基于图像的PCB板的在线检测
|
摘要
PCB在现代电子设备中占重要的地位,其质量直接影响产品的性能,目前PCB质量检测大都由人工目测完成,容易发生误检和漏检。因此PCB工业迫切需要在线自动检测。
基于图像的PCB在线检测主要包括图像采集、图像的预处理、边缘检测、PCB的定位和瑕疵图像的检测识别几个环节。本文重点就以下几个问题作了具体研究:
图像的预处理是在线检测的前提和基础,本文采用改进的中值滤波法和均值滤波法去除图像的噪声,基于拉普拉斯算法的图像的增强,采用最大类间方差法对PCB进行二值化处理;PCB图像的边缘检测研究中,本文采用基于全方位、多尺度的数学形态学法检测图像边缘;PCB的定位上,本文应用改进的Hough方法对PCB的圆形定位标志进行检测,并研究了具体的实现算法,通过实验证明此方法是比较好的算法;在PCB瑕疵识别中,基于多模板参考比较法的瑕疵检出方法,保留了参考比较法在速度上的优势,进一步提高了系统的检测能力,基于模板图像结构特征的句法结构瑕疵识别方法利用数学形态学理论提取模板图像的结构特征,并将这些结构特征与句法结构瑕疵识别方法相结合,有利于提高瑕疵图像识别速度和准确性,具有运算量小、计算速度快的特点。
PCB is very important in modern electronic equipment, its quality has direct impact to the product function, At present, PCB quality inspecting is completed mostly from manpower visual measurement, and the mistake check up happened and misses. PCB industry needs the online automation detecting therefore urgently.
Owing to that the image PCB checks system on line, mainly, the pretreatment, border detecting , the PCB allocation and blemish image detecting including image acquisition , the image distinguish several links. Priority has written the main body of a book with regard to several the following problems studying concretely:
The image pretreatment is premise and basis checking system on line, The article uses middle value wave filtering law and mean value wave filtering improving to follow the noise dislodging an image, Algorithmic image of Laplace-based strengthening, Adopt maximal kind room method difference to follow the value carrying out two on PCB spending treatment; PCB image edge detecting studies middle , the main body of a book adopt the because of all-direction , many dimension mathematics morphological approach detecting image border to law; On the PCB allocation, Improvement Hough method the main body of a book is applied gives a test to circular PCB allocation sign, has studied and the concrete realization algorithm, good by the fact that the experiment testifies this method is to compare algorithm; In the PCB blemish distinguishing, the method based on multipy form board reference blemishes inspect up out method, have reserved the reference comparison method advantage on speed and highly improved the systematic detecting ability; the based on mul-board image structure characteristic syntax structure blemish distinguishes method uses mathematics morphology theory to abstract the form board image structure characteristic, and the combination between the structure characteristics and the syntax structure blemish distinguishing is beneficial to improving blemish pattern recognition speed and accuracy, having an arithmetic small, calculate the quick characteristic of speed.
基于图像的PCB在线检测主要包括图像采集、图像的预处理、边缘检测、PCB的定位和瑕疵图像的检测识别几个环节。本文重点就以下几个问题作了具体研究:
图像的预处理是在线检测的前提和基础,本文采用改进的中值滤波法和均值滤波法去除图像的噪声,基于拉普拉斯算法的图像的增强,采用最大类间方差法对PCB进行二值化处理;PCB图像的边缘检测研究中,本文采用基于全方位、多尺度的数学形态学法检测图像边缘;PCB的定位上,本文应用改进的Hough方法对PCB的圆形定位标志进行检测,并研究了具体的实现算法,通过实验证明此方法是比较好的算法;在PCB瑕疵识别中,基于多模板参考比较法的瑕疵检出方法,保留了参考比较法在速度上的优势,进一步提高了系统的检测能力,基于模板图像结构特征的句法结构瑕疵识别方法利用数学形态学理论提取模板图像的结构特征,并将这些结构特征与句法结构瑕疵识别方法相结合,有利于提高瑕疵图像识别速度和准确性,具有运算量小、计算速度快的特点。
PCB is very important in modern electronic equipment, its quality has direct impact to the product function, At present, PCB quality inspecting is completed mostly from manpower visual measurement, and the mistake check up happened and misses. PCB industry needs the online automation detecting therefore urgently.
