992)的进展(一),数据采集与处理,1993,8:268～282
[104]吴一全,朱兆达,图像处理中阈值选取方法30年(1962-1992)的进展(二),数据采集与处理,1993,8:193～201
[105] Huang L K.Wang M JJ.Image Thresholding by Minimizing the Measure of Fuzziness. Pattern Recognition.1995,28(1):41~51
[106]刘健庄,栗文清,灰度图像的二维Ostu自动阈值分割法,自动化学报,1993,19(1):101～105
[107] J.S.Weska. A survey of Threshold Selection Techniques, CGIP, 1978, 7:259～265
[108] F. J. Chang, J. C. Yen and S. Chang. A new criterion for automatic multilevel thresholding. IEEE Trans. Image Process, 1995,4:370～378
[109] J.S.Weszka,A., Rosenfeld.Histogram modification for threshold selection., IEEE Trans. Syst.Man.Cybern.,1979,9:38～52
[110] G.Corneloup.Moysan.J.Maynin I E. IISCAN Image Segmentation by Thresholding Using Concurrence Matrix Analysis. Pattern Recognition. 1996, 29(2):281~296
[111] Li.L,Gong J,Chen W.Grey-Level Image Thresholding Based on Fisher Linear Projection of Two-Dimensinal Histogram. Pattern Recognition. 1997, 30(5) :743~750
[112] Prasanna K.Sahoo,Gurdial Aror.A thresholding method based on two-Dimensional Renyi's entropy[J].Pattern Recognition 2004,37:1149~1161
[113] Brink A D. Thresholding Digital Images Using two-Dimensional Entropics. Pattern Recognition, 1992, 25(8): 803-808
[114]严学强等,顺序形态学在图像边缘检测中的应用.信号处理,1997,13(4):357～362
[115] Heijmans H J A M, Ronse C., The algebraic basis of mathematical morphology, I. Dilations and Erosions., Computer Vision, Graphics, and Image Processing. 1990,3:245～295
[116]崔屹,图像处理与分析——数学形态学方法与应用,北京:科学出版社,2000
[117] Vincent L,Soille P.Wartersheds in digital space:Aefficient algorithms based on immersion simulation[j].IEEE Transactions on Pattern Analysis and Machine Intelligence 1991,13(6): 583~598
[118] Richard O.Duda,Peter E.Hart David G.Stork,Pattern Classification Second Edition,北京:工业出版社,2006
[119] KanalL., RaghavanS .,HybridSystetr.KeytoIntelligent Patern Recognition, Proceedings of International Joint Conference on Neural Networks,1992,4:177~183
[120]王连亮、陈怀新,图像识别的RSTC不变矩,数据采集与处理,2006,21(2): 225~229
[121]李艳双,曾珍香,主成分分析法在多指标综合评价方法中的应用,河北工业大学学报,1999,l28(1):94~97
[122] Rautaruukki New Technology Corp. Defect classification in surface inspection of strip steel.Steel Times International,1992,16(5):214～216
[123]赵松青等,基于神经网络的带钢表面孔洞检测系统研究,华中科技大学学报增刊,2004,24(10):220～222
[124] Keinosuke Fukunaga, Raymond R Hayes., Effect of sample size in classifier design, IEEE Trans Pattern and Machine,1989,11(8):873～885
[125] D.Rohrmus,Invariant texture features for web defect detection and classification,in:SPIE Proceedings on Machine Vision Systems for Inspection and Metrology VIII, Vol. 3836, Boston,MA, 1999, 144～155
[126]肖柳青,周石鹏,实用最优化方法,上海:上海交通大学出版社,2000
[127] V.M.Preciado, D. Guinea, J.Vicente.M.C. Garcia-Alegre and A. Ribeiro.,Automatic CNN Multi-template Tree Generation, Proc. of CNNA 2000,Catania, Italy, 2000
[128] Kanal Laveen N., On Pattern Categories, and Alternate Realities, Pattern Recognition Leters,1993,14 :241~245
[129] Kanal.L.,Raghavan.S.,HybridSystetr.KeytoIntelligent Pattern Recognition, Proceedings of International Joint Conference on Neural Networks,1992,4:177~183
[130]叶萝芸,戚飞虎,朱国吸,一种多级分类器集成的字符识别方法,电子学报,1998,26(11):15～19
[131] Tin Kan Ho, Decision Combination in Multiple Classifier Systems, IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(1): 66~75
[132] Christine Nadal, Complementary Algorithms for the Recognition of Totally Unconstrained Handwritten Numerals,10th International Conferenceon Patern Recognition,1990,1 :443~449
[133] Kimra F., Shridhar M., Handwritten Numerical Recognition Based on Multiple Algorithms, Pattern Recognition,1991,24(10) : 969~983
[134]乔进,潘保昌,赵学军,基于多级分类器的自由手写数字在线识别,重庆大学学报,1999,22(3):127~132
[135] Tung Cheng-Huang, Lee Hsi-Jian, Increasing Character Recognition Accuracy by Detection and Correction of Eroneously Identified Characters, Pattern Recognition,1994,27(9):1259～1266
[136] SinhaR .M .K,Hybrid Contextual Text Recognition with String Matching,IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(9): 915~925
[137] Paul Gader, Recognition of Handwriten Digits Using Template and Model Matching , Pattern Recognition,1991,24(5):421~431
[138]温昱,软件架构设计,北京:电子工业出版社,2007