基于互信息的图像配准并行算法研究与实现
|
摘要
图像配准是图像融合、图像分析、目标变化检测与识别等问题中的重要步骤,其应用遍及军事、遥感、医学、计算机视觉等多个领域。互信息(Mutual Information)来自于信息论,是两个随机变量统计相关性的度量,由于其具有无需预处理、自动化程度高以及鲁棒性强等特点,近几年将互信息作为一种相似性测度进行图像配准成为图像处理领域的研究热点。随着传感器、遥感平台等相关技术的发展,信息的获取途径越来越多,获得的数据量也随之急剧增长,而许多应用领域对图像配准处理速度的要求也越来越高。显然,传统的单处理器配准处理串行算法已经无法满足这样的运算需求,而并行处理是解决这一问题的重要技术手段。
目前,国内外的研究主要集中在提高配准质量上,而针对海量数据配准和强实时性配准的大规模并行算法研究尚处于起步阶段。因此研究并实现图像配准的并行算法,将大大提高配准处理效率,具有广阔的应用前景。
本文针对上述需求,重点针对基于互信息的图像配准并行算法进行深入研究和实践工作。本文的主要工作和贡献如下:
1、深入研究了互信息理论的计算方法。采用直方图和Parzen窗两种方法计算互信息,并分析比较了这两种计算方法。实验结果表明,直方图法得到的结果比较粗糙,但计算速度较快。基于Parzen窗估计的计算方法,样本估计的效果取决于窗函数的形式和宽度,在样本数目足够大时,计算精度高,但是在计算时需要进行多个累加和,计算量很大。
2、深入研究了图像配准算法的三种常用的相似性测度——互信息、相关系数、差方和,并通过实验从计算时间、锐度、对噪声的容忍性以及对多模图像配准的影响等方面分析和比较了三种测度的优劣。实验表明,在多数情况下,互信息的配准精度是这三种相似性测度中最高的。
3、提出并实现了一种基于互信息的刚性图像配准并行算法。该算法基于刚性变换模型,图像数据采用块(block)划分,在算法运行过程中实现了数据分块并行读入,较好地解决了负载平衡问题。采用二叉树规约方法计算互信息,加快配准速度。实验结果表明该算法获得了良好的加速比,可扩展性好,并行效率较高。
4、提出了一类(基于基函数)非刚性图像配准并行算法设计模型,并应用该模型对一种具体的非刚性串行算法进行了并行化。该模型采用并行读入交叉划分数据、并行自动选取标记点、二叉树规约计算互信息和并行输出分块图像。理论分析表明,该算法设计模型的并行效率高,通用性较强。
Image registration is an important problem in image fusion, image analysis, change detection and target recognition. Applications of image registration are in the domain of military, remote sensed data processing, medical, computer vision and so on. The mutual information, which originates from information theory, is the measure of two random variables statistical relevance, and can be applied in image registration as a similarity measure. Since the mutual information has advantages including no pre-processing, robustness and high automatic processing, it becomes a hot topic in image registration. With the rapid development of sensor and remote sensing platform technology, there are more and more approaches and sorts of the information we can get . As a result , the data sets gotten from the sensor are increasing tremendously. Meanwhile, rapid processing technologies and real time process in many domains become more and more urgent, and the traditional single-processor can't achieve the requirement. However, the key to solve the problem is using parallel processing. Since both the need for image registration and the amount of data to register are growing tremendously, the implementation of automatic image registration methods on high-performance computers needs to be investigated.
Nowadays, the current research is focusing on improving the registration quality mostly, but the research of parallel processing on the large number of data sets and the real time request in registration algorithms are in the beginning. So we do some research on parallel algorithms for image registration that could make great progress in the efficiency and the speed of image registration, which can be applied broadly.
This paper aims at the research and implementation of parallel algorithms for image registration processing based on mutual information. The contributions and relevant work in the paper are as follows:
Firstly, we discuss the mutual information computation methods which are based on Histogram and Parzen window. And then we analyze them and compare them with each other. It shows that the method based on Histogram is coarser, but it is faster than the method based on Parzen window. The Parzen Window method is determined by the window function's form and width. With this method, when samples are enough it is precise. But its cost is great because it has to be added up many times.