Owing to that the image PCB checks system on line, mainly, the pretreatment, border detecting , the PCB allocation and blemish image detecting including image acquisition , the image distinguish several links. Priority has written the main body of a book with regard to several the following problems studying concretely:
The image pretreatment is premise and basis checking system on line, The article uses middle value wave filtering law and mean value wave filtering improving to follow the noise dislodging an image, Algorithmic image of Laplace-based strengthening, Adopt maximal kind room method difference to follow the value carrying out two on PCB spending treatment; PCB image edge detecting studies middle , the main body of a book adopt the because of all-direction , many dimension mathematics morphological approach detecting image border to law; On the PCB allocation, Improvement Hough method the main body of a book is applied gives a test to circular PCB allocation sign, has studied and the concrete realization algorithm, good by the fact that the experiment testifies this method is to compare algorithm; In the PCB blemish distinguishing, the method based on multipy form board reference blemishes inspect up out method, have reserved the reference comparison method advantage on speed and highly improved the systematic detecting ability; the based on mul-board image structure characteristic syntax structure blemish distinguishes method uses mathematics morphology theory to abstract the form board image structure characteristic, and the combination between the structure characteristics and the syntax structure blemish distinguishing is beneficial to improving blemish pattern recognition speed and accuracy, having an arithmetic small, calculate the quick characteristic of speed.
引文
[1] Wen-YenWu,et al. Automated Inspection of Printed Circuit Boards through Machine Vision.Computers in Industry. 1996,(28): 103-111
[2] Astole J,Haavisto P Neuvo Y. Vectormedianfilter[J]. Processings of the IEEE, 1990,78:678—689.
[3] Windyga P S. Fast impulsive noise removal[J]. IEEE Transoin Image Processing,2001,10(1):173—179.
[4] Kaoru Arakawa. Median filter based On fuzzy rules and its application to image restoration[J]. Fuzzy Sets and Systems, 1996,77:3—13.
[5]Zhu Hua,Guan Jian-chun,HNG Rong-hua,el al. Experimental study on semi—open heat pipes and its applications EJ 3. Journal of Zhejiang University: Science, 2001,2(4): 426—430.
[6]Lam L,Whan S. Thinning methodologies—A comprehensive survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992.14 (9).
[7] S.Kobayashi et al, Identifying solder surface orientation from color highlight images, in Proc. IECON'90, 1990, vol. 1, pp. 821-825.
[8] R.J.K. Wassink, Soldering in Electronics. Ayr, U.K.: Electrochemical Publications,1984, ch. 2, pp. 11-51.
[9] A.C.Sanderson et al. Structured highlight inspection of specular surfaces. IEEE Trans.Pattern Anal.Machine Intell, vol.10, pp.44-55, Jan. 1988.
[10] Y.Nakagawa. Automatic visual inspection of solder joints on printed circuit boards. Proc.SPIE, vol.336, 121-127, 1982.
[11] H.O.Seyfullah, amd L. Onural. An Automated System for Design-Rule-based Visual Inspection of Printed Circuit Boards. Proceedings of the IEEE International Conference om Roboticd and Automation,2696-2701,1991
[12] A.M.Darwish,and A.K. Jain. A Rule Based Approach for Visual Pattern Inspection. IEEE Transaction of Pattern Analysis and Machine Intelligence,Vol.PAMI-10,No.1,56-58,1988
[13] Z.Ibrahim,S.A.R.Al-Attas, and Z.Aspar. Wavelet Based Algorighm for Image Comparison Technique in Application of Coarse-To-Fine Inspection of Printed Circuit Boards (PCB). Malaysia,October 2001
[14]Z.Ibrahim,S.A.R.Al-Attas,amd Z.Aspar,and R.Ghazali.Perfornance Evaluation of Wavelet-Based Algirithm for Printed Circuit Boards(PCB) Inspection.Jurnal Yeknologi D:Universiti Teknologi Malaysia,No.35(D),39-54,2001.
