基于模板的异常检测系统及其关键技术研究
|
摘要
随着工业、军事等领域对异常检测需求的日益增大,加之高性能、高可靠性图像处理算法的日益成熟,促使机器视觉技术广泛应用于异常检测当中。针对实际需求和一些亟待解决的问题,本文开展研究,设计并实现了基于模板的异常检测系统。
针对单一的异常检测算法无法普遍适用于各种应用环境和不同特征检测对象的问题,提出采用工厂策略模式对系统的异常检测算法模块进行设计,并实现了利用灰度信息配准匹配的异常检测和利用轮廓信息对准匹配两种适用于不同应用场合的异常检测方法。通过工厂策略模式和相应的配置文件,在应用环境或者检测对象的特征发生变化时,客户可以动态创建、配置和加载符合当前异常检测需求的算法,确保在当前应用中,异常检测模块能在快速、稳定、准确之间保持很好的平衡。
针对利用灰度信息模板匹配的异常检测方法容易受到摄像机抖动和环境光照变化影响的问题,设计了一种具备容错能力的分块投影匹配法,实现了摄像机抖动的图像纠正；接着在介绍了利用高斯滤波器和多项式拟合消除光照变化方法的基础上,提出了实时性能更好的Wallis变换法来消除光照变化的影响；最后基于加权多区域差分矩阵进行异常决策。实践证明,在摄像机抖动量不大,光照连续变化的情况下,该方法能实现快速、准确地检测异常。
针对利用轮廓信息对准匹配的异常检测方法对轮廓点分割的准确度要求很高的特点,首先对比了常用的边缘检测算法,提出采用Canny算子来准确提取图像的边缘,克服了传统边缘检测算子易受噪声干扰和粗轮廓的问题。接着基于边界追踪构建目标轮廓,同时计算轮廓的链码熵、链码空间分布熵和轮廓矩。最后先基于全局特征相似度的粗匹配在待检测图像中找到包含待检测对象的所有区域,再基于轮廓对准的细匹配进行异常判断,并精确地定位轮廓上异常的具体位置。
针对注塑模具的保护需求,实现了基于模板的异常检测系统。实践证明,本文提出的异常检测算法能够保证检测的实时性和准确性,阶段性地达到了研究的目的。
With the demand for abnormity detection increased day by day in industrial and military fields,high-performance and high reliability image processing algorithms become more mature, which promotes machine vision technology widely used in abnormity detection.Aimed at the actual demand and a number of issues needed to be addressed, this paper carried out the research, designed and implemented a template-based abnormity detection system.
Aimed at the problem that a single abnormity detection algorithm can't be universally suitable for various application environments and detection objects of different characteristics, we proposed the plant strategy model to design the abnormity detection module of the system and realized two kinds of abnormity detection methods:registration matching using gray information and alignment matching using contour information, which are suitable for different application situation.Through the plant strategy model and some corresponding configuration files, whether application environment or the characteristic of the detection object changes,the client can dynamically create,configure,and load the algorithm meeting the current demand of abnormity detection to ensure that the abnormity detection module can get a good balance among rapidity, stability and accuracy in the current application.
Aimed at the problem that the abnormity detection method of template matching using gray information is easy to be influenced by camera vibration and illumination change, this paper firstly designed a fault-tolerant block projection matching method to realize the image correction of camera vibration, and then proposed the Wallis transformation method to eliminate illumination change, which is more real-time than the mothed using Gaussian filter and polynomial fitting introduced before. Finally, carrying out abnormity decision based on weighted multi-areas difference matrix.The practice shows that in the situation of small camera vibration and successive illumination change, this method can quickly and accurately detect abnormity.
Aimed at the characteristic that high accuracy contour point segmentation is necessary for the abnormity detection method of alignment matching using contour information, this paper firstly compared common edge detection algorithm, and proposed the edge extraction method using canny operator to overcome the problem that traditional edge detection operator is easy to be influenced by noise and the problem that the contour is too thick. And then boundary tracing is used for constructing target contour and calculating chain code entropy, chain code spatial distribution entropy and contour moment. Finally, coarse matching based on global feature similarity is used for finding all areas in the image that contain the detection object, and then fine matching based on contour alignment is used for carrying out abnormity decision to precisely locate abnormity in the contour.
