数字图像拼接与配准技术的研究
|
摘要
数字图像拼接与配准技术作为图像处理的关键环节,正成为图像处理领域研究的热点。其应用领域相当的广泛,如人脸识别、视频监控图像分析、银行印章识别、医学诊断以及全景图生成等等方面有着非常普遍应用,在科研领域内得到了极大的重视和发展。
图像拼接与配准技术经过多年的发展已经积累了大量的研究成果,特别是配准技术,作为拼接的基础,相关技术也达到了较高的水平。图像拼接的方法主要有基于区域和基于特征,基于特征的拼接方法,主要是找图像之间的对应特征点,可以是点、边、曲率等特征,其优点是计算量比较小,但不够精确;基于区域的方法直接对每个像素进行比较,只要时间足够长,则可以拼接的足够精确,由于是对整个图像的像素操作,因此计算量特别大。配准技术主要是分为基于灰度、基于特征以及基于决策树这几种情况。研究最多的是基于灰度的图像配准,这种方法直接利用图像的灰度信息进行配准,通过像素对其间某种相似性度量的全局最优化实现配准,这种配准方法配准的速度比较低,对灰度信息变化非常敏感,没有充分利用灰度统计特性,对每一点的灰度信息依赖较大;基于特征的图像配准方法的研究也逐渐增多,这种方法先提取图像的特征,然后利用图像的特征进行配准;基于决策树的图像配准需要先建立自动表决专家系统模型,然后根据一定的决策规则进行配准。对这种方法的研究,目前没有突破性进展。
本文主要是讲述对于图像拼接以及配准技术方面的改进。对于图像拼接技术,如何比较准确快速地定位好衔接重叠的区域是体现其算法是否高效的一个重要指标。因为在图像拼接过程中,比较大的一部分时间主要是消耗在寻找相匹配的区域上面。针对基于区域拼接技术在定位重叠区域耗时长的特点,引入了利用多线程技术以及改进的SSDA算法,来提高定位的效率。通过与一些传统算法的比较,速度方面有很大的提高。本文在配准的改进方面,则根据图像迹算法配准率高,以及分形维配准不需要提出图像的边缘、轮廓、纹理等特征,对于图像边缘、轮廓、纹理信息不丰富的图像也可以进行配准的特点,提出了一种提高配准率的方法,就是在传统的分形维配准技术的基础上加入了图像迹的技术,另外还引入了噪声处理方法,在配准时间也有很大改进。
The development of computer graphics, is producing more and more far-reaching impact. Digital image stitching and registration technology as a key link in image processing has become a hot research field of image processing. Digital image registration fairly wide range of applications, such as face recognition, video surveillance image analysis, bank seal identification, medical diagnosis and panorama picture formation etc., has a very popular application, so this area of scientific research has been greatly attention and development.
Image stitching and registration technology have accumulated a large number of research results over the years, especially registration technology, as the basis for stitching, related technology have achieved a higher level. The methods of image stitching are mainly region-based and feature-based, Feature-based stitching method, is mainly to find the corresponding feature points between the images, which can be points, edges, curvature and other characteristics,it’s quantity of calculation is small, but is not pricise enough. Region-based approach is to compare each pixel directly, as long as time is long enough, you can splice a sufficient precision. Because it is the entire image pixel operations, so computation is particularly large. Registration techniques are mainly divided into basing on the grayscale, feature and decision tree. The most studied is based on gray-scale image registration, this method directly use the gray-scale image registration information, through the pixels on the similarity measure during a global optimization to achieve registration. This registration method is relatively low rate of registration of changes in gray level information is very sensitive to not make full use of gray-scale statistical properties of each point of larger gray-scale reliance on the information. Feature-based image registration methods of study gradually increased, this method first extract the image features, and then use the characteristics of the image registration. Image registration based on the decision-making need to set up an automated expert system model of the vote, and then the decision-making rules based on certain alignment. The study of this approach, there is no breakthrough.
