PCB表观缺陷的自动光学检测理论与技术
|
摘要
表观缺陷检测技术是印刷电路板(Printed Circuit Board，PCB)行业提高产品生产力，改进生产工业化水平的关键技术之一。随着计算机科学、图像处理、模式识别等诸多领域的发展，基于机器视觉的自动光学缺陷检测技术取代了传统的人工目检技术，对采集到的光电图像提取有用信息，进行处理并加以理解，最终完成实际检测，该技术成为PCB表观缺陷检测今后发展的方向。
在上世纪末，自动光学检测(Automatic Optical Inspection，AOI)技术在国际上已经得到一定程度的应用和推广，我国对PCB表观自动光学检测技术起步较晚，一定程度上影响了国内PCB产品的质量评价和市场竞争力。由于受到表观缺陷检测质量、检测速度等方面因素制约，整体系统仍处在研究和发展阶段。如何降低系统复杂度，增强系统稳定性，降低系统成本，优化缺陷检测和分类方法，提高检出率和分类正确率，成为自动光学检测的研究重点。本文针对PCB表观缺陷AOI系统的设计、缺陷的识别分类所涉及到的相关理论及关键技术进行了深入的研究，主要成果及相关研究内容如下所述。
(1)对PCB表观缺陷自动光学检测系统技术指标和性能进行分析，将系统按照功能划分为不同模块，提出针对PCB表观检测的照明、硬件和软件设计方案，研究利用空间评价函数调整照明最佳配置，采用明暗域结合的照明方式，配合高速线阵CCD采集图像。对硬件设备进行功能参数匹配以保证运动状态下图像质量清晰稳定。按照检测需求对软件进行模块化的系统设计，采用工位划分的流水处理模式，加入并行编程的设计架构，最终实现智能化的自动光学检测系统。
(2)在预处理单元，由于受制作工艺和照明设备的影响产生色彩偏差。分析色彩空间模型，研究CIE-Lab色彩模型中的亮度通道，利用亮度累积直方图计算映射函数去均衡板内的色差；利用照明模型得到亮度变换函数对板间色差进行校正。针对工业检测图像噪声来源的多样性，研究结合形态学的自适应各向异性扩散方程滤波去噪的方法，提高了检测的精度和系统性能。
(3)在图像配准和标准板的制作单元，考虑到PCB定位孔图像出现的部分缺失及图像配准对精度的要求，提出了一种基于随机Hough变换和空间数据坐标变换相结合的配准方法，该方法有效地提高了配准效率及精度，减少了计算时间。本系统首次将描述电气物理性质的Gerber文档引入建标过程，利用正则表达式自上而下的分析方法解析不同型号电路板对应的Gerber文档，通过形态学和神经网络的算法对解析后的图像进行修正，从而得到精准的PCB标准板，为后续缺陷检测和分类奠定良好的基础。
(4)在PCB表观缺陷的特征提取单元，由于受到电路板不同材质及缺陷形成机理的影响，不同物理层上的缺陷区域存在过渡区，提出将分形维数和过渡区理论相结合的局部动态阈值分割方法。该方法结合缺陷的过渡区域信息，利用分形维数对分层后的图像划分不同的子图区域，弥补局部阈值分割方法中子图像大小影响最终分割效果的问题，最终采用动态阈值进行图像分割，提高了缺陷提取的完整性和准确性。
(5)在对提取到的表观缺陷进行分类单元，研究了局部二元模式(LBP)和图像颜色特征相结合的纹理算子LBPC，通过卡方公式计算缺陷样本训练集和测试集的特征分类距离，从而完成对缺陷种类的自动分类识别。实验结果表明表观缺陷分类准确率得到明显提升，通过与传统自适应神经网络分类算法进行对比，分类正确率提高了12%，达到95.5%，满足了工业生产的需要。
(6)在对整个算法系统进行加速阶段，研究利用图形处理单元(GraphicProcessing Unit，GPU)对设备的实时性效果进行改进，深入分析CUDA的设计模式带来的并行处理优势，研究了利用该技术对PCB自动光学检测系统复杂算法的改进。通过实验结果分析表明系统实现了并行处理对表观缺陷图像的预处理、缺陷提取和自动分类算法的加速，大大缩减了整个系统的运行时间，对于数据量较大的图片，运算速度能提高近30倍左右。
本文通过对PCB表观缺陷自动光学检测技术理论和关键技术研究，提出了表观缺陷检测系统的设计方案、图像处理算法及分类识别方法，并且利用计算机图形图像处理单元降低算法系统的复杂度，提高图像处理的执行效率，完成25cm×22cm整板PCB缺陷检测平均时间仅需要3s，大大改善了自动表观检测系统的实时性，在实际的工程项目中得到验证，目前已成功应用在工业检测领域。
The apparent defect detection technology is one of the key technologies forimproving product productivity and increasing production level of industrialization inprinted circuit board (PCB) industry. With the development of computer science, imageprocessing, pattern recognition and etc., automated optical defect inspection technologybased on machine vision replaces the traditional manual visual inspection technology.The useful information is extracted from optical imagest to process for understanding.The actual detection results are ultimately finished. The technology is the maindevelopment direction of PCB apparent defect detection in the future.
In the later of last century, automatic optical inspection technology has been acertain degree of application and promotion in the world. But in our country, there isstill very large gap from others, which affectes the quality of PCB products and marketcompetitiveness to a certain extent. Due to constrain of apparent defect detection quality,detection speed and etc., overall systems are still in the research and development stage.It is automatic optical inspection (AOI) research focuses that how to reduce systemcomplexity, enhance system stability, reduce system costs, optimize defect detection andclassification methods and improve the detection rate and classification accuracy. In thispaper, PCB apparent defects AOI system design and defect identification classificationand other key technologies are researched. The main achievements and relative contentsare listed below:
(1) The technical indicators and performance of apparent defects on PCB AOIsystem were analysised, according to the system function, the system into differentmodules are divided, the lighting, hardware and software design scheme for PCBapparent detection are proposed. Lighting optimal configuration was adjusted by usingspace evaluation function, an illumination of light and dark field combination andacquired image with high-speed linear CCD is adopted. To ensure the image clarity andstability in motion, hardware devices are matched with each function parameters. Inaccordance with the inspection requirements, a modular software system with waterprocessing mode is designed, and ultimately satisfies the need of intelligent AOIsystem.
(2) In the preprocessing unit, owing to the manufacturing process and lighting effects, the system is prone to bring color deviation. Therefore, color space models areanalyzed, using the luminance channel of CIELAB color model and utilized mappingfunction by accumulated luminance histogram to balance the plate colors. The lightingmodel is used to get the brightness transformation function and then corrects the platecolors. For the noise sources diversity of industrial inspection image, with morphologyadaptive anisotropic diffusion equation, partial differential equations are studied to filternoise. The experimental results show that the method is good at reducing noise, whileretaining the image edge information. This approach protects the credibility of thepost-processing results and improves the detection accuracy and system performance.
(3) In the image registration and establishing standard board unit, considering thevarious forms of PCB positioning hole and image registration accuracy requirements,we propose a novel registration approach based on randomized Hough transform andspatial data transformation theory. The method has better performance in finding thetarget, improving detection accuracy, reducing memory space and the computationaltime. The Gerber file into building Standards process is introduced; regular expressiontop-down is used to analyze the Gerber files corresponding to different circuit board. Bymorphology and neural network algorithm to rectify the parsed image, accurate PCBstandard board to lay a good foundation for subsequent defect detection andclassification are obtained.
(4) In feature extraction of PCB apparent defects unit, because of the circuit boardsof different materials and various defects, there has a transition zone in differentphysical layer defect area. Thus the local dynamic threshold method combining fractaldimension with the transition zone theory is proposed. The method combined defecttransition zone information uses fractal dimension to divide layered images intodifferent sub-plot areas. It can compensate the problem that the image size affects thesegmentation in local threshold method. Finally dynamic threshold for imagesegmentation is adopted and the integrity and accuracy of defect extraction areimproved.
(5) In the classification of extraction apparent defect unit, the local binary pattern(LBP) is combined with image variance intensity feature and then the operator LBPC isproposed. By chi-square formula, the feature classification distance of defect sampletraining and test sets are calculated, thus completing the automatic classification ofdefect types. The experimental results for the accuracy of apparent defect classification have improved significantly. Proposed algorithm has been combined with traditionaladaptive neural network classification algorithm, the classification accuracy has beenincreased by12%to95.5%, which meets the need of industion
(6) In the acceleration of algorithm system unit, the graphics processing unit (GPU)is studied and the device effect of real-time is improved. Meanwhile the efficiency ofparallel processing of the CUDA design pattern and applied the technique in thecomplex algorithms improvement of PCB automatic optical detection systems arein-depth analyzed. The experimental results have indicated that the system achievesparallel processing acceleration for the apparent defect image preprocessing, extractionand automatic classification algorithm, which greatly reduces the running time of thesystem. Computing speed can increase30times for large amount of date in imageprocessing.