Aimed at the protection demand of injection mold, this paper realized the template-based abnormity detection system. The practice shows that abnormity detection algorithms proposed by this paper can guarantee real-time and accuracy abnormity detection and achieve the purpose of the study by phases.
针对单一的异常检测算法无法普遍适用于各种应用环境和不同特征检测对象的问题,提出采用工厂策略模式对系统的异常检测算法模块进行设计,并实现了利用灰度信息配准匹配的异常检测和利用轮廓信息对准匹配两种适用于不同应用场合的异常检测方法。通过工厂策略模式和相应的配置文件,在应用环境或者检测对象的特征发生变化时,客户可以动态创建、配置和加载符合当前异常检测需求的算法,确保在当前应用中,异常检测模块能在快速、稳定、准确之间保持很好的平衡。
针对利用灰度信息模板匹配的异常检测方法容易受到摄像机抖动和环境光照变化影响的问题,设计了一种具备容错能力的分块投影匹配法,实现了摄像机抖动的图像纠正；接着在介绍了利用高斯滤波器和多项式拟合消除光照变化方法的基础上,提出了实时性能更好的Wallis变换法来消除光照变化的影响；最后基于加权多区域差分矩阵进行异常决策。实践证明,在摄像机抖动量不大,光照连续变化的情况下,该方法能实现快速、准确地检测异常。
针对利用轮廓信息对准匹配的异常检测方法对轮廓点分割的准确度要求很高的特点,首先对比了常用的边缘检测算法,提出采用Canny算子来准确提取图像的边缘,克服了传统边缘检测算子易受噪声干扰和粗轮廓的问题。接着基于边界追踪构建目标轮廓,同时计算轮廓的链码熵、链码空间分布熵和轮廓矩。最后先基于全局特征相似度的粗匹配在待检测图像中找到包含待检测对象的所有区域,再基于轮廓对准的细匹配进行异常判断,并精确地定位轮廓上异常的具体位置。
针对注塑模具的保护需求,实现了基于模板的异常检测系统。实践证明,本文提出的异常检测算法能够保证检测的实时性和准确性,阶段性地达到了研究的目的。
With the demand for abnormity detection increased day by day in industrial and military fields,high-performance and high reliability image processing algorithms become more mature, which promotes machine vision technology widely used in abnormity detection.Aimed at the actual demand and a number of issues needed to be addressed, this paper carried out the research, designed and implemented a template-based abnormity detection system.
Aimed at the problem that a single abnormity detection algorithm can't be universally suitable for various application environments and detection objects of different characteristics, we proposed the plant strategy model to design the abnormity detection module of the system and realized two kinds of abnormity detection methods:registration matching using gray information and alignment matching using contour information, which are suitable for different application situation.Through the plant strategy model and some corresponding configuration files, whether application environment or the characteristic of the detection object changes,the client can dynamically create,configure,and load the algorithm meeting the current demand of abnormity detection to ensure that the abnormity detection module can get a good balance among rapidity, stability and accuracy in the current application.
Aimed at the problem that the abnormity detection method of template matching using gray information is easy to be influenced by camera vibration and illumination change, this paper firstly designed a fault-tolerant block projection matching method to realize the image correction of camera vibration, and then proposed the Wallis transformation method to eliminate illumination change, which is more real-time than the mothed using Gaussian filter and polynomial fitting introduced before. Finally, carrying out abnormity decision based on weighted multi-areas difference matrix.The practice shows that in the situation of small camera vibration and successive illumination change, this method can quickly and accurately detect abnormity.
Aimed at the characteristic that high accuracy contour point segmentation is necessary for the abnormity detection method of alignment matching using contour information, this paper firstly compared common edge detection algorithm, and proposed the edge extraction method using canny operator to overcome the problem that traditional edge detection operator is easy to be influenced by noise and the problem that the contour is too thick. And then boundary tracing is used for constructing target contour and calculating chain code entropy, chain code spatial distribution entropy and contour moment. Finally, coarse matching based on global feature similarity is used for finding all areas in the image that contain the detection object, and then fine matching based on contour alignment is used for carrying out abnormity decision to precisely locate abnormity in the contour.
Aimed at the protection demand of injection mold, this paper realized the template-based abnormity detection system. The practice shows that abnormity detection algorithms proposed by this paper can guarantee real-time and accuracy abnormity detection and achieve the purpose of the study by phases.