This paper is mainly about the technology improvements of image stitching and registration. For image stitching techniques, how to locate a good convergence of overlapping area more accurately and quickly is the embodiment of their algorithm as well as an important indicator of efficiency. Because in the image stitching process, the relatively large part of the time is mainly consumed in looking for the match area. For the time-consuming characteristics in positioning the region-based stitching overlap proposed the use of multi-threading technology, and improved SSDA algorithm to improve the targeting efficiency. Compared with some traditional algorithms, the speed has greatly improved. The improvements in the registration, according to the high registration rate of image trace, as well as the fractal dimension of the image registration do not need to make the edge, contour, texture and other features, for the image which edge, contour, texture information is not rich can also be carried out, this paper put forward a method to improve registration rates in the traditional registration technology on the basis of fractal dimension by adding the image trace technology, furthermore the introduction of noise processing methods, registration time also improved significantly.
图像拼接与配准技术经过多年的发展已经积累了大量的研究成果,特别是配准技术,作为拼接的基础,相关技术也达到了较高的水平。图像拼接的方法主要有基于区域和基于特征,基于特征的拼接方法,主要是找图像之间的对应特征点,可以是点、边、曲率等特征,其优点是计算量比较小,但不够精确;基于区域的方法直接对每个像素进行比较,只要时间足够长,则可以拼接的足够精确,由于是对整个图像的像素操作,因此计算量特别大。配准技术主要是分为基于灰度、基于特征以及基于决策树这几种情况。研究最多的是基于灰度的图像配准,这种方法直接利用图像的灰度信息进行配准,通过像素对其间某种相似性度量的全局最优化实现配准,这种配准方法配准的速度比较低,对灰度信息变化非常敏感,没有充分利用灰度统计特性,对每一点的灰度信息依赖较大;基于特征的图像配准方法的研究也逐渐增多,这种方法先提取图像的特征,然后利用图像的特征进行配准;基于决策树的图像配准需要先建立自动表决专家系统模型,然后根据一定的决策规则进行配准。对这种方法的研究,目前没有突破性进展。
本文主要是讲述对于图像拼接以及配准技术方面的改进。对于图像拼接技术,如何比较准确快速地定位好衔接重叠的区域是体现其算法是否高效的一个重要指标。因为在图像拼接过程中,比较大的一部分时间主要是消耗在寻找相匹配的区域上面。针对基于区域拼接技术在定位重叠区域耗时长的特点,引入了利用多线程技术以及改进的SSDA算法,来提高定位的效率。通过与一些传统算法的比较,速度方面有很大的提高。本文在配准的改进方面,则根据图像迹算法配准率高,以及分形维配准不需要提出图像的边缘、轮廓、纹理等特征,对于图像边缘、轮廓、纹理信息不丰富的图像也可以进行配准的特点,提出了一种提高配准率的方法,就是在传统的分形维配准技术的基础上加入了图像迹的技术,另外还引入了噪声处理方法,在配准时间也有很大改进。
The development of computer graphics, is producing more and more far-reaching impact. Digital image stitching and registration technology as a key link in image processing has become a hot research field of image processing. Digital image registration fairly wide range of applications, such as face recognition, video surveillance image analysis, bank seal identification, medical diagnosis and panorama picture formation etc., has a very popular application, so this area of scientific research has been greatly attention and development.
Image stitching and registration technology have accumulated a large number of research results over the years, especially registration technology, as the basis for stitching, related technology have achieved a higher level. The methods of image stitching are mainly region-based and feature-based, Feature-based stitching method, is mainly to find the corresponding feature points between the images, which can be points, edges, curvature and other characteristics,it’s quantity of calculation is small, but is not pricise enough. Region-based approach is to compare each pixel directly, as long as time is long enough, you can splice a sufficient precision. Because it is the entire image pixel operations, so computation is particularly large. Registration techniques are mainly divided into basing on the grayscale, feature and decision tree. The most studied is based on gray-scale image registration, this method directly use the gray-scale image registration information, through the pixels on the similarity measure during a global optimization to achieve registration. This registration method is relatively low rate of registration of changes in gray level information is very sensitive to not make full use of gray-scale statistical properties of each point of larger gray-scale reliance on the information. Feature-based image registration methods of study gradually increased, this method first extract the image features, and then use the characteristics of the image registration. Image registration based on the decision-making need to set up an automated expert system model of the vote, and then the decision-making rules based on certain alignment. The study of this approach, there is no breakthrough.