In this thesis, through research on PCB apparent defects automated opticalinspection theory and key technology, we proposed the apparent defect detection systemdesign scheme, image processing algorithms and classification methods. And then thecomplexity algorithm system has been reduced by using computer graphics and imageprocessing unit, improved the execution efficiency of image processing and thereal-time of apparent automatic detection system. The average detection time is only3swhen completion entire board of25cm×22cm PCB. Finally, the apparent automaticdetection system has been verified successfully in the actual projects and put intoindustrial application.
在上世纪末，自动光学检测(Automatic Optical Inspection，AOI)技术在国际上已经得到一定程度的应用和推广，我国对PCB表观自动光学检测技术起步较晚，一定程度上影响了国内PCB产品的质量评价和市场竞争力。由于受到表观缺陷检测质量、检测速度等方面因素制约，整体系统仍处在研究和发展阶段。如何降低系统复杂度，增强系统稳定性，降低系统成本，优化缺陷检测和分类方法，提高检出率和分类正确率，成为自动光学检测的研究重点。本文针对PCB表观缺陷AOI系统的设计、缺陷的识别分类所涉及到的相关理论及关键技术进行了深入的研究，主要成果及相关研究内容如下所述。
(1)对PCB表观缺陷自动光学检测系统技术指标和性能进行分析，将系统按照功能划分为不同模块，提出针对PCB表观检测的照明、硬件和软件设计方案，研究利用空间评价函数调整照明最佳配置，采用明暗域结合的照明方式，配合高速线阵CCD采集图像。对硬件设备进行功能参数匹配以保证运动状态下图像质量清晰稳定。按照检测需求对软件进行模块化的系统设计，采用工位划分的流水处理模式，加入并行编程的设计架构，最终实现智能化的自动光学检测系统。
(2)在预处理单元，由于受制作工艺和照明设备的影响产生色彩偏差。分析色彩空间模型，研究CIE-Lab色彩模型中的亮度通道，利用亮度累积直方图计算映射函数去均衡板内的色差；利用照明模型得到亮度变换函数对板间色差进行校正。针对工业检测图像噪声来源的多样性，研究结合形态学的自适应各向异性扩散方程滤波去噪的方法，提高了检测的精度和系统性能。
(3)在图像配准和标准板的制作单元，考虑到PCB定位孔图像出现的部分缺失及图像配准对精度的要求，提出了一种基于随机Hough变换和空间数据坐标变换相结合的配准方法，该方法有效地提高了配准效率及精度，减少了计算时间。本系统首次将描述电气物理性质的Gerber文档引入建标过程，利用正则表达式自上而下的分析方法解析不同型号电路板对应的Gerber文档，通过形态学和神经网络的算法对解析后的图像进行修正，从而得到精准的PCB标准板，为后续缺陷检测和分类奠定良好的基础。
(4)在PCB表观缺陷的特征提取单元，由于受到电路板不同材质及缺陷形成机理的影响，不同物理层上的缺陷区域存在过渡区，提出将分形维数和过渡区理论相结合的局部动态阈值分割方法。该方法结合缺陷的过渡区域信息，利用分形维数对分层后的图像划分不同的子图区域，弥补局部阈值分割方法中子图像大小影响最终分割效果的问题，最终采用动态阈值进行图像分割，提高了缺陷提取的完整性和准确性。
(5)在对提取到的表观缺陷进行分类单元，研究了局部二元模式(LBP)和图像颜色特征相结合的纹理算子LBPC，通过卡方公式计算缺陷样本训练集和测试集的特征分类距离，从而完成对缺陷种类的自动分类识别。实验结果表明表观缺陷分类准确率得到明显提升，通过与传统自适应神经网络分类算法进行对比，分类正确率提高了12%，达到95.5%，满足了工业生产的需要。
(6)在对整个算法系统进行加速阶段，研究利用图形处理单元(GraphicProcessing Unit，GPU)对设备的实时性效果进行改进，深入分析CUDA的设计模式带来的并行处理优势，研究了利用该技术对PCB自动光学检测系统复杂算法的改进。通过实验结果分析表明系统实现了并行处理对表观缺陷图像的预处理、缺陷提取和自动分类算法的加速，大大缩减了整个系统的运行时间，对于数据量较大的图片，运算速度能提高近30倍左右。
本文通过对PCB表观缺陷自动光学检测技术理论和关键技术研究，提出了表观缺陷检测系统的设计方案、图像处理算法及分类识别方法，并且利用计算机图形图像处理单元降低算法系统的复杂度，提高图像处理的执行效率，完成25cm×22cm整板PCB缺陷检测平均时间仅需要3s，大大改善了自动表观检测系统的实时性，在实际的工程项目中得到验证，目前已成功应用在工业检测领域。
The apparent defect detection technology is one of the key technologies forimproving product productivity and increasing production level of industrialization inprinted circuit board (PCB) industry. With the development of computer science, imageprocessing, pattern recognition and etc., automated optical defect inspection technologybased on machine vision replaces the traditional manual visual inspection technology.The useful information is extracted from optical imagest to process for understanding.The actual detection results are ultimately finished. The technology is the maindevelopment direction of PCB apparent defect detection in the future.
In the later of last century, automatic optical inspection technology has been acertain degree of application and promotion in the world. But in our country, there isstill very large gap from others, which affectes the quality of PCB products and marketcompetitiveness to a certain extent. Due to constrain of apparent defect detection quality,detection speed and etc., overall systems are still in the research and development stage.It is automatic optical inspection (AOI) research focuses that how to reduce systemcomplexity, enhance system stability, reduce system costs, optimize defect detection andclassification methods and improve the detection rate and classification accuracy. In thispaper, PCB apparent defects AOI system design and defect identification classificationand other key technologies are researched. The main achievements and relative contentsare listed below:
(1) The technical indicators and performance of apparent defects on PCB AOIsystem were analysised, according to the system function, the system into differentmodules are divided, the lighting, hardware and software design scheme for PCBapparent detection are proposed. Lighting optimal configuration was adjusted by usingspace evaluation function, an illumination of light and dark field combination andacquired image with high-speed linear CCD is adopted. To ensure the image clarity andstability in motion, hardware devices are matched with each function parameters. Inaccordance with the inspection requirements, a modular software system with waterprocessing mode is designed, and ultimately satisfies the need of intelligent AOIsystem.
(2) In the preprocessing unit, owing to the manufacturing process and lighting effects, the system is prone to bring color deviation. Therefore, color space models areanalyzed, using the luminance channel of CIELAB color model and utilized mappingfunction by accumulated luminance histogram to balance the plate colors. The lightingmodel is used to get the brightness transformation function and then corrects the platecolors. For the noise sources diversity of industrial inspection image, with morphologyadaptive anisotropic diffusion equation, partial differential equations are studied to filternoise. The experimental results show that the method is good at reducing noise, whileretaining the image edge information. This approach protects the credibility of thepost-processing results and improves the detection accuracy and system performance.
(3) In the image registration and establishing standard board unit, considering thevarious forms of PCB positioning hole and image registration accuracy requirements,we propose a novel registration approach based on randomized Hough transform andspatial data transformation theory. The method has better performance in finding thetarget, improving detection accuracy, reducing memory space and the computationaltime. The Gerber file into building Standards process is introduced; regular expressiontop-down is used to analyze the Gerber files corresponding to different circuit board. Bymorphology and neural network algorithm to rectify the parsed image, accurate PCBstandard board to lay a good foundation for subsequent defect detection andclassification are obtained.
(4) In feature extraction of PCB apparent defects unit, because of the circuit boardsof different materials and various defects, there has a transition zone in differentphysical layer defect area. Thus the local dynamic threshold method combining fractaldimension with the transition zone theory is proposed. The method combined defecttransition zone information uses fractal dimension to divide layered images intodifferent sub-plot areas. It can compensate the problem that the image size affects thesegmentation in local threshold method. Finally dynamic threshold for imagesegmentation is adopted and the integrity and accuracy of defect extraction areimproved.
(5) In the classification of extraction apparent defect unit, the local binary pattern(LBP) is combined with image variance intensity feature and then the operator LBPC isproposed. By chi-square formula, the feature classification distance of defect sampletraining and test sets are calculated, thus completing the automatic classification ofdefect types. The experimental results for the accuracy of apparent defect classification have improved significantly. Proposed algorithm has been combined with traditionaladaptive neural network classification algorithm, the classification accuracy has beenincreased by12%to95.5%, which meets the need of industion
(6) In the acceleration of algorithm system unit, the graphics processing unit (GPU)is studied and the device effect of real-time is improved. Meanwhile the efficiency ofparallel processing of the CUDA design pattern and applied the technique in thecomplex algorithms improvement of PCB automatic optical detection systems arein-depth analyzed. The experimental results have indicated that the system achievesparallel processing acceleration for the apparent defect image preprocessing, extractionand automatic classification algorithm, which greatly reduces the running time of thesystem. Computing speed can increase30times for large amount of date in imageprocessing.