Secondly, we discuss three typical kinds of similarity measure, which are Mutual Information, Correlation Coefficient and Sum of Square Differences. Then, the performance of these measures is compared and analyzed by computing time, sharpness, sensitivity of noise and effect on multimodal image registration. The results of experiments show that these similarity measure methods have different effect and performance in the different application circumstances, but the mutual information is more precise.
Thirdly, a rigid parallel image registration algorithm based on mutual information is presented and implemented. The algorithm uses rigid transform, and it solves the problem of load balancing with image data vertical division, data block parallel inputting. Binary Tree Reduction is used in parallel computing mutual information, which speeds up the registration rate and increases the computation efficiency. The experiment results show that the algorithm has a good speedup, scalability, and high parallel efficiency.
Finally, we present a parallel non-rigid image registration algorithm model (based on Basic Function), and then we use the model to parallel a non-rigid algorithm. The parallel technologies applied to the model are parallel inputting the Cross-division of the data, parallel automatic selecting marker, Binary Tree Reduction calculation of the mutual information and parallel outputting the block images. Theoretical analysis shows that the algorithm model has a high parallel efficiency and a relatively strong versatility.
目前,国内外的研究主要集中在提高配准质量上,而针对海量数据配准和强实时性配准的大规模并行算法研究尚处于起步阶段。因此研究并实现图像配准的并行算法,将大大提高配准处理效率,具有广阔的应用前景。
本文针对上述需求,重点针对基于互信息的图像配准并行算法进行深入研究和实践工作。本文的主要工作和贡献如下:
1、深入研究了互信息理论的计算方法。采用直方图和Parzen窗两种方法计算互信息,并分析比较了这两种计算方法。实验结果表明,直方图法得到的结果比较粗糙,但计算速度较快。基于Parzen窗估计的计算方法,样本估计的效果取决于窗函数的形式和宽度,在样本数目足够大时,计算精度高,但是在计算时需要进行多个累加和,计算量很大。
2、深入研究了图像配准算法的三种常用的相似性测度——互信息、相关系数、差方和,并通过实验从计算时间、锐度、对噪声的容忍性以及对多模图像配准的影响等方面分析和比较了三种测度的优劣。实验表明,在多数情况下,互信息的配准精度是这三种相似性测度中最高的。
3、提出并实现了一种基于互信息的刚性图像配准并行算法。该算法基于刚性变换模型,图像数据采用块(block)划分,在算法运行过程中实现了数据分块并行读入,较好地解决了负载平衡问题。采用二叉树规约方法计算互信息,加快配准速度。实验结果表明该算法获得了良好的加速比,可扩展性好,并行效率较高。
4、提出了一类(基于基函数)非刚性图像配准并行算法设计模型,并应用该模型对一种具体的非刚性串行算法进行了并行化。该模型采用并行读入交叉划分数据、并行自动选取标记点、二叉树规约计算互信息和并行输出分块图像。理论分析表明,该算法设计模型的并行效率高,通用性较强。
Image registration is an important problem in image fusion, image analysis, change detection and target recognition. Applications of image registration are in the domain of military, remote sensed data processing, medical, computer vision and so on. The mutual information, which originates from information theory, is the measure of two random variables statistical relevance, and can be applied in image registration as a similarity measure. Since the mutual information has advantages including no pre-processing, robustness and high automatic processing, it becomes a hot topic in image registration. With the rapid development of sensor and remote sensing platform technology, there are more and more approaches and sorts of the information we can get . As a result , the data sets gotten from the sensor are increasing tremendously. Meanwhile, rapid processing technologies and real time process in many domains become more and more urgent, and the traditional single-processor can't achieve the requirement. However, the key to solve the problem is using parallel processing. Since both the need for image registration and the amount of data to register are growing tremendously, the implementation of automatic image registration methods on high-performance computers needs to be investigated.
Nowadays, the current research is focusing on improving the registration quality mostly, but the research of parallel processing on the large number of data sets and the real time request in registration algorithms are in the beginning. So we do some research on parallel algorithms for image registration that could make great progress in the efficiency and the speed of image registration, which can be applied broadly.