This paper is mainly about the technology improvements of image stitching and registration. For image stitching techniques, how to locate a good convergence of overlapping area more accurately and quickly is the embodiment of their algorithm as well as an important indicator of efficiency. Because in the image stitching process, the relatively large part of the time is mainly consumed in looking for the match area. For the time-consuming characteristics in positioning the region-based stitching overlap proposed the use of multi-threading technology, and improved SSDA algorithm to improve the targeting efficiency. Compared with some traditional algorithms, the speed has greatly improved. The improvements in the registration, according to the high registration rate of image trace, as well as the fractal dimension of the image registration do not need to make the edge, contour, texture and other features, for the image which edge, contour, texture information is not rich can also be carried out, this paper put forward a method to improve registration rates in the traditional registration technology on the basis of fractal dimension by adding the image trace technology, furthermore the introduction of noise processing methods, registration time also improved significantly.
引文
[1] Thevenaz P,Optimization of Mutual Information for Multiresolution Image Registration[J],IEEE Trans.on Image Processing,2000、12,2083～2099.
[2]王岩松,阮秋琦,一种基于互相关的图像定位匹配算法研究及应用[J],北方交通大学学报,2002、4,20～24.
[3] INGLADA J,Adragna F,Automatic multi-sensor image registration by edge matching using genetic algorithms[A],IEEE International Conference on Geoscience and Remote Sensing Symposium[C],Sydney,IEEE,Australia,2001,5,2313～2315.
[4] OWN H S,HASSANIEN A E,Multiresolution image registration algorithm in wavelet transform domain[A] IEEE 14th International Conference on Digital Signal Processing[C],Santorini,IEEE,Greece,2002,2,889～892.
[5]刘卫光,周利华,基于小波概率估计的图像融合方法研究[J],光子学报,2004、1,101～104.
[6] BrownL.G..A survey of image registration techniques. ACM Computer, Surveys, Dec.1992, Vol.24,No.4,p325-376.
[7]曾文锋等,基于小波变换的红外图像配准方法[J],激光与红外,2003、8,288～289.
[8] Denney B S,de Figueiredo R J P,Optimal point target detection using adaptive auto regressive background prediction[J],Signal and Data Processing of Small Target,SPIE.2000、4048,46～57.
[9]李红,郑成勇,高景丽,基于小波多尺度图像配准的运动小目标检测[J],红外与激光工程,2003、6,267～270.
[10]孙广富,陈华明,卢焕章,一种低信噪比条件下的红外图像序列小目标实时检测算法[J],2003、12,508～511.
[11]舒付祥,孙继银,一种基于灰度特征的图象匹配算法设计与研究[J],计算机工程与应用,2002、9,101～102.
[12]陈宁江,李介谷,用归一化灰度组合法进行图像匹配[J],红外与激光工程,2000、10,5～9.
[13] Barnea D I,Silverman H F,A class of algorithms for fast digital image registration[J],IEEE Trans.on Comput,1972,C-21,2,179-186.
[14]李震,范湘涛,施建成,基于分窗口相关的遥感图象配准方法[J],中国图象图形学报,2001,6,2,129～132.
[15]韦燕凤,谢启伟,彭思龙,一种基于网格结构图象的目标匹配定位方法[J],中国图象图形学报,2002,7,7,658～662.
[16] Bourret P,Cabon B,A neural approach for satellite image registration and pairing segmented areas[J] SPIE,1995、25794,22.
[17]谢启炜,王洪剑,马超,小波变换目标快速匹配[J],湖北大学学报,2002、3,11～13.