In this thesis, through research on PCB apparent defects automated opticalinspection theory and key technology, we proposed the apparent defect detection systemdesign scheme, image processing algorithms and classification methods. And then thecomplexity algorithm system has been reduced by using computer graphics and imageprocessing unit, improved the execution efficiency of image processing and thereal-time of apparent automatic detection system. The average detection time is only3swhen completion entire board of25cm×22cm PCB. Finally, the apparent automaticdetection system has been verified successfully in the actual projects and put intoindustrial application.
引文
[1] Z. M. Li, Y. W. Lin, J. Huang. Preprocess Algorithm of PCB Line Detection[J].Optics andPrecision Engineerin,2007,15(2):242-246
[2] M. Moganti, F. Ercal. Automaticprinted Circuited Board Inspection Systems[J].IEEE Potentials,1995,14(3):6-10
[3] C. Steger, M. Ulrich.机器视觉算法与应用[M].(杨少荣).北京：清华大学出版社，2008,1-4
[4]刘金桥，吴金强.机器视觉系统发展及其应用[J].机械工程与自动化，2010,2(1):215-216
[5]张五一，赵强松，王东云.机器视觉的现状及发展趋势[J].中原工学院学报，2008,19(1):9-11
[6]胡涛.基于轮廓对比的PCB裸板缺陷检测算法研究[D].武汉：华中科技大学，2009,11-20
[7] H. G. da Silva, T. G. Amaral, O. P. Dias. Automatic Optical Inspection for Detecting DefectiveSolders on Printed Circuit Boards[C].Annual Conference on IEEE Industrial Electronics Society,Melbourne,2010,36:1087-1091
[8]潘明.基于机器视觉的大张印刷质量光电检查系统研究[D].成都：电子科技大学，2011,50-60
[9]柏长冰，齐春，宋福民，等. Hough变换快速检测圆形PCB Mark [J].光电工程，2005，32(9)：75-78
[10]乔闹生，叶玉堂，莫春华，等.印刷电路板光电图像畸变校正研究[J].光电子激光，2009,20(11):1548-1551
[11] N. Talbot. The Use of Automated Optical Testing (AOT) in Statistical Process Control (SPC) forPrinted Circuit Board (PCB) Production [J].Circuit World,2003,29(4):19~22
[12]黄永林，叶玉堂. PCB导线上下线宽检测算法研究[J].计量学报，2011,32(8):766-771
[13]戴维斯.机器视觉：理论、算法与实践（英文版第3版）[M].北京：人民邮电出版社，2009,150-161
[14]章毓晋.图像工程(上册)图像处理(第2版)[M].北京:清华大学出版社，2006,29-35
[15]胡跃明,谭颖.自动光学检测在中国的应用现状和发展[J].微计算机信息，2006,12(4):143-146
[16] R. F. Sajal, M. Kamruzzamman, F. Ahmed Jewel.Machine Vision Based Automatic System forReal Time Recognition and Sorting of Bangladeshi Bank Notes[C]. International Conference onComputer and Information Technology,2008,356-358
[17] T. T. Chung, Y. C. Huang. Optimum Desisn of A high Precision AOI Machine Structure[C].International Conference on Mechanical and Electronics Engineering,2010,164-168
[18]卢荣胜.自动光学检测技术的发展现状[J].红外与激光工程，2008,37(4):120-124
[19]刘霞．PCB光电自动外观检查机的光学及软件部分设计及实现[D].成都：电子科技大学，2010,1-14
[20]韩芳芳.表面缺陷视觉在线检测关键技术研究[D].天津：天津大学，2011,3-7
[21]毕昕,丁汉. TFT-LCD Mura缺陷机器视觉检测方法[J].机械工程学报，2010,46(12):13-19
[22] M. Moganti, F. Ereal. Automatic PCB Inspection Algorithms Asurvey[J]. Computer Vision andImage Understanding.1996,63(2):287-313
[23]梅领亮.PCB最终外观检查机关键技术研究[D].成都：电子科技大学，2010,3-16
[24] N. Mar, P. Yarlagadda, C. Fookesc. Design and Development of Automatic Visual InspectionSystem for PCB Manufacturing [J]. Robotics and Computer Integrated Manufacturing,2011,27(5):949-962
[25] S. Kishimoto, N. Kakimori, Y. Yamamoto, et al.. A printed Circuit Board (PCB) InspectionSystem Employing the Multi-lighting Optical System[C].8th IEMT International ElectronicManufacturing Technology Conference, IEEE,1990,120-129
[26] W. Y. Wu, M. J. J. Wang, C. M. Liu, et al. Automated Inspection of Printed Circuit Boardsthrough Machine Vision [J]. Computer in Industry,1996,28(2):103-111
[27] H. Zheng, L. X. Kong, S. Nahavandi. Automatic Inspection of Metallic Surface Defects UsingGenetic Algorithms [J]. Journal of Materials Processing Technology,2002,12(6):427-433
[28] D. Z. WANG, C. H. WU, I. ANDREW, et al.. Fast Multi-Template Matching Using a ParticleSwarm Optimization Algorithm for PCB Inspection[C]. Conference European Workshops onthe Theory and Applications of Evolutionary Computation,2008,365-370
[29] E. K. Teoh, D. P. Mital, B. W. Lee, et al.. Automated Visual Inspection of Surface Mount PCB[J]. Signal Processing and System Control Factory Automation,1990,20(8):576-580
[30] HAE-WON OH, TAE-HYUNG PARK. Gerber-character Recognition System of Auto-teachingProgram for PCB Assembly Machines[C]. SICE Annual Conference,2004,8(2):300-305
[31] J. P. Jones, L.A. Palmer. An Evaluation of the Two-Dimensional Gabor Filter Model of SimpleReceptive Fields in Cat Striate Cortex[J]. Neurophysiology.1987,23(8):1233-1244
[32] A. V. Bhavsar, A. N. Rajagopalan. Range Map with Missing Data Joint ResolutionEnhancement and Inpainting[J].2008Sixth Indian Conference on Computer Vision, Graphics&Image Processing, IEEE,2008:259-365
[33] E. Candes, J. Romberg, T. Tao. Robust Uncertainty Principles: Exact Signal Reconstructionfrom Highly Incomplete Frequency Information[J]. IEEE Transactions on Information Theory,2006,52(2):489-509
[34] M. Elad, M. Figueiredo, Y. Ma. On the Role of Sparse and Redundant Representations in ImageProcessing[J]. Proceedings of the IEEE-Special Issue on Applications of SparseRepresentation and Compressive Sensing,2010,98(6):1451-1459
[35] L. Zhang, X. L. Wu.An Edge-Guided Image Interpolation Algorithm via Directional Filteringand Data Fusion [J]. IEEE Transactions on Image Processing,2006,15(8):2226-2238
[36] H. Chui, A. Rangarajan, A new Point Matching Algorithm for Non-rigid Registration, CVIU,2003,89(2-3):114-141
[37] M. J. Chen, C. H. Huang, W. L. Lee. A fast Edge-oriented Algorithm for Image Interpolation[J].Image and Vision Computing,2005,23(9):791-798
[38]朱宏殷，郭永飞，司国良.多TDICCD拼接相机成像非均匀性实时校正的硬件实现[J].光学精密工程，2011,12(19):3025-3041
[39]吴福培，邝泳聪，张宪民，等．基于模式匹配及其参数自适应的PCB焊点检测[J].光学精密工程，2009,17(10):2586-2593
[40]袁红中，付炜，郭永魁.一种基于动态阈值的镀铜表面缺陷检测算法[J].燕山大学学报，2018,34(4):336-340
[41]刘建伟，梁晋，梁新合，等.大尺寸工业视觉测量系统[J].光学精密工程，2010,18(1)：126-134
[42]薛骏.基于机器视觉的表面贴装元件检测技术研究[D].成都：西南交通大学，2008,25-30
[43]卢素涵.2006年全球自动光学检测(AOI)设备市场概况[EB/OL],http://optics.ofweek.com/2008-01/ART-250003-8400-13713001.html, Jan.21,2008
[44]牛玉洲,宋培华,张建正.机器视觉在铜箔基板疵点在线检测系统中应用[J].微计算机信息，2001,12(11):730-736