[15]C.Schrernmer,C.Kuhmunch,and C.Esser.Wavelet Filter Evaluation For Image Coding,Technical Report TR-01-006,Department for Mathematics and Computer Science.University of Mannheim.
[16]F.Ercal,F.Bunyak,H.Feng,and L.zheng.A Fast Modular PLE-based Inspection Scheme for PCB.Proceeding of SPIE-Architectures,Networks and Intelligent Systems for Manfacturing Integration,Vol.3203,45-49,1997.
[17]F.Ercal,M.Allen,and H,Feng.Proof of Correctness and Performance Analysis of a Systolic Image Difference Algorithm for RLE-Compressed Images.IEEE ransaction on Parallel and Distrebuted Computing Systems,Vol.11,No.5,433-443,2000
[18]Zhang YJ.A survey on evaluation methods for images egmentation.Patenr Recognition,1996,29(8):1335-1346
[19]John M.Gauch.Image Segmentation and Analysis via Multiscale Gradient Watershed Hierarchies.IEEE.Trans.on Image Porcessing,8(1):69-79,January 1999
[20]Chuang Gu and Ming-Chieh Lee.Semantic Video Object Segmentation and Tracking using Mathematical Morphology and Perspective Motion Model.IEEE.Porceeding,pages 514-517,1997
[21]Y.Qin-zhong,and EE.Danielson.Inspection of Printed Circuit Boards by Connectivity Preserving Shrinking.IEEE Transaction on Pattern Analysis and Machine Intelligence,VOL.PAM 10,NO.5,737-742,1998
[22]Z.Ibrahim.Analysis of the Wavelet-based Image Difference Algorithm for PCB Inspection.IEEE international Conference on Robotics and Automation,2108-2113,2002
[23]W.Wen-Yen,J.W.Mao-Jiun,and L.Chih-Ming.Automated Inspection of Printed Ciruit Boards Through Machine Vision.Computers in Industry,Vol.28,Issue 2,103-111,1996.
[24]Homg-Hai Loh and Ming-Sing lu.Printed Circuit Board Inspection Using Image Analysis.IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS,VOL.35,NO.2,MARCH/APRIL 1999
[25]许一金等.保持图像细节的局部自适应去噪滤波器新方法[J].信号处理,2005,21(2).191-194
[26]董继扬,张军英.一种简单的椒盐噪声滤波算法[J].计算机工程与应用, 2003,(20):27-28.
[27]张旭明等.用于图像处理的白适应阈值滤波[J].计算机辅助设计与图形学学报,2005,17(2).295-299.
[28]胡浩,王明照,杨杰.自适应模糊加权均值滤波器[J].系统工程与电子技术,2002,24(2):15-17.
[29]关新平等.一种新的图像去噪混合滤波方法[J].激光杂志,Vol.28.No.1.2007:57-59.
[30]蔡靖,杨晋生,丁润涛.分类均值2加权中值混合滤波器[J].天津大学学报,1999,32(5):551-554.
[31]刘泉,胡文娟.基于机器视觉的PCB缺陷检测系统的设计与研究.电子器件,Vol.30 No.2,Ap-2007
[32]Lee J,Haralick R M.Shapiro L G.Morphology edge detection[J].IEEE Trans RA,1997,3(4):142-156
[33]宋鸣,胡学龙,高燕.基于全方位和多尺度形态学的图像边缘检测.扬州大学学报,Vol.8 No.1,Feb.2005
[34]付忠良.图象阈值选取方法的构造[J].中国图象图形学报,2000,5(6):466-499.
[35]肖梅,韩崇昭,张雷.基于多尺度轮廓结构元素的数学形态学边缘检测.西安交通大学学报,Vol.39 No.6,Jun.2005
[36]于莉娜,胡正平,练秋生.基于改进随机Hough变换的混合圆/椭圆快速检测方法.电子测量与仪器学报,Vol.18 No.2,Jun.2005
[37]何伟,李薇,张玲.基于计算机图像处理的电路印刷板缺陷检测.计算测量与控制,2007.15(10):1295-1297.