[18]吴均,朱重光,赵忠明,一种基于小波分析的旋转不变图像快速匹配方法[J],遥感学报,2002、9,339～342.
[19]张国柱,王程,王润生,基于小波变换的多分辨率图像匹配方法[J],计算机工程与应用,2001、13,113～114.
[20] Hsieh Jun wei,Image registration using a new edge based approach[J],Computer Vision and Image understanding,1997,67,2,112-130.
[21]彭小明,丁明跃,周成平,一种准自动多传感器图像配准方法[J],华中科技大学学报,2003、4,85～87.
[22]陈灵娜,盛利元,陈俊熹,CT图像配准算法的研究与实现[J],医疗设备信息,2004,19,8:4～5.
[23] Pluim J P W,Maintz J B N,Viergver M A,Image registration by maximization of combined mutual information and gradient information[J],IEEE Transactions on Medical Imaging,2000,19,8,809～814.
[24] Roche A,Pennec X,Malandain G,etal,Rigid registration of 3-Dultrasound with MR images:a new approach combining intensity and gradient information[J],IEEE Transaction on Medical Imaging,2001,20,10,1038～1049.
[25]王强,彭嘉雄,基于轮廓的多源图像的配准[J],计算机与数字工程,2002、5,1～4.
[26]董开坤,胡铭曾,一个新颖的基于熵特征的并行图像匹配算法[J],黑龙江工程学院学报,2001,15,1,40～43.
[27] Shung-Shing Lee,Shi-Jinn Horng,Horng-Ren Tsai,Entropy thresholding and its parallel algorithm on the reconfigurable array of processors with wider bus networks[J],IEEE Transactions on Image Processing,1999,8,9,1229～1242.
[28] Clark F Olson,Image registration by aligning entropies[A],Proceedings of 2001 IEEE Computer Society Conference[C],Kauai,IEEE,Hawaii,USA,2001,2,331～336.
[29]黄勇,王建国,黄顺吉,SAR图像匹配算法及实现[J],信号处理,2003,19,2,179～156.
[30]刘哲,郝重阳,刘晓翔,樊养余,多光谱图像与全色图像的像素级融合研究[J],数据采集与处理,2003,18,3,296～301.
[31]唐健,朱继红,孙增圻,基于智能优化策略的图像自动配准方法[J],清华大学学报(自然科学版),2004,44,9,1252～1255.
[32]刘斌,彭嘉雄,图像配准的小波分解方法[J],计算机辅助设计与图形学学报,2003,15,9,1070～1073.
[33]刘道海,孙作龙,黄樟灿,图像匹配问题的新算法[J],武汉理工大学学报,2002,2,25～27.
[34] Anuta P.E..Spatial registration of multispectral and multitemporal digital imagery using fast Fourier transformation techniques.IEEE Trans.on Geosci.Electron,Oct, 1970,Vol.GE.8,p355-368.
[35] Barnea D.I.,Silverman H.F..A class of algorithms for fast digital image registration.IEEE Trans.on Computers,1972,Vol.C-21,p179-186.
[36] W.K.Pratt著,高荣坤等译,数字图像处理学。科学出版社,1983.
[37] M.Svedlow,C.D.MacGillen,Paul E.Anuta.Image registration:Two new techniques for image matching.Proc 5th Joint Conf.On Artificial Intelligence.Cambridge.Mess.,p659-663.
[38] Henri Maitre,Yifeng Wu.A dynamic programming algorithm for elastic registration of distorted pictures based on autoregressive model.IEEE Trans.on acoustics,speech,and signal processing,1989,Vol.37,p288-298
[39] Jan Flussr.An adaptive method for image registration.Pattern Recognition,1992,Vol.25,p45-54.
[40]熊兴华,钱曾波,王任享。遗传算法与最小二乘法相结合的遥感图像子像素匹配。测绘学报,2001,2,30(1):54-59.
[41]郭海涛,刘智,张保明。基于遗传算法的快速影像匹配技术的研究。测绘学院学报。2001,9,18(S1):20-22.