[45]余丛华.基于机器视觉的纺织品缺陷检测系统研究与设计[D].武汉：武汉工程大学，2012,14-20
[46]杨高科.基于虚拟仪器的质量检测机器视觉系统[D].西安：西北大学，2002,12-14
[47] H. K. Cheung, et al. A Novel Illumination Compensation Scheme for Sprite Coding[C].ICSP’04Proceedings.2004,1223-1227
[48]章毓晋，图像分割[M].北京：清华大学出版社，2002,137~157
[49]吴平川，路同浚，王炎.机器视觉与钢板表面缺陷的无损检测[J].无损检测，2000，22(1):13-16
[50]蒲亮,叶玉堂,宋昀岑，等.基于优化K-D树的大面积高密度PCB快速AOI[J].仪器仪表学报，2011,32(4):955-960
[51] R. C.冈萨雷斯, P.温茨．数字图像处理[M].北京：电子工业出版社，2011,423-480
[52] S. Somatilake, A.N. Chalmers. An Image Based Food Classification System[C]. Proceedings ofImage and VisionComputing, New Zealand.2007,260-265
[53]张洪涛.钢板表面缺陷在线视觉检测系统关键技术研究[D].天津：天津大学，2008,9-11
[54] Jae-Kang Lee, Il-Hwan Kim. New Recognition Algorithm for Various Kinds of Euro Banknotes[J]. Industrial Electronics Society,2003,23(12):2266-2270
[55] J. H. Kim, S. Ahn, J. W Jeon, et al.. Byun. A High-Speed High-Resolution Vision System for theInspection of TFT LCD[C], Proceedings.ISIE2001. IEEE Int. Symposium on IndustrialElectronic.2001,101-105
[56] X. Tan, B. Triggs. Enhanced Local Texture Feature Sets for Face Recognition under DifficultLighting Conditions[J]. IEEE Transactions on Image Processing,2010,19(6):1635-1650
[57] S. N. Chiu, M. H. PERN. Reflection-Area-Based Feature Descriptor for Solder Joint Inspection[J].Machine Vision and Applications.2007,8(12):95-106
[58] Z. L. Shu, F. H. Qi. A novel algorithm for fast circle detection using randomized Houghtransforms[J]. Computer Engineering,2003,29(6):86-89
[59]曹智文.基于机器视觉的线结构光尺寸测量系统[D].武汉:湖北工业大学，2012,15-20
[60] L. Calvin, Snyder.并行程序设计原理[M].北京：机械工业出版社，2009,22-24
[61] G. T. Mattson, A. B. Sanders, L. Berna.并行编程模式[M]．北京：清华大学出版社，2005,7-9
[62] B.Wilkinson, M.Allen.并行程序设计[M]．北京：机械工业出版社，2005,1-4
[63]周伟明,多核计算与程序设计[M].武汉：华中科技大学出版社，2009,10-11
[64]黄杰贤,李迪,叶峰,等．挠性印制电路板焊盘表面缺陷的检测[J].光学精密工程，2010,18(11):2443-2553
[65]胡亮.基于线阵CCD钢板表面缺陷在线检测系统的研究[J].计量学报，2005(7):200-203
[66]王勤.高速线阵CCD图像数据采集系统的研究[D].天津：天津大学，2005,1-13
[67]姚蛟，叶玉堂，张静，等. PCB自动光学检测中Gerber文件的解析研究[J].计算机工程与设计，2012,33(6):2481-2485
[68]彭向前,陈幼平,余文勇.一种基于机器视觉的浮法玻璃质量在线检测系统[J].制造业自动化，2007,29(12):50-53
[69]吴凤和.基于计算机视觉测量技术的图像轮廓提取方法研究[J].计量学报，2007,28(1):18-22
[70]吕恒毅，刘杨，郭永飞.遥感相机焦面CCD机械拼接中重叠像元数的确定[J].光学精密工程，2012,5(20):1042-1046
[71]李俊.机器视觉照明光源关键技术研究[D].天津:天津理工大学，2006,14-26
[72]赵媛.基于PWM的LED机器视觉光源技术的研究[D].哈尔滨：哈尔滨工业大学，2009,8-14
[73]韩志冲，钟嫄等.单片机控制信号采集的软硬件设计及其在光源测量系统中的应用[J].电子器件，2008,23(8)：643-645
[74]张未强,陆洋.如何为机器视觉系统选择采集卡[J].可编程控制器与工厂自动化.2005,23(7):34-40
[75]陈博洋，赖雪峰，陈桂林等.线阵CCD相机的研制[J].科学技术与工程，2007，12(11)：43-51
[76] K. C. Liu, S. Wang, W. Shao, et al.. Color-Edge Detection Based on Discrimination ofNoticeable Color Contrasts[J]. International Journal of Imaging Systems and Technology,2009,19(4):332-339
[77] L. G. Shapiro， G. C. Stockman，赵清洁译.计算机视觉[M].北京：机械工业出版社，2005,224-230
[78] D. C. Montgomery. Design and Analysis of Experiments, Fifth Edition[M]. New York: JohnWiley,2006,60-112
[79] Perona P, Malik J. Scale-Space and Edge Detection Using Anisotropic Diffusion[J], IEEE Trans.Pat. Anal.Machine Intel.1990,12(7):629-639
[80]张洪涛，段发阶，叶声华.一种快速亚像素边缘检测方法研究[J].计量学报，2002,23(4):263-265
[81]黄永林，叶玉堂，陈镇龙，等.一种新的快速Hough变换圆检测方法[J].电子测量与仪器学报，2010(9):837-842
[82]腾今朝,邱杰.利用Hough变换实现直线的快速精确检测[J].中国图象图形学报，2008,17(6):68-75
[83] L. Xu, E. Oja, P. Kultanen. A New Curve Detection Method Randomized HoughTransform(RHT)[J]. Pattern Recognition Letters,1990,11(5):331-338
[84] G. W. Wei. Generalized Perona-Malik Equation for Image Restoration [J]. IEEE SignalProcessing,1999,6(5):65-167
[85] H. C. V. Assen, P. M. Egmont, J. H. C.Reiber. Accurate Object Localization in Gray LevelImages Using the Center of Gravity Measure: Accuracy Versus Precision[C]. IEEETransactions on Image Processing(S1057-7149),2002,11(12):1379-1384
[86] L. Xu, E. Oja Randomized Hough Transform (RHT): Basic Mechanisms Algorithms andComputational Complexities[J]. CVGIP: Image Understanding,1993,57(2):131-154
[87]尚会超.印刷图像在线检测的算法研究与系统实现[D].武汉：华中科技大学，2006,81-84
[88] C. Chadwick. Five degrees of freedom[J]. Vision Systems Design, Dec.,2011,16(12):625-632
[89] Nitin Aggarwal, William Clem Karl. Line Detection in Images Through RegularizedHoughtransform[J].IEEE Transactions on image processing,2006,15(3):582-591
[90] Q. Z. Ye, P. E. Danielsson. Inspection of Printed Circuit Boards by Connectivity PreservingShrinking[J]. IEEE Transactions on Pattern Analysis and Mach Intelligence,1988,10(5):737-742
[91] A. Nakib，H. Oulhadj，P. Siarry．Image Histogram ThresholdingBased on MultiobjectiveOptimization[J]．Signal Processing,2007,87(11):2516-2534
[92] J. A. Canny. Computational Approach to Edge Detection[J]. IEEE Trans. On PAMI,1986,8(6):679-698
[93] H. Zollner, R. Sablatnig. A Method for Determining Geometrical Distortion of Off-The-ShelfWide-Angle Cameras[J]. Lecture notes in computer science,2005,12(27):424-429
[94]甘金来.图像边缘检测算法的比较研究[D].成都：电子科技大学，2005,13-43
[95] A. Jan. V. Mieghem, I. Hadar, et al.. Melen.Straight Line Extraction Using Iterative Total LeastSquares Methods[J]. Journal of Visual Communication and Image Representation tation,1995,6(1):659-668
[96] F. Pernekopf, O. L. Paul. Image Acquisition Techniques for Automatic Visual Inspection ofMetallic Surface [J]. NDT&E International,2003,36(8):609-617
[97] Q. M. Hu, Z. J. Hou, N. Wieslawl. Supervised Range-Constrained Thresholding[J]. IEEETransactions on Image Processing,2006,15(1):228-240
[98] P. Felzenszwalb, Huttenlocher. Efficient Graph-Based Image Segmentation[J].Int.ComputerVision,2004,59(2):167-181
[99] J. Zhang, Y. T. Ye, Y. Xie, et al. High Density Print Circuit Board Line Width MeasurementAlgorithm Based on Statistical Process Control Theory[J]. Optik,2013,9(1):62-66
[100] M. Pietikainen, A. Hadid, G. Zhao, et al. Computer Vision Using Local Binary Patterns [M].Germany: Springer,2011,13-47
[101]毋小省，孙君顶.基于局部边缘二值模式的图像检索[J].光电子激光，2013,24(2):184-190
[102] N. Loris, L. Alessandra, B. Sheryl. Survey on LBP Based Texture Descriptors for ImageClassification [J]. Expert System with Applications,2012,39(9):3934-3641