[38]林金龙,石青云.用点Hough变换实现圆检测的方法.计算机工程,vol 29No.11,July.2003
[39]屈稳太.基于弦中点Hough变换的椭圆检测方法.浙江大学学报,Vol.39No.8,Aug.2005
[40]周长发.精通Visual C++图象编程[M].北京:电子工业出版社,2001
[41]舒昌县等.基于形态学的边缘检测[J].中国图象图形学报,1999(2):139-142
[42]杨静宜等.计算机图象处理及常用算法手则[M].南京大学出版社,1997
[43]章暝晋.图象处理分析[M].北京:清华大学出版社,2001
[44]马利庄.图象二值化图象特征的保留[J].中国图象图形学报,1998,19(5):69-79.
[45]李杰.印刷电路板缺陷自动视觉检测系统[J].计算机工程,1992,18(5):35-38.
[46]张利.PCB板检测中的定位研究[J].中国图像图形学报,1999,4(8): 639-661.
[47]何斌等.Visual C++数字图像处理.北京:人民邮电出版社,2001
[48]季华等.PCB测试技术的综合利用.2002,(4):24-26.
[49]王强.图象二值化图象信息的保留[J].计算机辅助设计与图形学学报,2000,12(10):746-750.
[50]盛业华等.一种保形的快速图像形态快速算法.中国图像图像学报,2000,5(2):89-93
[51]Kenneth R Castleman.数字图象处理[M].北京:电子工业出版社,2002.3:159-179.
[52]欧珊瑚,王倩丽,朱哲瑜.Visual C++.NET数字图象处理技术与应用,清华大学出版社
[53]李强.PCB板缺陷自动检测技术的分析研究.硕士论文,2002年6月
[54]高 湘玲.PCB数字图像检测与识别研究.西安交通大学.硕士论文,2002年12月
[55]娄春.数字图像处理技术在IC和PCB外观检查中的应用.华中科技大学,硕士论文,2003年
[56]徐胜海.印刷电路板瑕疵自动光学检测系统的研究.合肥工业大学,硕士论文,2001年
[57]Song J.Delpe J.The analysis of morphological filters with multiple structuring elements.Computer Vision graphicsand Image Porcessing,1990,50:308-328
[58]刘循,游志胜.多尺度形态学图像边缘检测方法.光电工程,2003.6,3(30)
[59]Nieminen Dekka Heinonen.Yrjo Neavo.A New Class of Detail-preserving Filters for Image Porcessing.IEEE Transon Pattenr Analysis Intelligence,1987,PAMI-9(1)
[60]黄智.图象处理与识别实用程序库[M].天津科学技术出版社,1989:50-60.
[61]张宏林.Visual C++数字图象模式识别技术及工程实践[M].北京:电子工业出版社,2002.
[62]徐建华.图像处理和分析[M].北京:科学出版社,1992.
[63]唐常青.数学形态学方法及其应用[M].北京:科学出版社,1990.
[2] Astole J,Haavisto P Neuvo Y. Vectormedianfilter[J]. Processings of the IEEE, 1990,78:678—689.
[3] Windyga P S. Fast impulsive noise removal[J]. IEEE Transoin Image Processing,2001,10(1):173—179.
[4] Kaoru Arakawa. Median filter based On fuzzy rules and its application to image restoration[J]. Fuzzy Sets and Systems, 1996,77:3—13.
[5]Zhu Hua,Guan Jian-chun,HNG Rong-hua,el al. Experimental study on semi—open heat pipes and its applications EJ 3. Journal of Zhejiang University: Science, 2001,2(4): 426—430.
[6]Lam L,Whan S. Thinning methodologies—A comprehensive survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992.14 (9).
[7] S.Kobayashi et al, Identifying solder surface orientation from color highlight images, in Proc. IECON'90, 1990, vol. 1, pp. 821-825.
[8] R.J.K. Wassink, Soldering in Electronics. Ayr, U.K.: Electrochemical Publications,1984, ch. 2, pp. 11-51.
[9] A.C.Sanderson et al. Structured highlight inspection of specular surfaces. IEEE Trans.Pattern Anal.Machine Intell, vol.10, pp.44-55, Jan. 1988.