[42]李智,张雅声。基于轮廓特征的图像配准。CCUA图像分会,1997.
[43]王小睿,吴信才。遥感多图像的自动配准技术。中国图形图像学报。1997(10).
[44]解凯,郭恒业,张田文.图像Mosaics技术综述[J].电子学报,2004,32(4):630-634.
[45] Lucas B D,Kanade T. An iterative image registration technique with an applicationin stereo- vision[C]//In:Seventh Conference on Artificial Intelligence(IJCAI-81).Vancouver:[s.n.],1981:674- 679
[46]钟力,胡晓峰.重叠图像拼接算法[J].中国图像图形学报,1998,3(5):367-370.
[47]陈果,左洪福.显微图像的一种快速拼接算法[J].仪器仪表学报,2003,24(4):343-347.
[48] Castro E D,Morandi C.Registration of Translated and Rotated Images Using Finite Fourier Transforms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,PAMI,1987,9(5):700-703.
[49] Anuta P E.Spatial Registration of Multispectral and Multitemporal Digital Images Using fast Fourier Transform Techniques[J].IEEE Trans Geo.Elec.,1970(8):353-368.
[50] Kuglin C D,Hines D C.The Phase Correlation Image Alignment Method[C]//In Proc of IEEE Int Conf.on Cybernetics and Society.New York:[s.n.],1975:163-165.
[51]许雷,张恒义,虞亚军,等.一种基于相位相关法及数学形态学方法的眼底血管图像自动拼接方法[J].生物医学工程杂志,1998,15(3):286-290.
[52] Li H,Manjunath B S,Mitra S K.A contour based approach to multisensor image registration[J].IEEE Trans Image Processing,1995(4):320-334.
[53]俞辉,侯在克,何旭莉,等.一种基于轮廓特征的图像拼接算法设计与实现[J].石油大学学报:自然科学版,2003,27(2):114-118.
[54]张静,胡志萍,刘志泰,等.基于轮廓相位相关的图像自动拼接[J].大连理工大学学报,2005,45(1):68-74.
[55] Harris C,Stephens M.A combined corner and edge detector[C]//InProc.Alvey Conf Vision.England:Manchester University Press,1988:189-192.
[56] Brown M,Lowe D G.Invariant Features From Interest Point Groups[C]//In British Machine Vision Conference.Cardiff,Wales:[s.n.],2002:656-665.
[57] Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of ComputerVision,2004,60(2):91-110.
[58] Burt P J,Adelson E H.The laplacian pyramid as a compact image code[J].IEEE Transaction on Communications,1983,com-31(4):532-540.
[59] Anuta P.E..Spatial registration of multispectral and multitemporal digital imagery using fast Fourier transform techniques.IEEE Trans.Geo Elec,1970(8):353-368.
[60] B.S.Reddy,B.N.Chatterji.An fft-based technique for translation,rotation,and scale-invariant image registration.IEEE Trans on Image Processing,1996,3(8):1266-1270.
[61] D.J.Lee,S.Mitra,T.F.Krile.Analysis of sequential complex images,using feature extraction and two dimentional cepstrum techniques.J.Opt Soc Am.A, 1989,6(6):863-871.
[62] Q.S.Chen,M.Defrise,F.Deconinck.Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration .IEEE Trans.on Pattern Analysis and Machine Intelligence,1994,16(12):1156-1168.
[63] A.Rosenfeld and A.C.Kak.Digital Picture Processing.Vol.I and II,Academic Press, Orlando, FL,1982.
[64] D.I.Barnea and H.F.Silverman.A class of algorithm for fast digital registration. IEEE Trans.on Computers C-21,1972,p179-186.
[65] A.Goshtasby,G.C.Stockman,C.V.Page.A region-based approach to digital image registration with subpixel accuracy.IEEE Trans.on Geoscience and Remote Sensing,1986,GE-24(3),390-399.
[66] Xiaolong Dai,Siamak Khorram.A feature-Based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Trans.on Geoscience and Remote Sensing,1999,37(5),2351-2362.