[103] X. F. He, F. Frank. Flat-Panel Color Filter Inspection[J].Vision Systems Design. May1,2011,16(5):789-797
[104] S. Lee, L. M. Chang, M. Skibniewski. Automated Recognition of Surface Defects UsingDigital Color Image Processing[J]. Automation in Construction,2006,15(4):540-449
[105] T. H.Sun, C.C. Teng, M.S. Cheng, et al.. Electric Contacts Inspection Using Machine Vision[J].Image and Vision Computing,2010,28(6):890-901
[106] E. Rathu, M. Salo, J. Heikkila. Affine Invariant Pattern Recognition Using Multi-ScaleAuto-Convolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(6):908-918
[107] H. W. Chang. Detecting Low-Contrast Defect Regions on Glasses Using Highly RobustModel-Fitting Estimator[C], International Conference on Control, Automation and Systems,Oct.,2007,17-20
[108] Z. H. Wei, G. L. Zhang. The Application of Machine Vision in Inspecting Position-ControlAccuracy of Motor Control Systems[C]. Proceedings of the Fifth International Conference onElectrical Machines and Systems, Shenyang, P.R. China: ICEMS,2001,1031-1038
[109] Fernandez C, Platero C, Campoy P, Aracil R. Vision System for Online Surface Inspection InAluminium Casting Process[C]. IEEE Conference on Industrial Electronics, Control,Instrumentation and Automation.1993,1854-1859
[110] J. H. Wang. A Topology Set Method for Vectorization[J]. Eighth ACIS InternationalConference on Software Engineering, IEEE,2007,9(6):229-234
[111] Z. Wang, A. C. Bovik, H. R. Sheikh, et al.. Image Quality Assessment: form Error Visibility toStructural Similarity[J]. IEEE Transactions on Image Processing,2004,13(4):600-612
[112] Z. Roman, M. Elad, M. Protter.On Single Image Scale-Up Using Sparse Representation[C].Proceedings of the7thInternational Conference on Curves and Surfaces, Avignon, France,June2010,456-462
[113] G. Davis, S. Mallat, M. Avellaneda. Adaptive Greedy Approximations[J]. Journal ofConstructive Approximation,1997,13(1):57-98
[114] M. G. Sicairos, T. Samuel. Thurman, James R. Fienup. Efficient Subpixel Image RegistrationAlgorithms [J].Optics Letters,2008,33(2):156-158
[115] T. Blumensath, M. E. Davies. On the Difference Between Orthogonal Matching Pursuit andOrthogonal Least Squares[EB/OL].http://users.fmrib.ox.ac.uk/~tblumens/publications.html,2007
[116] J. Kaipio, E. Somersalo. Statistical and Computational Inverse Problems[M]. AppliedMathematical Sciences, vol.160, Springer, USA,2004,70-156
[117]章毓晋.图像工程(中册)-图像分析[M].北京:清华大学出版社，2005,35-100
[118]张梅,文静华,张祖勋,等.微分运算与形态学深度图像分割比较[J].计算机工程与应用,2010，46(19):1173-1176
[119] C. M Shakarji. Least-Squares Fitting Algorithms of The NIST Algorithm Testing System[J].Journal of Research of the National Institure of Standards and Technology,1998,103(6):634-637
[120] B. Reddy, B. Chatterji. An FFT-based Technique for Translation, Rotation and Scale-InvariantImage Registration[J]. IEEE Transaction on Image Processing,1996,5(8):1266-1271
[121] D. Demigny, F. G. Lorca, L. Kessal. Evaluation of Edge Detectors Performances with ADiscrete Expression of Canny’s Criteria. In: Proceedings of International Conference on ImageProcessing[C], Los Alamitos, CA, USA: IEEE, Computer SOC Press.1995,1242-1249
[122] P. L. Worthington. Enhanced Canny Edge Detection Using Curvature Consistency[C]. In:Proceedings International Conference on Pattern Recognition.2002,897-904
[123] D. Demigny, T. A. Kamle, Discrete Expression of Canny’s Criteria for Stepedge DetectorPerformances Evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,16(9):636-645
[124] X. H. Ying,H. B. Zha. An Efficient Method for the Detection of Projected ConcentricCircle[C]. IEEE International Conference on Information Processing.2007,789-795
[125] D. M. Kwak, W. S. Kim, D. H. Choi, et al. Vision-Based Mura Detection for TFT-LCD Panel[C]. Int. Conf. on Computer, Communication and Control Technologies, Orlando, Florida,USA October31,2003,1328-1336
[126]姜长城.中小尺寸TFT-LCD玻璃基板检测装备的光机电系统研究[D].广州：华南理工大学，2012,32-34
[127] B. David, W. H. WU.大规模并行处理器编程实践[M]．北京：清华大学出版社，2010,4-5
[128] Wei G W. Generalized Perona-Malik Equation for Image Restoration[J]. IEEE Signal andProcessing.1999,22(6):865-873
[129] B. Reddy, B. Chatterji B. An FFT-Based Technique for Translation, Rotation andScale-Invariant Image Registration[J]. IEEE Transaction on Image Processing,1996,5(8):1266-1271
[130] H. Zhou, J. Y. Ren, X. X. Zhang, et al.. Design of Imaging System Based on CCD in FieldReadout Mode[J]. Microcomputer Information,2009,16(32):1151-1162
[131] K. W. Pratt. Digital image processing: PIKS Inside, Third Edition[M]. John Wiley&Sons, Inc.2001,8-90
[132] T. Blu, P. Thevenaz, M. Unser.Linear Interpolation Revitalized[J]. IEEE Transactions onImage Processing,2004,13(5):710-719
[133]朱鉴,吴恩华.基于GPU的球面深度图实时绘制[J].计算机学报，2009,32(2),231-240
[134]杨正龙,金林,李蔚清.基于GPU的图形电磁计算加速算法[J].电子学报，2007,35(6),1056-1060
[135] Changki Jeong, Jinwoo Yoo, PooGyeon Park, A Defect Inspection Method for TFT PanelUsing The Compute Unified Device Architecture (CUDA)[C]. IEEEInternational Symposiumon Industrial Electronics, Seoul,2009,779-782
[136]张舒,褚艳利. GPU高性能计算之CUDA[M].中国水利水电出版社，2009,5-60
[137]刘万春，刘建君，朱玉文，等，一种实时高速的八连通区域填充算法[J]，计算机应用研究，2006,6(2):177-179
[138] J. Sanders, E. Kandrot. CUDA by Example[M].北京：清华大学出版社，2010,10-20
[139] J. D. Hall, N. A. Carr, J. C. Hart.Cache and Bandwidth Aware Matrix Multiplication on TheGPU [R]. UIUCDCS-R-2003-2328, Champaign: University of Illinois at Urbana-Champaign,2003
[140] J. Bolz, I. Farmer, E. Grinspun, et al. Sparse Matrix Solvers on The GPU: Conjugate Gradientsand Multi-Grid[J]. ACM Transactions on Graphics,2003,22(3):917-924
[141] N. Fujimoto.Dense Matrix-Vector Multiplication on The CUDA Architecture[J].ParallelProcessing Letters,2008,18(4),511-530
[142]吴恩华,柳有权.基于图形处理器(GPU)的通用计算[J].计算机辅助设计与图形学学报，2004,16(5),601-612
[143]曹锋,周傲英.基于图形处理器的数据流快速聚类[J].软件学报，2007,18(2),291-302.