This paper aims at the research and implementation of parallel algorithms for image registration processing based on mutual information. The contributions and relevant work in the paper are as follows:
Firstly, we discuss the mutual information computation methods which are based on Histogram and Parzen window. And then we analyze them and compare them with each other. It shows that the method based on Histogram is coarser, but it is faster than the method based on Parzen window. The Parzen Window method is determined by the window function's form and width. With this method, when samples are enough it is precise. But its cost is great because it has to be added up many times.
Secondly, we discuss three typical kinds of similarity measure, which are Mutual Information, Correlation Coefficient and Sum of Square Differences. Then, the performance of these measures is compared and analyzed by computing time, sharpness, sensitivity of noise and effect on multimodal image registration. The results of experiments show that these similarity measure methods have different effect and performance in the different application circumstances, but the mutual information is more precise.
Thirdly, a rigid parallel image registration algorithm based on mutual information is presented and implemented. The algorithm uses rigid transform, and it solves the problem of load balancing with image data vertical division, data block parallel inputting. Binary Tree Reduction is used in parallel computing mutual information, which speeds up the registration rate and increases the computation efficiency. The experiment results show that the algorithm has a good speedup, scalability, and high parallel efficiency.
Finally, we present a parallel non-rigid image registration algorithm model (based on Basic Function), and then we use the model to parallel a non-rigid algorithm. The parallel technologies applied to the model are parallel inputting the Cross-division of the data, parallel automatic selecting marker, Binary Tree Reduction calculation of the mutual information and parallel outputting the block images. Theoretical analysis shows that the algorithm model has a high parallel efficiency and a relatively strong versatility.
引文
[1]Lisa Gottesfeld Brown.A Survey of Image Registration Techniques.ACM ComputingS urveys,1992,325-376.
[2]A.Collignon,F.Maes,D.Delaere,D.Vandermeulen,P.Suetens,and G.Marchal,Automated multi-modality image registration based on information theory,Information Processing in Medical Imaging,Y.Bizais,C.Barillot,and R.Di Paola,Eds.1995,Kluwer Academic Publishers,1997,187-198
[3]P.A.Viola,Alignment by maximization of mutual information,Ph.D.thesis,Massachusetts Institute of Technology,Boston,MA,USA,1995
[4]Twan Dr IrJ.B.A.Maintz,Max Prof Dr Ir M.A.Viergever.A Survey of medial image registration Medical Image Analysis,1998
[5]Karl Rohr,Elastic registration ofmultimodal medical images:a survey,KI--Künstliche Intelligenz,July 2000,11-17
[6]Peter Rogelj,non-rigid registration ofmulti-modality images,Ph.D.Thesis,2003
[7]章孝灿,黄智才,赵元洪,遥感数字图像处理,杭州:浙江大学出版社,1997
[8]熊桢,高光谱遥感图像分类技术研究,北京:中国科学院遥感应用研究所,2000
[9]Jan Kybic,and Michael Unser,Fast Parametric Elastic Image Registration,IEEE Trans.image processing,November 2003,1427-1442
[10]Jacqueline Le Moigne,William J.Campbell,and Robert F.Cromp,An automated Parallel Image Registration Technique Based on the Correlation of Wavelet Features,IEEE Trans.geoscience and remote sensing,August 2002,1849-1864