[67] P.Bourret,B.Cabon.A neural approach for satellite image registration and pairing segmented areas.[J] SPIE,1995,(2579):22-26.
[68] Gemint Davies Consulting Ltd. DirectShow.2000.
[69] Donoho D L,Johnstone I M,Adapting to unknown smoothness via wavelet Shrinkage[J],J.ASA,1995、90,1200～1223.
[70]彭真明,张启衡,魏宇星,张覃平,基于多特征融合的图像匹配模式[J],强激光与粒子束,2004,16,3,281~285.
[71]孙博玲,分形维数及其测量方法[J],东北林业大学学报,2004,32,3,116~119.
[2]王岩松,阮秋琦,一种基于互相关的图像定位匹配算法研究及应用[J],北方交通大学学报,2002、4,20～24.
[3] INGLADA J,Adragna F,Automatic multi-sensor image registration by edge matching using genetic algorithms[A],IEEE International Conference on Geoscience and Remote Sensing Symposium[C],Sydney,IEEE,Australia,2001,5,2313～2315.
[4] OWN H S,HASSANIEN A E,Multiresolution image registration algorithm in wavelet transform domain[A] IEEE 14th International Conference on Digital Signal Processing[C],Santorini,IEEE,Greece,2002,2,889～892.
[5]刘卫光,周利华,基于小波概率估计的图像融合方法研究[J],光子学报,2004、1,101～104.
[6] BrownL.G..A survey of image registration techniques. ACM Computer, Surveys, Dec.1992, Vol.24,No.4,p325-376.
[7]曾文锋等,基于小波变换的红外图像配准方法[J],激光与红外,2003、8,288～289.
[8] Denney B S,de Figueiredo R J P,Optimal point target detection using adaptive auto regressive background prediction[J],Signal and Data Processing of Small Target,SPIE.2000、4048,46～57.
[9]李红,郑成勇,高景丽,基于小波多尺度图像配准的运动小目标检测[J],红外与激光工程,2003、6,267～270.
[10]孙广富,陈华明,卢焕章,一种低信噪比条件下的红外图像序列小目标实时检测算法[J],2003、12,508～511.
[11]舒付祥,孙继银,一种基于灰度特征的图象匹配算法设计与研究[J],计算机工程与应用,2002、9,101～102.
[12]陈宁江,李介谷,用归一化灰度组合法进行图像匹配[J],红外与激光工程,2000、10,5～9.
[13] Barnea D I,Silverman H F,A class of algorithms for fast digital image registration[J],IEEE Trans.on Comput,1972,C-21,2,179-186.
[14]李震,范湘涛,施建成,基于分窗口相关的遥感图象配准方法[J],中国图象图形学报,2001,6,2,129～132.
[15]韦燕凤,谢启伟,彭思龙,一种基于网格结构图象的目标匹配定位方法[J],中国图象图形学报,2002,7,7,658～662.
[16] Bourret P,Cabon B,A neural approach for satellite image registration and pairing segmented areas[J] SPIE,1995、25794,22.
[17]谢启炜,王洪剑,马超,小波变换目标快速匹配[J],湖北大学学报,2002、3,11～13.
[18]吴均,朱重光,赵忠明,一种基于小波分析的旋转不变图像快速匹配方法[J],遥感学报,2002、9,339～342.
[19]张国柱,王程,王润生,基于小波变换的多分辨率图像匹配方法[J],计算机工程与应用,2001、13,113～114.
[20] Hsieh Jun wei,Image registration using a new edge based approach[J],Computer Vision and Image understanding,1997,67,2,112-130.
[21]彭小明,丁明跃,周成平,一种准自动多传感器图像配准方法[J],华中科技大学学报,2003、4,85～87.
[22]陈灵娜,盛利元,陈俊熹,CT图像配准算法的研究与实现[J],医疗设备信息,2004,19,8:4～5.