[144] A. Nukada, S. Matsuoka.Auto-Tuning3-D FFT Library for CUDA GPUs[C]. InternationalConference for High Performance Computing, Networking, Storage and Analysis, SC,2008,1-11
[145] B. Nathan, G. Michael.Efficient Sparse Matrix-Vector Multiplication on CUDA[R].NVIDIATechnical Report NVR-2008-004, Dec,2008
[146] Y. Liu, E. Z. Zhang, X. Shen. A Cross-Input Adaptive Framework for GPU ProgramOptimizations [C]. Los Alamitos, CA, USA,2009,1–10
[147]储璟骏,杨新,高艳.使用GPU编程的光线投射体绘制算法[J].计算机辅助设计与图形学学报，2007,19(2):257-262
[148] A. Fitsgibbon, N. Pilu, F. Robert. Directleast square fitting of ellipse[J]. IEEE Transactions onPattern Analysis and Machine Intelligence.1999,12(4):234-240
[149] Y. S. Xu, J. B. Weaver, M. J. Healy. A Spatially Selective Noise Filtration Technique[J]. IEEETrans Image Processing,2000,9(9):1532-1546
[150] G. Jiang, L. Quan.Detection of Concentric Circles for Camera Calibration[C].10th IEEEInternational Conference on Computer Vision.2005,609-616
[151] M. Monoi., S. Sasaki, K. Dobashi., et al..A Single-Layer CCD Image Sensor with Side GapElectrode and Gradual Potential Channel[C]. Society of Photo-Optical InstrumentationEngineers (SPIE) Conference Series, SPIE,2009,724-732
[152]英特尔亚太研发有限公司,北京并行科技公司．释放多核潜能[M]．北京：清华大学出版社，2010,2-6
[153] M. Elad, J. L. Starck, P. Querre, et al.. Simultaneous Cartoon and Texture Image InpaintingUsing Morphological Component Analysis (MCA)[J]. Applied and Computational HarmonicAnalysis,2005,19(3):340-358
[2] M. Moganti, F. Ercal. Automaticprinted Circuited Board Inspection Systems[J].IEEE Potentials,1995,14(3):6-10
[3] C. Steger, M. Ulrich.机器视觉算法与应用[M].(杨少荣).北京：清华大学出版社，2008,1-4
[4]刘金桥，吴金强.机器视觉系统发展及其应用[J].机械工程与自动化，2010,2(1):215-216
[5]张五一，赵强松，王东云.机器视觉的现状及发展趋势[J].中原工学院学报，2008,19(1):9-11
[6]胡涛.基于轮廓对比的PCB裸板缺陷检测算法研究[D].武汉：华中科技大学，2009,11-20
[7] H. G. da Silva, T. G. Amaral, O. P. Dias. Automatic Optical Inspection for Detecting DefectiveSolders on Printed Circuit Boards[C].Annual Conference on IEEE Industrial Electronics Society,Melbourne,2010,36:1087-1091
[8]潘明.基于机器视觉的大张印刷质量光电检查系统研究[D].成都：电子科技大学，2011,50-60
[9]柏长冰，齐春，宋福民，等. Hough变换快速检测圆形PCB Mark [J].光电工程，2005，32(9)：75-78
[10]乔闹生，叶玉堂，莫春华，等.印刷电路板光电图像畸变校正研究[J].光电子激光，2009,20(11):1548-1551
[11] N. Talbot. The Use of Automated Optical Testing (AOT) in Statistical Process Control (SPC) forPrinted Circuit Board (PCB) Production [J].Circuit World,2003,29(4):19~22
[12]黄永林，叶玉堂. PCB导线上下线宽检测算法研究[J].计量学报，2011,32(8):766-771
[13]戴维斯.机器视觉：理论、算法与实践（英文版第3版）[M].北京：人民邮电出版社，2009,150-161
[14]章毓晋.图像工程(上册)图像处理(第2版)[M].北京:清华大学出版社，2006,29-35
[15]胡跃明,谭颖.自动光学检测在中国的应用现状和发展[J].微计算机信息，2006,12(4):143-146
[16] R. F. Sajal, M. Kamruzzamman, F. Ahmed Jewel.Machine Vision Based Automatic System forReal Time Recognition and Sorting of Bangladeshi Bank Notes[C]. International Conference onComputer and Information Technology,2008,356-358
[17] T. T. Chung, Y. C. Huang. Optimum Desisn of A high Precision AOI Machine Structure[C].International Conference on Mechanical and Electronics Engineering,2010,164-168
[18]卢荣胜.自动光学检测技术的发展现状[J].红外与激光工程，2008,37(4):120-124
[19]刘霞．PCB光电自动外观检查机的光学及软件部分设计及实现[D].成都：电子科技大学，2010,1-14
[20]韩芳芳.表面缺陷视觉在线检测关键技术研究[D].天津：天津大学，2011,3-7
[21]毕昕,丁汉. TFT-LCD Mura缺陷机器视觉检测方法[J].机械工程学报，2010,46(12):13-19
[22] M. Moganti, F. Ereal. Automatic PCB Inspection Algorithms Asurvey[J]. Computer Vision andImage Understanding.1996,63(2):287-313
[23]梅领亮.PCB最终外观检查机关键技术研究[D].成都：电子科技大学，2010,3-16
[24] N. Mar, P. Yarlagadda, C. Fookesc. Design and Development of Automatic Visual InspectionSystem for PCB Manufacturing [J]. Robotics and Computer Integrated Manufacturing,2011,27(5):949-962
[25] S. Kishimoto, N. Kakimori, Y. Yamamoto, et al.. A printed Circuit Board (PCB) InspectionSystem Employing the Multi-lighting Optical System[C].8th IEMT International ElectronicManufacturing Technology Conference, IEEE,1990,120-129
[26] W. Y. Wu, M. J. J. Wang, C. M. Liu, et al. Automated Inspection of Printed Circuit Boardsthrough Machine Vision [J]. Computer in Industry,1996,28(2):103-111
[27] H. Zheng, L. X. Kong, S. Nahavandi. Automatic Inspection of Metallic Surface Defects UsingGenetic Algorithms [J]. Journal of Materials Processing Technology,2002,12(6):427-433
[28] D. Z. WANG, C. H. WU, I. ANDREW, et al.. Fast Multi-Template Matching Using a ParticleSwarm Optimization Algorithm for PCB Inspection[C]. Conference European Workshops onthe Theory and Applications of Evolutionary Computation,2008,365-370
[29] E. K. Teoh, D. P. Mital, B. W. Lee, et al.. Automated Visual Inspection of Surface Mount PCB[J]. Signal Processing and System Control Factory Automation,1990,20(8):576-580
[30] HAE-WON OH, TAE-HYUNG PARK. Gerber-character Recognition System of Auto-teachingProgram for PCB Assembly Machines[C]. SICE Annual Conference,2004,8(2):300-305
[31] J. P. Jones, L.A. Palmer. An Evaluation of the Two-Dimensional Gabor Filter Model of SimpleReceptive Fields in Cat Striate Cortex[J]. Neurophysiology.1987,23(8):1233-1244
[32] A. V. Bhavsar, A. N. Rajagopalan. Range Map with Missing Data Joint ResolutionEnhancement and Inpainting[J].2008Sixth Indian Conference on Computer Vision, Graphics&Image Processing, IEEE,2008:259-365
[33] E. Candes, J. Romberg, T. Tao. Robust Uncertainty Principles: Exact Signal Reconstructionfrom Highly Incomplete Frequency Information[J]. IEEE Transactions on Information Theory,2006,52(2):489-509
[34] M. Elad, M. Figueiredo, Y. Ma. On the Role of Sparse and Redundant Representations in ImageProcessing[J]. Proceedings of the IEEE-Special Issue on Applications of SparseRepresentation and Compressive Sensing,2010,98(6):1451-1459
[35] L. Zhang, X. L. Wu.An Edge-Guided Image Interpolation Algorithm via Directional Filteringand Data Fusion [J]. IEEE Transactions on Image Processing,2006,15(8):2226-2238
[36] H. Chui, A. Rangarajan, A new Point Matching Algorithm for Non-rigid Registration, CVIU,2003,89(2-3):114-141
[37] M. J. Chen, C. H. Huang, W. L. Lee. A fast Edge-oriented Algorithm for Image Interpolation[J].Image and Vision Computing,2005,23(9):791-798
[38]朱宏殷，郭永飞，司国良.多TDICCD拼接相机成像非均匀性实时校正的硬件实现[J].光学精密工程，2011,12(19):3025-3041
[39]吴福培，邝泳聪，张宪民，等．基于模式匹配及其参数自适应的PCB焊点检测[J].光学精密工程，2009,17(10):2586-2593
[40]袁红中，付炜，郭永魁.一种基于动态阈值的镀铜表面缺陷检测算法[J].燕山大学学报，2018,34(4):336-340
[41]刘建伟，梁晋，梁新合，等.大尺寸工业视觉测量系统[J].光学精密工程，2010,18(1)：126-134
[42]薛骏.基于机器视觉的表面贴装元件检测技术研究[D].成都：西南交通大学，2008,25-30
[43]卢素涵.2006年全球自动光学检测(AOI)设备市场概况[EB/OL],http://optics.ofweek.com/2008-01/ART-250003-8400-13713001.html, Jan.21,2008
[44]牛玉洲,宋培华,张建正.机器视觉在铜箔基板疵点在线检测系统中应用[J].微计算机信息，2001,12(11):730-736
[45]余丛华.基于机器视觉的纺织品缺陷检测系统研究与设计[D].武汉：武汉工程大学，2012,14-20