[11]Torsten Rohlfing and Calvin R.Maurer,Nonrigid image registration in shared-memory multiprocessor environments with application to brains,breasts and bees,IEEE trans,information technology in biomedicine,March 2003,16-25
[12]周海芳,遥感图像并行处理算法的研究与应用,国防科学技术大学研究生院博士论文,2003
[13]D.Rueckert,M.J.Clarkson,D.L.G.Hill,and D.J.Hawkes,Non-rigid registration using higher-order mutual information,Medical Imaging:Image Processing,K.M.Hanson,Ed.2000,SPIE Press,Bellingham
[14]W.K.Prat,Correlation techniques of image registration,IEEE Trans.Aero space and Electronic Systems,1974
[15]W.K.Prat,Digital Image Processing,John Wiley,NewYork,2nd ed.,1991
[16] R.Berthilsson , Affine correlation , Proc.Int'l.Conf.on Patern Recognition CPR'98, Brisbane, Australia , 1998
[17] A.Simper, Correcting general band-to-band misregistrations, Proc.IEEE Int'l. Conf.on Image Processing ICIP'96, volt, L ausanne, Switzerland, 1996, 597-600
[18] Kaneko S, Satoh Y, Igarashi S. Using selective Correlation coefficient for robust image registration, Patern Recognition.2003, 1165-1173
[19] G. Wolberg, S. Zokai, Image registration for perspective deformation recovery,SPIE Conference on Automatic Target Recognition X, Orlando, Florida,USA, April 2000
[20] Studholme C, Hill DLG, Hawkes DJ, An overlap invariant entropy measure of 3D medical image alignment. Patern Recognition, 1999, 71-86
[21] D. Rueckert, C.Hayes, C. Studholme, E Summers, M. Leach registration of breast MR images using mutual information, ProcD. J. Hawkes, Non-rigid Medical Image Computing and Computer-Assisted Intervention MICCAI'98,Cambridge , 1144-1152
[22] P. W .Pluim, J. B. A .Maintz, M .A .Viergever, Proc. Int'l Workshop on Biomedical Image , 2003
[23] A .Goshtasby, Template matching in rotated images, IEEE Trans.Patem Analysis and M achine Intelligence7 , 1985
[24] H Jiang, R .A.Robb, and K S Holton, New approach to 3-D registration of multimodality medical images by surface matching.Proc.of SPIE, 1992
[25] G. Stockman, S. Kopstein, S. Benet, Matching images to models for registration and object detection viaclustering, I EEE Trans.Patem Analysis and Machine Intelligence , 1982
[26] G. Barrow, JM. Tenenbaum, R. C. Bolles, H. C. Wolf, Parametric correspondence and chamfer matching:Intell., Cambridge, Two new techniques for image matching, Proc. 5th Int'l. Joint Conf. Art, Massachusets, 1977
[27] J. Canny, A computational approach to edge detection, IEEE Trans. Patern Analysis and Machine Intelligence , 1986
[28] D.Marr, E.Hildreth, Theory of edge detection, Proc.R .Soc.London, 1980
[29] H.Li , B .S. Manjunath, S. K .Mitra, A contour-based approach to multi sensor image registration, IEEE Trans.Image Processing , 1995
[30] J. B .A .Maintz, P .A .vanden Elsen, M .A .Viergever, E valuation on ridge seeking o perators for multi modality medical image matching, IEEE Trans.Patem Analysis and Machine Intelligence,1996,320-333
[31]J.B.A.Maintz,P.A.vanden Elsen,M.A.Viergever,Comparison of edge-based and ridge based registration of CT and MR brain images,Medical Image Analysis1,1996,151-161
[32]R.Bajcsy and S.Kovacic,Multiresolution elastic matching,Comput.Vis.Graph.Image Process.,1989,1-21
[33]Karl Rohr,Elastic registration of multimodal medical images:a survey,KI--Künstliche Intelligenz 3/00,July 2000,11-17
[34]G.E.Christensen,R.D.Rabbitt,Miller,Deformable templates using large deformation kinematics,IEEE Trans.Image Processing,vol.5,1996,1435-1447
[35]M Bro Nielsen,C.Cramkow,Fast fluid registration of medical images,SPIE Medicallmaging,1996,267-276
[36]R.L.Harder,R.N.Desmarais,Interpolation using surface splines,Journal of A ircraft9,1972,189-191