[23] Pluim J P W,Maintz J B N,Viergver M A,Image registration by maximization of combined mutual information and gradient information[J],IEEE Transactions on Medical Imaging,2000,19,8,809～814.
[24] Roche A,Pennec X,Malandain G,etal,Rigid registration of 3-Dultrasound with MR images:a new approach combining intensity and gradient information[J],IEEE Transaction on Medical Imaging,2001,20,10,1038～1049.
[25]王强,彭嘉雄,基于轮廓的多源图像的配准[J],计算机与数字工程,2002、5,1～4.
[26]董开坤,胡铭曾,一个新颖的基于熵特征的并行图像匹配算法[J],黑龙江工程学院学报,2001,15,1,40～43.
[27] Shung-Shing Lee,Shi-Jinn Horng,Horng-Ren Tsai,Entropy thresholding and its parallel algorithm on the reconfigurable array of processors with wider bus networks[J],IEEE Transactions on Image Processing,1999,8,9,1229～1242.
[28] Clark F Olson,Image registration by aligning entropies[A],Proceedings of 2001 IEEE Computer Society Conference[C],Kauai,IEEE,Hawaii,USA,2001,2,331～336.
[29]黄勇,王建国,黄顺吉,SAR图像匹配算法及实现[J],信号处理,2003,19,2,179～156.
[30]刘哲,郝重阳,刘晓翔,樊养余,多光谱图像与全色图像的像素级融合研究[J],数据采集与处理,2003,18,3,296～301.
[31]唐健,朱继红,孙增圻,基于智能优化策略的图像自动配准方法[J],清华大学学报(自然科学版),2004,44,9,1252～1255.
[32]刘斌,彭嘉雄,图像配准的小波分解方法[J],计算机辅助设计与图形学学报,2003,15,9,1070～1073.
[33]刘道海,孙作龙,黄樟灿,图像匹配问题的新算法[J],武汉理工大学学报,2002,2,25～27.
[34] Anuta P.E..Spatial registration of multispectral and multitemporal digital imagery using fast Fourier transformation techniques.IEEE Trans.on Geosci.Electron,Oct, 1970,Vol.GE.8,p355-368.
[35] Barnea D.I.,Silverman H.F..A class of algorithms for fast digital image registration.IEEE Trans.on Computers,1972,Vol.C-21,p179-186.
[36] W.K.Pratt著,高荣坤等译,数字图像处理学。科学出版社,1983.
[37] M.Svedlow,C.D.MacGillen,Paul E.Anuta.Image registration:Two new techniques for image matching.Proc 5th Joint Conf.On Artificial Intelligence.Cambridge.Mess.,p659-663.
[38] Henri Maitre,Yifeng Wu.A dynamic programming algorithm for elastic registration of distorted pictures based on autoregressive model.IEEE Trans.on acoustics,speech,and signal processing,1989,Vol.37,p288-298
[39] Jan Flussr.An adaptive method for image registration.Pattern Recognition,1992,Vol.25,p45-54.
[40]熊兴华,钱曾波,王任享。遗传算法与最小二乘法相结合的遥感图像子像素匹配。测绘学报,2001,2,30(1):54-59.
[41]郭海涛,刘智,张保明。基于遗传算法的快速影像匹配技术的研究。测绘学院学报。2001,9,18(S1):20-22.
[42]李智,张雅声。基于轮廓特征的图像配准。CCUA图像分会,1997.
[43]王小睿,吴信才。遥感多图像的自动配准技术。中国图形图像学报。1997(10).
[44]解凯,郭恒业,张田文.图像Mosaics技术综述[J].电子学报,2004,32(4):630-634.
[45] Lucas B D,Kanade T. An iterative image registration technique with an applicationin stereo- vision[C]//In:Seventh Conference on Artificial Intelligence(IJCAI-81).Vancouver:[s.n.],1981:674- 679
[46]钟力,胡晓峰.重叠图像拼接算法[J].中国图像图形学报,1998,3(5):367-370.
[47]陈果,左洪福.显微图像的一种快速拼接算法[J].仪器仪表学报,2003,24(4):343-347.