[10] Y.Nakagawa. Automatic visual inspection of solder joints on printed circuit boards. Proc.SPIE, vol.336, 121-127, 1982.
[11] H.O.Seyfullah, amd L. Onural. An Automated System for Design-Rule-based Visual Inspection of Printed Circuit Boards. Proceedings of the IEEE International Conference om Roboticd and Automation,2696-2701,1991
[12] A.M.Darwish,and A.K. Jain. A Rule Based Approach for Visual Pattern Inspection. IEEE Transaction of Pattern Analysis and Machine Intelligence,Vol.PAMI-10,No.1,56-58,1988
[13] Z.Ibrahim,S.A.R.Al-Attas, and Z.Aspar. Wavelet Based Algorighm for Image Comparison Technique in Application of Coarse-To-Fine Inspection of Printed Circuit Boards (PCB). Malaysia,October 2001
[14]Z.Ibrahim,S.A.R.Al-Attas,amd Z.Aspar,and R.Ghazali.Perfornance Evaluation of Wavelet-Based Algirithm for Printed Circuit Boards(PCB) Inspection.Jurnal Yeknologi D:Universiti Teknologi Malaysia,No.35(D),39-54,2001.
[15]C.Schrernmer,C.Kuhmunch,and C.Esser.Wavelet Filter Evaluation For Image Coding,Technical Report TR-01-006,Department for Mathematics and Computer Science.University of Mannheim.
[16]F.Ercal,F.Bunyak,H.Feng,and L.zheng.A Fast Modular PLE-based Inspection Scheme for PCB.Proceeding of SPIE-Architectures,Networks and Intelligent Systems for Manfacturing Integration,Vol.3203,45-49,1997.
[17]F.Ercal,M.Allen,and H,Feng.Proof of Correctness and Performance Analysis of a Systolic Image Difference Algorithm for RLE-Compressed Images.IEEE ransaction on Parallel and Distrebuted Computing Systems,Vol.11,No.5,433-443,2000
[18]Zhang YJ.A survey on evaluation methods for images egmentation.Patenr Recognition,1996,29(8):1335-1346
[19]John M.Gauch.Image Segmentation and Analysis via Multiscale Gradient Watershed Hierarchies.IEEE.Trans.on Image Porcessing,8(1):69-79,January 1999
[20]Chuang Gu and Ming-Chieh Lee.Semantic Video Object Segmentation and Tracking using Mathematical Morphology and Perspective Motion Model.IEEE.Porceeding,pages 514-517,1997
[21]Y.Qin-zhong,and EE.Danielson.Inspection of Printed Circuit Boards by Connectivity Preserving Shrinking.IEEE Transaction on Pattern Analysis and Machine Intelligence,VOL.PAM 10,NO.5,737-742,1998
[22]Z.Ibrahim.Analysis of the Wavelet-based Image Difference Algorithm for PCB Inspection.IEEE international Conference on Robotics and Automation,2108-2113,2002
[23]W.Wen-Yen,J.W.Mao-Jiun,and L.Chih-Ming.Automated Inspection of Printed Ciruit Boards Through Machine Vision.Computers in Industry,Vol.28,Issue 2,103-111,1996.
[24]Homg-Hai Loh and Ming-Sing lu.Printed Circuit Board Inspection Using Image Analysis.IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS,VOL.35,NO.2,MARCH/APRIL 1999
[25]许一金等.保持图像细节的局部自适应去噪滤波器新方法[J].信号处理,2005,21(2).191-194
[26]董继扬,张军英.一种简单的椒盐噪声滤波算法[J].计算机工程与应用, 2003,(20):27-28.
[27]张旭明等.用于图像处理的白适应阈值滤波[J].计算机辅助设计与图形学学报,2005,17(2).295-299.
[28]胡浩,王明照,杨杰.自适应模糊加权均值滤波器[J].系统工程与电子技术,2002,24(2):15-17.
[29]关新平等.一种新的图像去噪混合滤波方法[J].激光杂志,Vol.28.No.1.2007:57-59.