[37]W.E.L.Grimson,A computational theory of visual surface interpolation,Phil.Trans.R.Soc.London.,1982,395-427
[38]F.L.Bookstein,Principal warps:Thin-plate splines and the decomposition of deformations IEEE Trans.Patern Analysis and Machine Intelligence 11,1989,567-585
[39]A.Goshtasby,Registration of images with geometric distortions,Remote S ensing,1988,60-64
[40]冯林,张名举,贺明峰,戚正君,滕弘飞,用分层互信息和薄板样条实现医学图像弹性自动配准,计算机辅助设计与图形学学报,2005
[41]Ozkan M,Fitzpatrick J.M,Kawamura K.Image Registration for a Transputer-Based Distributed System.in proceedings of the 2nd International Conference on Industrial & Engineering Applications of AI & Expert Systems (IEA/AIE-89),1989,08-915
[42]LeMoigne J.Towards a Parallel Registration of Multiple Resolution Remote Sensing Data.Proceedings of IGARSS'95.Firenze,Italy.1995
[43]Turton B,Arslan T,Horrocks D.A hardware architecture for a parallel genetic algorithm for image registration,in Proceedings of IEEE Colloquium on Genetic Algorithms in Image Processing and Vision.,1994,111-116
[44]El-Ghazawi T,Chalermwat P,LeMoigne J.Wavelet-based image Registration on parallel computers,in SuperComputing'97:High Performance Networking and Computing:Proceedings ACM/IEEE.,1997
[45]Chalermwat P.High performance automatic image registration for remote sensing.[Ph.D.Thesis].George Mason University.Fairfax,Virginia.1999
[46]Haifang Zhou,Xuejun Yang,Yu Tang,First Evaluation of Parallel Methods of Automatic Global Image Registration Based on Wavelets,Proceedings of the 34th International Conference on Parallel Processing(ICPP'05),Oslo,Norway,IEEE Computer Society,Los Alamitos,2005,129-136
[47]G.E.Christensen,R.D.Rabbitt,Miller,Deformable templates using large deformation kinematics,IEEE Trans.Image Processing,vol.5,996,1435-1447
[48]Simon K.Warfield,Matthieu Ferrant,Xavier Gallez,Arya Nabavi,Ferenc A.Jolesz,RonKikinis,Real-Time Biomechanical Simulation of Volumetric Brain Deformation for Image Guided Neurosurgery,SuperComputing 2000
[49]Fumihiko Ino,Kanrou Ooyama,Kenichi Hagihara,A data distributed parallel algorithm for nonrigid image registration,Parallel Computing,Vol.31,Issue 2005,19-43
[50]Mark P.Wachowiak,Member,IEEE,and Terry M.Peters,Senior Member,IEEE,High Performance Medical Image Registration Using New Optimization Techniques,HPCS'05
[51]Torsten Rohlfing and Calvin R.Maurer,Nonrigid image registration in shared-memory multiprocessor environments with application to brains,breasts,and bees,IEEE trans,information technology in biomedicin,2003,16-25
[52]Radu Stefanescu,Parallel nonlinear registration of medical images with a priori information on anatomy and pathology,PhD thesis,University de Nice -Sophia Antipolis,March 2005
[53]Pitas I.Parallel Algorithms for Digital Image Processing,Computer Vision and Neural Network.John Wiley & SonLtd.UK.1993
[54]陈国良.并行算法的设计与分析.北京:高等教育出版社.1994
[55]沈志宇,廖湘科,胡子昂,并行程序设计,长沙:国防科技大学出版社.1997
[56]Philippe Thevenaz,Michael Unser,Optimization of mutual information for multiresolution image registration,IEEE trans.Image processing,December 2000,2083-2099
[57]I.Vajda,Yheoryof statistical inference and information,Dordrecht,The Netherlands,Kluwer,1989
[58]StudholmeC,Measure of 3D medical image alignment.Pattem Recognition,1999
[59]E.Parzen,"On Estimation of a Probability Density Function and Mode,"Annals of Math.Statistics,vol.33,Sept.1962,1065-1076
[60]S.Heldmann,O.Mahnke,D.Potts,J.Modersitzki,and B.Fischer,Fast computation of Mutual Information in a variational image registration approach,Bildverarbeitung für die Medizin 2004 T.Tolxdorff,J.Braun,H.Handels,A.Horsch,H.P.Meinzer(eds),Springer,Berlin,2004,pp448-452