[48] Castro E D,Morandi C.Registration of Translated and Rotated Images Using Finite Fourier Transforms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,PAMI,1987,9(5):700-703.
[49] Anuta P E.Spatial Registration of Multispectral and Multitemporal Digital Images Using fast Fourier Transform Techniques[J].IEEE Trans Geo.Elec.,1970(8):353-368.
[50] Kuglin C D,Hines D C.The Phase Correlation Image Alignment Method[C]//In Proc of IEEE Int Conf.on Cybernetics and Society.New York:[s.n.],1975:163-165.
[51]许雷,张恒义,虞亚军,等.一种基于相位相关法及数学形态学方法的眼底血管图像自动拼接方法[J].生物医学工程杂志,1998,15(3):286-290.
[52] Li H,Manjunath B S,Mitra S K.A contour based approach to multisensor image registration[J].IEEE Trans Image Processing,1995(4):320-334.
[53]俞辉,侯在克,何旭莉,等.一种基于轮廓特征的图像拼接算法设计与实现[J].石油大学学报:自然科学版,2003,27(2):114-118.
[54]张静,胡志萍,刘志泰,等.基于轮廓相位相关的图像自动拼接[J].大连理工大学学报,2005,45(1):68-74.
[55] Harris C,Stephens M.A combined corner and edge detector[C]//InProc.Alvey Conf Vision.England:Manchester University Press,1988:189-192.
[56] Brown M,Lowe D G.Invariant Features From Interest Point Groups[C]//In British Machine Vision Conference.Cardiff,Wales:[s.n.],2002:656-665.
[57] Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of ComputerVision,2004,60(2):91-110.
[58] Burt P J,Adelson E H.The laplacian pyramid as a compact image code[J].IEEE Transaction on Communications,1983,com-31(4):532-540.
[59] Anuta P.E..Spatial registration of multispectral and multitemporal digital imagery using fast Fourier transform techniques.IEEE Trans.Geo Elec,1970(8):353-368.
[60] B.S.Reddy,B.N.Chatterji.An fft-based technique for translation,rotation,and scale-invariant image registration.IEEE Trans on Image Processing,1996,3(8):1266-1270.
[61] D.J.Lee,S.Mitra,T.F.Krile.Analysis of sequential complex images,using feature extraction and two dimentional cepstrum techniques.J.Opt Soc Am.A, 1989,6(6):863-871.
[62] Q.S.Chen,M.Defrise,F.Deconinck.Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration .IEEE Trans.on Pattern Analysis and Machine Intelligence,1994,16(12):1156-1168.
[63] A.Rosenfeld and A.C.Kak.Digital Picture Processing.Vol.I and II,Academic Press, Orlando, FL,1982.
[64] D.I.Barnea and H.F.Silverman.A class of algorithm for fast digital registration. IEEE Trans.on Computers C-21,1972,p179-186.
[65] A.Goshtasby,G.C.Stockman,C.V.Page.A region-based approach to digital image registration with subpixel accuracy.IEEE Trans.on Geoscience and Remote Sensing,1986,GE-24(3),390-399.
[66] Xiaolong Dai,Siamak Khorram.A feature-Based image registration algorithm using improved chain-code representation combined with invariant moments. IEEE Trans.on Geoscience and Remote Sensing,1999,37(5),2351-2362.
[67] P.Bourret,B.Cabon.A neural approach for satellite image registration and pairing segmented areas.[J] SPIE,1995,(2579):22-26.
[68] Gemint Davies Consulting Ltd. DirectShow.2000.
[69] Donoho D L,Johnstone I M,Adapting to unknown smoothness via wavelet Shrinkage[J],J.ASA,1995、90,1200～1223.
[70]彭真明,张启衡,魏宇星,张覃平,基于多特征融合的图像匹配模式[J],强激光与粒子束,2004,16,3,281~285.
[71]孙博玲,分形维数及其测量方法[J],东北林业大学学报,2004,32,3,116~119.