引文
[1]郭安哲,马莉.基于模板配准的零件轮廓缺损检测[J].机电工程技术,2008,37(12)：54～56
[2]石绘,余文勇.基于多目视觉的高速印刷质量在线检测系统[J].武汉理工大学学报,2007,29(6)：65～68
[3]周兵,杜润秋,李波.家庭安全监控的实时异常检测与分类算法[J].北京航空航天大学学报,2003,29(9)：825～828
[4]周记林,马莉.基于机器视觉的珍珠图像采集及缺陷检测[J].计算机工程与应用,2008,44(3)：210～213
[5]张永军编著.基于序列图像的视觉检测理论与方法[M].武汉：武汉大学出版社,2008
[6]Meylani R, Ertuzun A,Ercil A.Texture Defect Detection Using the Adaptive Two-Dimensional Lattice Filter[J].Image Processing,1996,3:165～168
[7]Chi-ho Chan,Grantham Pang.Fabric Defect Detection by Fourier Analysis[J].IEEE Transactions on Industry Applications,2000,36(5):1267～1276
[8]Luo.Automatic Color Printing Inspection by Image Processing[J].Journal of Materials Technology,2003(139):373～378
[9]Zeljko Hocenski,Suzana Vasilic,Verica Hocenski.Improved Canny Edge Detector in Ceramic Tiles Defect Detection[J].Pattern Analysis and Machine Intelligence,2006,9(13):3328～3331
[10]Jong Pilyun,Young Supark,Boyeul Seo,etal.Development of Real-time Defect Detection Algorithm for Hign-speed Steel Bar in Coil[J].SICE-ICASE International Joint Conference,2006,18(21):2495～2498
[11]Xiang Huaxie,Majid Mirmehdi.Texture Exemplars for Defect Detection on Random Textured Surfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(8):1454～1464
[12]Sung Wookyun,Nam Woongkong,Gyumin Lee,etal.Development of Defect Detection Algorithm in Cold Rolling.International Conference on Control, Automation and Systems[J],2008,14(17):1729～1733
[13]Dr R S Sabeenian,M E Paramasivam.Defect Detection and Identification in Textile Fabrics Using Multi Resolution Combined Statistical and Spatial Frequency Method[J].IEEE 2nd International Advance Computing Conference, 2010,10(22):162～166
[14]贡玉南,华建兴,黄秀宝.基于匹配Gabor滤波器的规则纹理缺陷检测方法[J].中国图像图形学报,2001,6(7)：624～628
[15]潘洪平,董申.钢球表面质量评价系统用展开轮的理论研究[J].轴承,2001,23(12)：28～31
[16]刘雪芳.一种新的基于图像区域特征的生物芯片边缘检测方法[J].电了科技,2003,5(21)：35～38
[17]乐晓峰,赵敏,栾宝剑,等.计算机视觉技术在发动机缺陷检测系统中的应用[J].计算机测量与控制,2005,13(6)：516～518
[18]Henry Y T Ngan,Grantham K H Pang,Nelson H C Yung.Patterned Fabric Defect Detection Using a Motif-based Approach[J].Pattern Recognition,2008,41(6): 33～36
[19]Zhu Zhengwei,Guo Yuying.On Image Registration and Defect Detection Techniques in the Print Quality Detection of Cigarette Wrapper[J].Proceedings of the 27th Chinese Control Conference,2008,16(18):34～38
[20]Lin Jie,Luo Siwei,Li Qingyong,etal.Real-time Rail Head Surface Defect Detection:a Geometrical Approach[J].IEEE International Symposium on Industrial Electronics,2009,5(8):769～774
[21]周彩霞,匡纲要.基于差影法粗分割与多模板匹配的人脸检测[J].计算机工程与应用,2004,25(10)：1648～1652
[22]陈廉清,崔治,王龙山.基于差影和模板匹配的微小轴承表面缺陷检测[J].中国机械工程,2006,17(10)：1019～1022
[23]Morovic J,Shaw J,Pei Lisun.A Fast Non-Iterative and Exact Histogram Matching Algorithm[J].Pattern Recognition Letters,2002,23(1-3):127～135
[24]Jun Weihsieh,Hong Yuanmark,Kuo Chinfan,etal.Image Registration Using a New Edge-based Approach[J].Computer Vision and Image Understanding,1997, 67(2):112～130