[61]Radu Stefanescu,Parallel nonlinear registration of medical images with a prior information on anatomy and pathology,PhD thesis,University de Nice - Sophia Antipolis,March 2005
[62]Arlene A.Cole-Rhodes,Kisha L.Johnson,Jacqueline LeMoigne,and Ilya Zavorin,Multiresolution Registration of Remote Sensing Imagery by Optimization of Mutual Information Using a Stochastic Gradient[J],IEEE Trans.Image Processing,Dec.2003,1495-1511
[63]Ilya Zavorin,Jacqueline LeMoigne,Use of Multiresolution Wavelet Feature Pyramids for Automatic Registration of Multisensor Imagery[J],IEEE Trans.Image Processing,June 2005,770-782
[64]时永刚,邹谋炎,图像配准中统计型相似性测度的比较与分析,计算机学报2004.9,1278-1283
[65]Jochen F.Krücker,Gerald L.LeCarpentier,J.Brian Fowlkes,and Paul L.Carson,Rapid Elastic Image Registration for 3-D Ultrasound,IEEE Trans.medical imaging,vol.21,no.11,Novermber 2002,1384-1394
[66]粟塔山,最优化计算原理与算法程序设计,长沙:国防科技大学出版社,2000
[67]Barbara Zitova*,Jan Flusser,Image registration methods:a survey,Image and Vision Computing 21,June 2003
[68]Kybic,and Michael Unser,Fast Parametric Elastic Image Registration,IEEE Trans.image processing,vol.12,no.11,November 2003,1427-1442
[69]Likar B,Pemus F.A hierarchical approach ato elastic registration based mutual information[J].Image and Vision Computing,2001,31-40
[70]K.Rohr,Localization properties of direct comer detectors,Journal of Mathematical Imaging and Vision 4 1994,139-150
[71]J.A.Schnabel,D.Rueckert,M.Quist,J.M.Blackall,A.D.Castellano-Smith,T.Hartkens,G.P.Penney,W.A.Hall,H.Liu,C.L.Truwit,F.A.Gerritsen,D.L.G.Hill,D.J.Hawkes,A generic framework for non-rigid registration based on non-uniform multi-level free-form deformations,in:Proceeding of the 4th International Conference on Medical Image Computing and Computer- Assisted Intervention(MICCAI_01),Lecture Notes in Computer Science,vol.2208,2001,573-581
[2]A.Collignon,F.Maes,D.Delaere,D.Vandermeulen,P.Suetens,and G.Marchal,Automated multi-modality image registration based on information theory,Information Processing in Medical Imaging,Y.Bizais,C.Barillot,and R.Di Paola,Eds.1995,Kluwer Academic Publishers,1997,187-198
[3]P.A.Viola,Alignment by maximization of mutual information,Ph.D.thesis,Massachusetts Institute of Technology,Boston,MA,USA,1995
[4]Twan Dr IrJ.B.A.Maintz,Max Prof Dr Ir M.A.Viergever.A Survey of medial image registration Medical Image Analysis,1998
[5]Karl Rohr,Elastic registration ofmultimodal medical images:a survey,KI--Künstliche Intelligenz,July 2000,11-17
[6]Peter Rogelj,non-rigid registration ofmulti-modality images,Ph.D.Thesis,2003
[7]章孝灿,黄智才,赵元洪,遥感数字图像处理,杭州:浙江大学出版社,1997
[8]熊桢,高光谱遥感图像分类技术研究,北京:中国科学院遥感应用研究所,2000
[9]Jan Kybic,and Michael Unser,Fast Parametric Elastic Image Registration,IEEE Trans.image processing,November 2003,1427-1442
[10]Jacqueline Le Moigne,William J.Campbell,and Robert F.Cromp,An automated Parallel Image Registration Technique Based on the Correlation of Wavelet Features,IEEE Trans.geoscience and remote sensing,August 2002,1849-1864
[11]Torsten Rohlfing and Calvin R.Maurer,Nonrigid image registration in shared-memory multiprocessor environments with application to brains,breasts and bees,IEEE trans,information technology in biomedicine,March 2003,16-25
[12]周海芳,遥感图像并行处理算法的研究与应用,国防科学技术大学研究生院博士论文,2003
[13]D.Rueckert,M.J.Clarkson,D.L.G.Hill,and D.J.Hawkes,Non-rigid registration using higher-order mutual information,Medical Imaging:Image Processing,K.M.Hanson,Ed.2000,SPIE Press,Bellingham