[46]杨高科.基于虚拟仪器的质量检测机器视觉系统[D].西安：西北大学，2002,12-14
[47] H. K. Cheung, et al. A Novel Illumination Compensation Scheme for Sprite Coding[C].ICSP’04Proceedings.2004,1223-1227
[48]章毓晋，图像分割[M].北京：清华大学出版社，2002,137~157
[49]吴平川，路同浚，王炎.机器视觉与钢板表面缺陷的无损检测[J].无损检测，2000，22(1):13-16
[50]蒲亮,叶玉堂,宋昀岑，等.基于优化K-D树的大面积高密度PCB快速AOI[J].仪器仪表学报，2011,32(4):955-960
[51] R. C.冈萨雷斯, P.温茨．数字图像处理[M].北京：电子工业出版社，2011,423-480
[52] S. Somatilake, A.N. Chalmers. An Image Based Food Classification System[C]. Proceedings ofImage and VisionComputing, New Zealand.2007,260-265
[53]张洪涛.钢板表面缺陷在线视觉检测系统关键技术研究[D].天津：天津大学，2008,9-11
[54] Jae-Kang Lee, Il-Hwan Kim. New Recognition Algorithm for Various Kinds of Euro Banknotes[J]. Industrial Electronics Society,2003,23(12):2266-2270
[55] J. H. Kim, S. Ahn, J. W Jeon, et al.. Byun. A High-Speed High-Resolution Vision System for theInspection of TFT LCD[C], Proceedings.ISIE2001. IEEE Int. Symposium on IndustrialElectronic.2001,101-105
[56] X. Tan, B. Triggs. Enhanced Local Texture Feature Sets for Face Recognition under DifficultLighting Conditions[J]. IEEE Transactions on Image Processing,2010,19(6):1635-1650
[57] S. N. Chiu, M. H. PERN. Reflection-Area-Based Feature Descriptor for Solder Joint Inspection[J].Machine Vision and Applications.2007,8(12):95-106
[58] Z. L. Shu, F. H. Qi. A novel algorithm for fast circle detection using randomized Houghtransforms[J]. Computer Engineering,2003,29(6):86-89
[59]曹智文.基于机器视觉的线结构光尺寸测量系统[D].武汉:湖北工业大学，2012,15-20
[60] L. Calvin, Snyder.并行程序设计原理[M].北京：机械工业出版社，2009,22-24
[61] G. T. Mattson, A. B. Sanders, L. Berna.并行编程模式[M]．北京：清华大学出版社，2005,7-9
[62] B.Wilkinson, M.Allen.并行程序设计[M]．北京：机械工业出版社，2005,1-4
[63]周伟明,多核计算与程序设计[M].武汉：华中科技大学出版社，2009,10-11
[64]黄杰贤,李迪,叶峰,等．挠性印制电路板焊盘表面缺陷的检测[J].光学精密工程，2010,18(11):2443-2553
[65]胡亮.基于线阵CCD钢板表面缺陷在线检测系统的研究[J].计量学报，2005(7):200-203
[66]王勤.高速线阵CCD图像数据采集系统的研究[D].天津：天津大学，2005,1-13
[67]姚蛟，叶玉堂，张静，等. PCB自动光学检测中Gerber文件的解析研究[J].计算机工程与设计，2012,33(6):2481-2485
[68]彭向前,陈幼平,余文勇.一种基于机器视觉的浮法玻璃质量在线检测系统[J].制造业自动化，2007,29(12):50-53
[69]吴凤和.基于计算机视觉测量技术的图像轮廓提取方法研究[J].计量学报，2007,28(1):18-22
[70]吕恒毅，刘杨，郭永飞.遥感相机焦面CCD机械拼接中重叠像元数的确定[J].光学精密工程，2012,5(20):1042-1046
[71]李俊.机器视觉照明光源关键技术研究[D].天津:天津理工大学，2006,14-26
[72]赵媛.基于PWM的LED机器视觉光源技术的研究[D].哈尔滨：哈尔滨工业大学，2009,8-14
[73]韩志冲，钟嫄等.单片机控制信号采集的软硬件设计及其在光源测量系统中的应用[J].电子器件，2008,23(8)：643-645
[74]张未强,陆洋.如何为机器视觉系统选择采集卡[J].可编程控制器与工厂自动化.2005,23(7):34-40
[75]陈博洋，赖雪峰，陈桂林等.线阵CCD相机的研制[J].科学技术与工程，2007，12(11)：43-51
[76] K. C. Liu, S. Wang, W. Shao, et al.. Color-Edge Detection Based on Discrimination ofNoticeable Color Contrasts[J]. International Journal of Imaging Systems and Technology,2009,19(4):332-339
[77] L. G. Shapiro， G. C. Stockman，赵清洁译.计算机视觉[M].北京：机械工业出版社，2005,224-230
[78] D. C. Montgomery. Design and Analysis of Experiments, Fifth Edition[M]. New York: JohnWiley,2006,60-112
[79] Perona P, Malik J. Scale-Space and Edge Detection Using Anisotropic Diffusion[J], IEEE Trans.Pat. Anal.Machine Intel.1990,12(7):629-639
[80]张洪涛，段发阶，叶声华.一种快速亚像素边缘检测方法研究[J].计量学报，2002,23(4):263-265
[81]黄永林，叶玉堂，陈镇龙，等.一种新的快速Hough变换圆检测方法[J].电子测量与仪器学报，2010(9):837-842
[82]腾今朝,邱杰.利用Hough变换实现直线的快速精确检测[J].中国图象图形学报，2008,17(6):68-75
[83] L. Xu, E. Oja, P. Kultanen. A New Curve Detection Method Randomized HoughTransform(RHT)[J]. Pattern Recognition Letters,1990,11(5):331-338
[84] G. W. Wei. Generalized Perona-Malik Equation for Image Restoration [J]. IEEE SignalProcessing,1999,6(5):65-167
[85] H. C. V. Assen, P. M. Egmont, J. H. C.Reiber. Accurate Object Localization in Gray LevelImages Using the Center of Gravity Measure: Accuracy Versus Precision[C]. IEEETransactions on Image Processing(S1057-7149),2002,11(12):1379-1384
[86] L. Xu, E. Oja Randomized Hough Transform (RHT): Basic Mechanisms Algorithms andComputational Complexities[J]. CVGIP: Image Understanding,1993,57(2):131-154
[87]尚会超.印刷图像在线检测的算法研究与系统实现[D].武汉：华中科技大学，2006,81-84
[88] C. Chadwick. Five degrees of freedom[J]. Vision Systems Design, Dec.,2011,16(12):625-632
[89] Nitin Aggarwal, William Clem Karl. Line Detection in Images Through RegularizedHoughtransform[J].IEEE Transactions on image processing,2006,15(3):582-591
[90] Q. Z. Ye, P. E. Danielsson. Inspection of Printed Circuit Boards by Connectivity PreservingShrinking[J]. IEEE Transactions on Pattern Analysis and Mach Intelligence,1988,10(5):737-742
[91] A. Nakib，H. Oulhadj，P. Siarry．Image Histogram ThresholdingBased on MultiobjectiveOptimization[J]．Signal Processing,2007,87(11):2516-2534
[92] J. A. Canny. Computational Approach to Edge Detection[J]. IEEE Trans. On PAMI,1986,8(6):679-698
[93] H. Zollner, R. Sablatnig. A Method for Determining Geometrical Distortion of Off-The-ShelfWide-Angle Cameras[J]. Lecture notes in computer science,2005,12(27):424-429
[94]甘金来.图像边缘检测算法的比较研究[D].成都：电子科技大学，2005,13-43
[95] A. Jan. V. Mieghem, I. Hadar, et al.. Melen.Straight Line Extraction Using Iterative Total LeastSquares Methods[J]. Journal of Visual Communication and Image Representation tation,1995,6(1):659-668
[96] F. Pernekopf, O. L. Paul. Image Acquisition Techniques for Automatic Visual Inspection ofMetallic Surface [J]. NDT&E International,2003,36(8):609-617
[97] Q. M. Hu, Z. J. Hou, N. Wieslawl. Supervised Range-Constrained Thresholding[J]. IEEETransactions on Image Processing,2006,15(1):228-240
[98] P. Felzenszwalb, Huttenlocher. Efficient Graph-Based Image Segmentation[J].Int.ComputerVision,2004,59(2):167-181
[99] J. Zhang, Y. T. Ye, Y. Xie, et al. High Density Print Circuit Board Line Width MeasurementAlgorithm Based on Statistical Process Control Theory[J]. Optik,2013,9(1):62-66
[100] M. Pietikainen, A. Hadid, G. Zhao, et al. Computer Vision Using Local Binary Patterns [M].Germany: Springer,2011,13-47
[101]毋小省，孙君顶.基于局部边缘二值模式的图像检索[J].光电子激光，2013,24(2):184-190
[102] N. Loris, L. Alessandra, B. Sheryl. Survey on LBP Based Texture Descriptors for ImageClassification [J]. Expert System with Applications,2012,39(9):3934-3641
[103] X. F. He, F. Frank. Flat-Panel Color Filter Inspection[J].Vision Systems Design. May1,2011,16(5):789-797
[104] S. Lee, L. M. Chang, M. Skibniewski. Automated Recognition of Surface Defects UsingDigital Color Image Processing[J]. Automation in Construction,2006,15(4):540-449
[105] T. H.Sun, C.C. Teng, M.S. Cheng, et al.. Electric Contacts Inspection Using Machine Vision[J].Image and Vision Computing,2010,28(6):890-901
[106] E. Rathu, M. Salo, J. Heikkila. Affine Invariant Pattern Recognition Using Multi-ScaleAuto-Convolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(6):908-918
[107] H. W. Chang. Detecting Low-Contrast Defect Regions on Glasses Using Highly RobustModel-Fitting Estimator[C], International Conference on Control, Automation and Systems,Oct.,2007,17-20