[25]葛永新,杨丹,张小洪.基于边缘特征点对对齐度的图像配准方法[J].中国图像图形学报,2007,12(7)：1291～1295
[26]Li Winston,Leung H A.Maximum Likelihood Approach for Image Registration Using Control Point and Intensity[J].IEEE Transactions on Image Processing, 2004,13(8):1115～1127
[27]Fitch A J,Kadyrov A,Chrismas W J,etc.Fast Robust Correlation[J].IEEE Transaction on Processing,2005,14(8):1063～1073
[28]Chen Li,Yap Kimhui.A Fuzzy K-Nearest-Neighbor Algorithm to Blind Image Deconvolution[J].Proceeding of the IEEE Intermational Conference on Systems, Man and Cybernetics,2003,3:2049～2054
[29]Lam K P.Image Coding/Reconstruction and Matching Using a Parallel Distributed Hebbian Architecture[J].Proceeding of the 2002 IEEE International Joint Conference on Neural Networks,Piscataway,NJ,USA:IEEE,2002, 974～979
[30]许亚军,陈小惠.一种基于遗传算法和小波分解的刚性图像配准方法[J].江苏科技大学学报,2008,22(2)：75～78
[31]李伟,杨绍清.基于改进自适应遗传算法的图像配准方法[J].激光与红外,2009,39(9)：991～994
[32]唐斌兵,陈团强,王正明.基于小波变换的图像配准方法[J].计算机应用,2007,27(9)：2103～2105
[33]何仁芳,王乘,杨文兵.基于混沌遗传算法的图像匹配[J].红外与激光工程,2003,32(1)：13～16
[34]宋晓宇,刘云鹏,王永会.基于PBIL的快速图像匹配方法的研究[J].计算机工程与应用,2005,25(7)：43～45
[35]孔金生,张小凤,王璇.基于轮廓特征的模板匹配方法及其应用[J].计算机工程与应用,2008,44(22)：201～203
[36]胡涛,郭宝平,郭轩,等.基于轮廓特征的图像配准[J].光电工程,2009,36(11)：118～127
[37]李强,张钹.一种基于图像灰度的快速匹配算法[J].软件学报,2006,17(2)：216～222
[38]Gang Hong,Yun Zhang.Combination of Feature-based and Area-based Image Registration Technique for High Resolution Remote Sensing Image[J].Geoscience and Remote Sensing Symposium,2007,7(2):377～380
[39]罗磊,殷建平,张国敏,等.基于加权相邻关系的形状轮廓点匹配[J].计算机工程与科学,2008,30(11)：34～37
[40]王小鹏,阎国梁,裴建刚,等.由形态学边缘模式匹配实现数字稳像[J].光学精密工程,2009,17(3)：684～689
[41]胡涛,郭宝平,郭轩,等.基于轮廓特征的图像配准[J].光电工程,2009,36(11)：118～122
[42]Ranjan Jana,Chhanda Ray.Image Registration Using Object Shape's Chain Code[J].Image and Signal Processing,2009,22(13):1～5
[43]Chang Hungchang,Lai Shanghong,Lu K R.A Robust Real-Time Video Stabilization Algorithm[J],J.Vis.Common.Image R,2006,25(17):659～673
[44]袁修孝,宋妍.基于边缘特征匹配的遥感影像变化检测预处理方法[J].武汉大学学报,2007,32(5)：381～384
[45]罗军,董鸿雁,沈振康.基于位平面匹配和卡尔曼滤波的视频稳像[J].红外与激光工程,2008,37(2)：304～307
[46]Wang Xiaoyong,Li Qi,Xu Zhihai,etal.Real-time Digital Image Stabilization System based on Gray Projection Algorithm[J].Acta Photonica Sinica,2006, 35(8):1268～1271
[47]Sun Hui.Fast Gray Projection Algorithm and its Application to Electronic Image Stabilization[J].Optics and Precision Engineering,2007,15(3):412～416
[48]景麟,王宏远,周娅.基于MSE匹配法则的全零块判决算法[J].华中科技大学学报,2008,36(5)：16～19
[49]贺玉文,赵黎,钟玉琢,等.快速鲁棒的全局运动估计算法[J].软件学报,2001,12(8)：1220～1228
[50]Gang Chen,Tai Hu,Xiao Yongguo,etal.A Fast Region-based Image Segmentation Based on Least Square Method[J].Proceeding of the 2009 IEEE International Conference on Systems,Man,and Cybernetics San Antonio,TX, USA-October 2009