[14]W.K.Prat,Correlation techniques of image registration,IEEE Trans.Aero space and Electronic Systems,1974
[15]W.K.Prat,Digital Image Processing,John Wiley,NewYork,2nd ed.,1991
[16] R.Berthilsson , Affine correlation , Proc.Int'l.Conf.on Patern Recognition CPR'98, Brisbane, Australia , 1998
[17] A.Simper, Correcting general band-to-band misregistrations, Proc.IEEE Int'l. Conf.on Image Processing ICIP'96, volt, L ausanne, Switzerland, 1996, 597-600
[18] Kaneko S, Satoh Y, Igarashi S. Using selective Correlation coefficient for robust image registration, Patern Recognition.2003, 1165-1173
[19] G. Wolberg, S. Zokai, Image registration for perspective deformation recovery,SPIE Conference on Automatic Target Recognition X, Orlando, Florida,USA, April 2000
[20] Studholme C, Hill DLG, Hawkes DJ, An overlap invariant entropy measure of 3D medical image alignment. Patern Recognition, 1999, 71-86
[21] D. Rueckert, C.Hayes, C. Studholme, E Summers, M. Leach registration of breast MR images using mutual information, ProcD. J. Hawkes, Non-rigid Medical Image Computing and Computer-Assisted Intervention MICCAI'98,Cambridge , 1144-1152
[22] P. W .Pluim, J. B. A .Maintz, M .A .Viergever, Proc. Int'l Workshop on Biomedical Image , 2003
[23] A .Goshtasby, Template matching in rotated images, IEEE Trans.Patem Analysis and M achine Intelligence7 , 1985
[24] H Jiang, R .A.Robb, and K S Holton, New approach to 3-D registration of multimodality medical images by surface matching.Proc.of SPIE, 1992
[25] G. Stockman, S. Kopstein, S. Benet, Matching images to models for registration and object detection viaclustering, I EEE Trans.Patem Analysis and Machine Intelligence , 1982
[26] G. Barrow, JM. Tenenbaum, R. C. Bolles, H. C. Wolf, Parametric correspondence and chamfer matching:Intell., Cambridge, Two new techniques for image matching, Proc. 5th Int'l. Joint Conf. Art, Massachusets, 1977
[27] J. Canny, A computational approach to edge detection, IEEE Trans. Patern Analysis and Machine Intelligence , 1986
[28] D.Marr, E.Hildreth, Theory of edge detection, Proc.R .Soc.London, 1980
[29] H.Li , B .S. Manjunath, S. K .Mitra, A contour-based approach to multi sensor image registration, IEEE Trans.Image Processing , 1995
[30] J. B .A .Maintz, P .A .vanden Elsen, M .A .Viergever, E valuation on ridge seeking o perators for multi modality medical image matching, IEEE Trans.Patem Analysis and Machine Intelligence,1996,320-333
[31]J.B.A.Maintz,P.A.vanden Elsen,M.A.Viergever,Comparison of edge-based and ridge based registration of CT and MR brain images,Medical Image Analysis1,1996,151-161
[32]R.Bajcsy and S.Kovacic,Multiresolution elastic matching,Comput.Vis.Graph.Image Process.,1989,1-21
[33]Karl Rohr,Elastic registration of multimodal medical images:a survey,KI--Künstliche Intelligenz 3/00,July 2000,11-17
[34]G.E.Christensen,R.D.Rabbitt,Miller,Deformable templates using large deformation kinematics,IEEE Trans.Image Processing,vol.5,1996,1435-1447
[35]M Bro Nielsen,C.Cramkow,Fast fluid registration of medical images,SPIE Medicallmaging,1996,267-276
[36]R.L.Harder,R.N.Desmarais,Interpolation using surface splines,Journal of A ircraft9,1972,189-191
[37]W.E.L.Grimson,A computational theory of visual surface interpolation,Phil.Trans.R.Soc.London.,1982,395-427
[38]F.L.Bookstein,Principal warps:Thin-plate splines and the decomposition of deformations IEEE Trans.Patern Analysis and Machine Intelligence 11,1989,567-585
[39]A.Goshtasby,Registration of images with geometric distortions,Remote S ensing,1988,60-64