[30]蔡靖,杨晋生,丁润涛.分类均值2加权中值混合滤波器[J].天津大学学报,1999,32(5):551-554.
[31]刘泉,胡文娟.基于机器视觉的PCB缺陷检测系统的设计与研究.电子器件,Vol.30 No.2,Ap-2007
[32]Lee J,Haralick R M.Shapiro L G.Morphology edge detection[J].IEEE Trans RA,1997,3(4):142-156
[33]宋鸣,胡学龙,高燕.基于全方位和多尺度形态学的图像边缘检测.扬州大学学报,Vol.8 No.1,Feb.2005
[34]付忠良.图象阈值选取方法的构造[J].中国图象图形学报,2000,5(6):466-499.
[35]肖梅,韩崇昭,张雷.基于多尺度轮廓结构元素的数学形态学边缘检测.西安交通大学学报,Vol.39 No.6,Jun.2005
[36]于莉娜,胡正平,练秋生.基于改进随机Hough变换的混合圆/椭圆快速检测方法.电子测量与仪器学报,Vol.18 No.2,Jun.2005
[37]何伟,李薇,张玲.基于计算机图像处理的电路印刷板缺陷检测.计算测量与控制,2007.15(10):1295-1297.
[38]林金龙,石青云.用点Hough变换实现圆检测的方法.计算机工程,vol 29No.11,July.2003
[39]屈稳太.基于弦中点Hough变换的椭圆检测方法.浙江大学学报,Vol.39No.8,Aug.2005
[40]周长发.精通Visual C++图象编程[M].北京:电子工业出版社,2001
[41]舒昌县等.基于形态学的边缘检测[J].中国图象图形学报,1999(2):139-142
[42]杨静宜等.计算机图象处理及常用算法手则[M].南京大学出版社,1997
[43]章暝晋.图象处理分析[M].北京:清华大学出版社,2001
[44]马利庄.图象二值化图象特征的保留[J].中国图象图形学报,1998,19(5):69-79.
[45]李杰.印刷电路板缺陷自动视觉检测系统[J].计算机工程,1992,18(5):35-38.
[46]张利.PCB板检测中的定位研究[J].中国图像图形学报,1999,4(8): 639-661.
[47]何斌等.Visual C++数字图像处理.北京:人民邮电出版社,2001
[48]季华等.PCB测试技术的综合利用.2002,(4):24-26.
[49]王强.图象二值化图象信息的保留[J].计算机辅助设计与图形学学报,2000,12(10):746-750.
[50]盛业华等.一种保形的快速图像形态快速算法.中国图像图像学报,2000,5(2):89-93
[51]Kenneth R Castleman.数字图象处理[M].北京:电子工业出版社,2002.3:159-179.
[52]欧珊瑚,王倩丽,朱哲瑜.Visual C++.NET数字图象处理技术与应用,清华大学出版社
[53]李强.PCB板缺陷自动检测技术的分析研究.硕士论文,2002年6月
[54]高 湘玲.PCB数字图像检测与识别研究.西安交通大学.硕士论文,2002年12月
[55]娄春.数字图像处理技术在IC和PCB外观检查中的应用.华中科技大学,硕士论文,2003年
[56]徐胜海.印刷电路板瑕疵自动光学检测系统的研究.合肥工业大学,硕士论文,2001年
[57]Song J.Delpe J.The analysis of morphological filters with multiple structuring elements.Computer Vision graphicsand Image Porcessing,1990,50:308-328
[58]刘循,游志胜.多尺度形态学图像边缘检测方法.光电工程,2003.6,3(30)
[59]Nieminen Dekka Heinonen.Yrjo Neavo.A New Class of Detail-preserving Filters for Image Porcessing.IEEE Transon Pattenr Analysis Intelligence,1987,PAMI-9(1)
[60]黄智.图象处理与识别实用程序库[M].天津科学技术出版社,1989:50-60.
[61]张宏林.Visual C++数字图象模式识别技术及工程实践[M].北京:电子工业出版社,2002.
[62]徐建华.图像处理和分析[M].北京:科学出版社,1992.
[63]唐常青.数学形态学方法及其应用[M].北京:科学出版社,1990.