[108] Z. H. Wei, G. L. Zhang. The Application of Machine Vision in Inspecting Position-ControlAccuracy of Motor Control Systems[C]. Proceedings of the Fifth International Conference onElectrical Machines and Systems, Shenyang, P.R. China: ICEMS,2001,1031-1038
[109] Fernandez C, Platero C, Campoy P, Aracil R. Vision System for Online Surface Inspection InAluminium Casting Process[C]. IEEE Conference on Industrial Electronics, Control,Instrumentation and Automation.1993,1854-1859
[110] J. H. Wang. A Topology Set Method for Vectorization[J]. Eighth ACIS InternationalConference on Software Engineering, IEEE,2007,9(6):229-234
[111] Z. Wang, A. C. Bovik, H. R. Sheikh, et al.. Image Quality Assessment: form Error Visibility toStructural Similarity[J]. IEEE Transactions on Image Processing,2004,13(4):600-612
[112] Z. Roman, M. Elad, M. Protter.On Single Image Scale-Up Using Sparse Representation[C].Proceedings of the7thInternational Conference on Curves and Surfaces, Avignon, France,June2010,456-462
[113] G. Davis, S. Mallat, M. Avellaneda. Adaptive Greedy Approximations[J]. Journal ofConstructive Approximation,1997,13(1):57-98
[114] M. G. Sicairos, T. Samuel. Thurman, James R. Fienup. Efficient Subpixel Image RegistrationAlgorithms [J].Optics Letters,2008,33(2):156-158
[115] T. Blumensath, M. E. Davies. On the Difference Between Orthogonal Matching Pursuit andOrthogonal Least Squares[EB/OL].http://users.fmrib.ox.ac.uk/~tblumens/publications.html,2007
[116] J. Kaipio, E. Somersalo. Statistical and Computational Inverse Problems[M]. AppliedMathematical Sciences, vol.160, Springer, USA,2004,70-156
[117]章毓晋.图像工程(中册)-图像分析[M].北京:清华大学出版社，2005,35-100
[118]张梅,文静华,张祖勋,等.微分运算与形态学深度图像分割比较[J].计算机工程与应用,2010，46(19):1173-1176
[119] C. M Shakarji. Least-Squares Fitting Algorithms of The NIST Algorithm Testing System[J].Journal of Research of the National Institure of Standards and Technology,1998,103(6):634-637
[120] B. Reddy, B. Chatterji. An FFT-based Technique for Translation, Rotation and Scale-InvariantImage Registration[J]. IEEE Transaction on Image Processing,1996,5(8):1266-1271
[121] D. Demigny, F. G. Lorca, L. Kessal. Evaluation of Edge Detectors Performances with ADiscrete Expression of Canny’s Criteria. In: Proceedings of International Conference on ImageProcessing[C], Los Alamitos, CA, USA: IEEE, Computer SOC Press.1995,1242-1249
[122] P. L. Worthington. Enhanced Canny Edge Detection Using Curvature Consistency[C]. In:Proceedings International Conference on Pattern Recognition.2002,897-904
[123] D. Demigny, T. A. Kamle, Discrete Expression of Canny’s Criteria for Stepedge DetectorPerformances Evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,16(9):636-645
[124] X. H. Ying,H. B. Zha. An Efficient Method for the Detection of Projected ConcentricCircle[C]. IEEE International Conference on Information Processing.2007,789-795
[125] D. M. Kwak, W. S. Kim, D. H. Choi, et al. Vision-Based Mura Detection for TFT-LCD Panel[C]. Int. Conf. on Computer, Communication and Control Technologies, Orlando, Florida,USA October31,2003,1328-1336
[126]姜长城.中小尺寸TFT-LCD玻璃基板检测装备的光机电系统研究[D].广州：华南理工大学，2012,32-34
[127] B. David, W. H. WU.大规模并行处理器编程实践[M]．北京：清华大学出版社，2010,4-5
[128] Wei G W. Generalized Perona-Malik Equation for Image Restoration[J]. IEEE Signal andProcessing.1999,22(6):865-873
[129] B. Reddy, B. Chatterji B. An FFT-Based Technique for Translation, Rotation andScale-Invariant Image Registration[J]. IEEE Transaction on Image Processing,1996,5(8):1266-1271
[130] H. Zhou, J. Y. Ren, X. X. Zhang, et al.. Design of Imaging System Based on CCD in FieldReadout Mode[J]. Microcomputer Information,2009,16(32):1151-1162
[131] K. W. Pratt. Digital image processing: PIKS Inside, Third Edition[M]. John Wiley&Sons, Inc.2001,8-90
[132] T. Blu, P. Thevenaz, M. Unser.Linear Interpolation Revitalized[J]. IEEE Transactions onImage Processing,2004,13(5):710-719
[133]朱鉴,吴恩华.基于GPU的球面深度图实时绘制[J].计算机学报，2009,32(2),231-240
[134]杨正龙,金林,李蔚清.基于GPU的图形电磁计算加速算法[J].电子学报，2007,35(6),1056-1060
[135] Changki Jeong, Jinwoo Yoo, PooGyeon Park, A Defect Inspection Method for TFT PanelUsing The Compute Unified Device Architecture (CUDA)[C]. IEEEInternational Symposiumon Industrial Electronics, Seoul,2009,779-782
[136]张舒,褚艳利. GPU高性能计算之CUDA[M].中国水利水电出版社，2009,5-60
[137]刘万春，刘建君，朱玉文，等，一种实时高速的八连通区域填充算法[J]，计算机应用研究，2006,6(2):177-179
[138] J. Sanders, E. Kandrot. CUDA by Example[M].北京：清华大学出版社，2010,10-20
[139] J. D. Hall, N. A. Carr, J. C. Hart.Cache and Bandwidth Aware Matrix Multiplication on TheGPU [R]. UIUCDCS-R-2003-2328, Champaign: University of Illinois at Urbana-Champaign,2003
[140] J. Bolz, I. Farmer, E. Grinspun, et al. Sparse Matrix Solvers on The GPU: Conjugate Gradientsand Multi-Grid[J]. ACM Transactions on Graphics,2003,22(3):917-924
[141] N. Fujimoto.Dense Matrix-Vector Multiplication on The CUDA Architecture[J].ParallelProcessing Letters,2008,18(4),511-530
[142]吴恩华,柳有权.基于图形处理器(GPU)的通用计算[J].计算机辅助设计与图形学学报，2004,16(5),601-612
[143]曹锋,周傲英.基于图形处理器的数据流快速聚类[J].软件学报，2007,18(2),291-302.
[144] A. Nukada, S. Matsuoka.Auto-Tuning3-D FFT Library for CUDA GPUs[C]. InternationalConference for High Performance Computing, Networking, Storage and Analysis, SC,2008,1-11
[145] B. Nathan, G. Michael.Efficient Sparse Matrix-Vector Multiplication on CUDA[R].NVIDIATechnical Report NVR-2008-004, Dec,2008
[146] Y. Liu, E. Z. Zhang, X. Shen. A Cross-Input Adaptive Framework for GPU ProgramOptimizations [C]. Los Alamitos, CA, USA,2009,1–10
[147]储璟骏,杨新,高艳.使用GPU编程的光线投射体绘制算法[J].计算机辅助设计与图形学学报，2007,19(2):257-262
[148] A. Fitsgibbon, N. Pilu, F. Robert. Directleast square fitting of ellipse[J]. IEEE Transactions onPattern Analysis and Machine Intelligence.1999,12(4):234-240
[149] Y. S. Xu, J. B. Weaver, M. J. Healy. A Spatially Selective Noise Filtration Technique[J]. IEEETrans Image Processing,2000,9(9):1532-1546
[150] G. Jiang, L. Quan.Detection of Concentric Circles for Camera Calibration[C].10th IEEEInternational Conference on Computer Vision.2005,609-616
[151] M. Monoi., S. Sasaki, K. Dobashi., et al..A Single-Layer CCD Image Sensor with Side GapElectrode and Gradual Potential Channel[C]. Society of Photo-Optical InstrumentationEngineers (SPIE) Conference Series, SPIE,2009,724-732
[152]英特尔亚太研发有限公司,北京并行科技公司．释放多核潜能[M]．北京：清华大学出版社，2010,2-6
[153] M. Elad, J. L. Starck, P. Querre, et al.. Simultaneous Cartoon and Texture Image InpaintingUsing Morphological Component Analysis (MCA)[J]. Applied and Computational HarmonicAnalysis,2005,19(3):340-358
© 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 |