[51]Guo Pingyan,Qing Pan,Yang Kang.Research on A New Gaussian Self-Adaptive Smoothing Algorithm in Image Processing[J].VLSI Design and Video Technology,2005,30(28):348～352
[52]Li Changming,Xu Guosheng.Sub-pixel Edge Detection Based on Polynomial Fitting for Line-Matrix CCD Image[J].Information and Computing Science, 2009,11(10):262～264
[53]Annupan R,Stanislav S.A Filter Bank Method to Construct Rotationally Invariant Moments for Pattern Recognition[J].Pattern Recognition Letters 28,2007,36(12): 1492～1500
[54]孙君顶.基于链码分布特征及相关性的轮廓描述与检索[J].光电子.激光,2008,19(8)：1112～1115
[55]Liu Y S,Yang L H,Sun Q.Contour-based Moment Invariants and Their Application to the Recognition of Object Shapes[J].Journal of Image and Graphics,2004,9(3):308～313
[56]Pradabpet C,Ravinu N,Chivapreecha S,etal.An Efficient Filter Structure for Multiplierless Sobel Edge Detection[J].Innovative Technologies in Intelligent Systems and Industrial Applications,2009,14(8):40～44
[57]Rosenfeld,Azriel.The Max Roberts Operator is a Hueckel-Type Edge Detector[J].Pattern Analysis and Machine Intelligence,1981,3(1):101～103
[58]Cong Khapham,Yamano K.An Edge Extraction Method for Color Image Using Multiple-Valued LOG Filter and Color Space[J].Computer and Information Science,2007,54(10):658～662
[59]Liu Xiang,Xia Jinsong,Yang Donghe.Cocoon Edge Detection based on Self-Adaptive Canny Operator[J].Computer Science and Software Engineering, 2008,6(1):7～10
[60]于洋,刘二莉,周铁涛,等.边界追踪及Freeman码在定量金相中的应用[J].北京航空航天大学学报,2004,30(8)：767～770
[2]石绘,余文勇.基于多目视觉的高速印刷质量在线检测系统[J].武汉理工大学学报,2007,29(6)：65～68
[3]周兵,杜润秋,李波.家庭安全监控的实时异常检测与分类算法[J].北京航空航天大学学报,2003,29(9)：825～828
[4]周记林,马莉.基于机器视觉的珍珠图像采集及缺陷检测[J].计算机工程与应用,2008,44(3)：210～213
[5]张永军编著.基于序列图像的视觉检测理论与方法[M].武汉：武汉大学出版社,2008
[6]Meylani R, Ertuzun A,Ercil A.Texture Defect Detection Using the Adaptive Two-Dimensional Lattice Filter[J].Image Processing,1996,3:165～168
[7]Chi-ho Chan,Grantham Pang.Fabric Defect Detection by Fourier Analysis[J].IEEE Transactions on Industry Applications,2000,36(5):1267～1276
[8]Luo.Automatic Color Printing Inspection by Image Processing[J].Journal of Materials Technology,2003(139):373～378
[9]Zeljko Hocenski,Suzana Vasilic,Verica Hocenski.Improved Canny Edge Detector in Ceramic Tiles Defect Detection[J].Pattern Analysis and Machine Intelligence,2006,9(13):3328～3331
[10]Jong Pilyun,Young Supark,Boyeul Seo,etal.Development of Real-time Defect Detection Algorithm for Hign-speed Steel Bar in Coil[J].SICE-ICASE International Joint Conference,2006,18(21):2495～2498
[11]Xiang Huaxie,Majid Mirmehdi.Texture Exemplars for Defect Detection on Random Textured Surfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(8):1454～1464
[12]Sung Wookyun,Nam Woongkong,Gyumin Lee,etal.Development of Defect Detection Algorithm in Cold Rolling.International Conference on Control, Automation and Systems[J],2008,14(17):1729～1733
[13]Dr R S Sabeenian,M E Paramasivam.Defect Detection and Identification in Textile Fabrics Using Multi Resolution Combined Statistical and Spatial Frequency Method[J].IEEE 2nd International Advance Computing Conference, 2010,10(22):162～166
[14]贡玉南,华建兴,黄秀宝.基于匹配Gabor滤波器的规则纹理缺陷检测方法[J].中国图像图形学报,2001,6(7)：624～628
[15]潘洪平,董申.钢球表面质量评价系统用展开轮的理论研究[J].轴承,2001,23(12)：28～31
[16]刘雪芳.一种新的基于图像区域特征的生物芯片边缘检测方法[J].电了科技,2003,5(21)：35～38
[17]乐晓峰,赵敏,栾宝剑,等.计算机视觉技术在发动机缺陷检测系统中的应用[J].计算机测量与控制,2005,13(6)：516～518
[18]Henry Y T Ngan,Grantham K H Pang,Nelson H C Yung.Patterned Fabric Defect Detection Using a Motif-based Approach[J].Pattern Recognition,2008,41(6): 33～36
[19]Zhu Zhengwei,Guo Yuying.On Image Registration and Defect Detection Techniques in the Print Quality Detection of Cigarette Wrapper[J].Proceedings of the 27th Chinese Control Conference,2008,16(18):34～38
[20]Lin Jie,Luo Siwei,Li Qingyong,etal.Real-time Rail Head Surface Defect Detection:a Geometrical Approach[J].IEEE International Symposium on Industrial Electronics,2009,5(8):769～774
[21]周彩霞,匡纲要.基于差影法粗分割与多模板匹配的人脸检测[J].计算机工程与应用,2004,25(10)：1648～1652
[22]陈廉清,崔治,王龙山.基于差影和模板匹配的微小轴承表面缺陷检测[J].中国机械工程,2006,17(10)：1019～1022
[23]Morovic J,Shaw J,Pei Lisun.A Fast Non-Iterative and Exact Histogram Matching Algorithm[J].Pattern Recognition Letters,2002,23(1-3):127～135
[24]Jun Weihsieh,Hong Yuanmark,Kuo Chinfan,etal.Image Registration Using a New Edge-based Approach[J].Computer Vision and Image Understanding,1997, 67(2):112～130
[25]葛永新,杨丹,张小洪.基于边缘特征点对对齐度的图像配准方法[J].中国图像图形学报,2007,12(7)：1291～1295
[26]Li Winston,Leung H A.Maximum Likelihood Approach for Image Registration Using Control Point and Intensity[J].IEEE Transactions on Image Processing, 2004,13(8):1115～1127
[27]Fitch A J,Kadyrov A,Chrismas W J,etc.Fast Robust Correlation[J].IEEE Transaction on Processing,2005,14(8):1063～1073
[28]Chen Li,Yap Kimhui.A Fuzzy K-Nearest-Neighbor Algorithm to Blind Image Deconvolution[J].Proceeding of the IEEE Intermational Conference on Systems, Man and Cybernetics,2003,3:2049～2054
[29]Lam K P.Image Coding/Reconstruction and Matching Using a Parallel Distributed Hebbian Architecture[J].Proceeding of the 2002 IEEE International Joint Conference on Neural Networks,Piscataway,NJ,USA:IEEE,2002, 974～979
[30]许亚军,陈小惠.一种基于遗传算法和小波分解的刚性图像配准方法[J].江苏科技大学学报,2008,22(2)：75～78
[31]李伟,杨绍清.基于改进自适应遗传算法的图像配准方法[J].激光与红外,2009,39(9)：991～994
[32]唐斌兵,陈团强,王正明.基于小波变换的图像配准方法[J].计算机应用,2007,27(9)：2103～2105
[33]何仁芳,王乘,杨文兵.基于混沌遗传算法的图像匹配[J].红外与激光工程,2003,32(1)：13～16
[34]宋晓宇,刘云鹏,王永会.基于PBIL的快速图像匹配方法的研究[J].计算机工程与应用,2005,25(7)：43～45
[35]孔金生,张小凤,王璇.基于轮廓特征的模板匹配方法及其应用[J].计算机工程与应用,2008,44(22)：201～203
[36]胡涛,郭宝平,郭轩,等.基于轮廓特征的图像配准[J].光电工程,2009,36(11)：118～127
[37]李强,张钹.一种基于图像灰度的快速匹配算法[J].软件学报,2006,17(2)：216～222
[38]Gang Hong,Yun Zhang.Combination of Feature-based and Area-based Image Registration Technique for High Resolution Remote Sensing Image[J].Geoscience and Remote Sensing Symposium,2007,7(2):377～380
[39]罗磊,殷建平,张国敏,等.基于加权相邻关系的形状轮廓点匹配[J].计算机工程与科学,2008,30(11)：34～37
[40]王小鹏,阎国梁,裴建刚,等.由形态学边缘模式匹配实现数字稳像[J].光学精密工程,2009,17(3)：684～689
[41]胡涛,郭宝平,郭轩,等.基于轮廓特征的图像配准[J].光电工程,2009,36(11)：118～122
[42]Ranjan Jana,Chhanda Ray.Image Registration Using Object Shape's Chain Code[J].Image and Signal Processing,2009,22(13):1～5
[43]Chang Hungchang,Lai Shanghong,Lu K R.A Robust Real-Time Video Stabilization Algorithm[J],J.Vis.Common.Image R,2006,25(17):659～673
[44]袁修孝,宋妍.基于边缘特征匹配的遥感影像变化检测预处理方法[J].武汉大学学报,2007,32(5)：381～384
[45]罗军,董鸿雁,沈振康.基于位平面匹配和卡尔曼滤波的视频稳像[J].红外与激光工程,2008,37(2)：304～307
[46]Wang Xiaoyong,Li Qi,Xu Zhihai,etal.Real-time Digital Image Stabilization System based on Gray Projection Algorithm[J].Acta Photonica Sinica,2006, 35(8):1268～1271
[47]Sun Hui.Fast Gray Projection Algorithm and its Application to Electronic Image Stabilization[J].Optics and Precision Engineering,2007,15(3):412～416
[48]景麟,王宏远,周娅.基于MSE匹配法则的全零块判决算法[J].华中科技大学学报,2008,36(5)：16～19
[49]贺玉文,赵黎,钟玉琢,等.快速鲁棒的全局运动估计算法[J].软件学报,2001,12(8)：1220～1228
[50]Gang Chen,Tai Hu,Xiao Yongguo,etal.A Fast Region-based Image Segmentation Based on Least Square Method[J].Proceeding of the 2009 IEEE International Conference on Systems,Man,and Cybernetics San Antonio,TX, USA-October 2009
[51]Guo Pingyan,Qing Pan,Yang Kang.Research on A New Gaussian Self-Adaptive Smoothing Algorithm in Image Processing[J].VLSI Design and Video Technology,2005,30(28):348～352
[52]Li Changming,Xu Guosheng.Sub-pixel Edge Detection Based on Polynomial Fitting for Line-Matrix CCD Image[J].Information and Computing Science, 2009,11(10):262～264
[53]Annupan R,Stanislav S.A Filter Bank Method to Construct Rotationally Invariant Moments for Pattern Recognition[J].Pattern Recognition Letters 28,2007,36(12): 1492～1500
[54]孙君顶.基于链码分布特征及相关性的轮廓描述与检索[J].光电子.激光,2008,19(8)：1112～1115
[55]Liu Y S,Yang L H,Sun Q.Contour-based Moment Invariants and Their Application to the Recognition of Object Shapes[J].Journal of Image and Graphics,2004,9(3):308～313
[56]Pradabpet C,Ravinu N,Chivapreecha S,etal.An Efficient Filter Structure for Multiplierless Sobel Edge Detection[J].Innovative Technologies in Intelligent Systems and Industrial Applications,2009,14(8):40～44
[57]Rosenfeld,Azriel.The Max Roberts Operator is a Hueckel-Type Edge Detector[J].Pattern Analysis and Machine Intelligence,1981,3(1):101～103
[58]Cong Khapham,Yamano K.An Edge Extraction Method for Color Image Using Multiple-Valued LOG Filter and Color Space[J].Computer and Information Science,2007,54(10):658～662
[59]Liu Xiang,Xia Jinsong,Yang Donghe.Cocoon Edge Detection based on Self-Adaptive Canny Operator[J].Computer Science and Software Engineering, 2008,6(1):7～10
[60]于洋,刘二莉,周铁涛,等.边界追踪及Freeman码在定量金相中的应用[J].北京航空航天大学学报,2004,30(8)：767～770