[40]冯林,张名举,贺明峰,戚正君,滕弘飞,用分层互信息和薄板样条实现医学图像弹性自动配准,计算机辅助设计与图形学学报,2005
[41]Ozkan M,Fitzpatrick J.M,Kawamura K.Image Registration for a Transputer-Based Distributed System.in proceedings of the 2nd International Conference on Industrial & Engineering Applications of AI & Expert Systems (IEA/AIE-89),1989,08-915
[42]LeMoigne J.Towards a Parallel Registration of Multiple Resolution Remote Sensing Data.Proceedings of IGARSS'95.Firenze,Italy.1995
[43]Turton B,Arslan T,Horrocks D.A hardware architecture for a parallel genetic algorithm for image registration,in Proceedings of IEEE Colloquium on Genetic Algorithms in Image Processing and Vision.,1994,111-116
[44]El-Ghazawi T,Chalermwat P,LeMoigne J.Wavelet-based image Registration on parallel computers,in SuperComputing'97:High Performance Networking and Computing:Proceedings ACM/IEEE.,1997
[45]Chalermwat P.High performance automatic image registration for remote sensing.[Ph.D.Thesis].George Mason University.Fairfax,Virginia.1999
[46]Haifang Zhou,Xuejun Yang,Yu Tang,First Evaluation of Parallel Methods of Automatic Global Image Registration Based on Wavelets,Proceedings of the 34th International Conference on Parallel Processing(ICPP'05),Oslo,Norway,IEEE Computer Society,Los Alamitos,2005,129-136
[47]G.E.Christensen,R.D.Rabbitt,Miller,Deformable templates using large deformation kinematics,IEEE Trans.Image Processing,vol.5,996,1435-1447
[48]Simon K.Warfield,Matthieu Ferrant,Xavier Gallez,Arya Nabavi,Ferenc A.Jolesz,RonKikinis,Real-Time Biomechanical Simulation of Volumetric Brain Deformation for Image Guided Neurosurgery,SuperComputing 2000
[49]Fumihiko Ino,Kanrou Ooyama,Kenichi Hagihara,A data distributed parallel algorithm for nonrigid image registration,Parallel Computing,Vol.31,Issue 2005,19-43
[50]Mark P.Wachowiak,Member,IEEE,and Terry M.Peters,Senior Member,IEEE,High Performance Medical Image Registration Using New Optimization Techniques,HPCS'05
[51]Torsten Rohlfing and Calvin R.Maurer,Nonrigid image registration in shared-memory multiprocessor environments with application to brains,breasts,and bees,IEEE trans,information technology in biomedicin,2003,16-25
[52]Radu Stefanescu,Parallel nonlinear registration of medical images with a priori information on anatomy and pathology,PhD thesis,University de Nice -Sophia Antipolis,March 2005
[53]Pitas I.Parallel Algorithms for Digital Image Processing,Computer Vision and Neural Network.John Wiley & SonLtd.UK.1993
[54]陈国良.并行算法的设计与分析.北京:高等教育出版社.1994
[55]沈志宇,廖湘科,胡子昂,并行程序设计,长沙:国防科技大学出版社.1997
[56]Philippe Thevenaz,Michael Unser,Optimization of mutual information for multiresolution image registration,IEEE trans.Image processing,December 2000,2083-2099
[57]I.Vajda,Yheoryof statistical inference and information,Dordrecht,The Netherlands,Kluwer,1989
[58]StudholmeC,Measure of 3D medical image alignment.Pattem Recognition,1999
[59]E.Parzen,"On Estimation of a Probability Density Function and Mode,"Annals of Math.Statistics,vol.33,Sept.1962,1065-1076
[60]S.Heldmann,O.Mahnke,D.Potts,J.Modersitzki,and B.Fischer,Fast computation of Mutual Information in a variational image registration approach,Bildverarbeitung für die Medizin 2004 T.Tolxdorff,J.Braun,H.Handels,A.Horsch,H.P.Meinzer(eds),Springer,Berlin,2004,pp448-452
[61]Radu Stefanescu,Parallel nonlinear registration of medical images with a prior information on anatomy and pathology,PhD thesis,University de Nice - Sophia Antipolis,March 2005
[62]Arlene A.Cole-Rhodes,Kisha L.Johnson,Jacqueline LeMoigne,and Ilya Zavorin,Multiresolution Registration of Remote Sensing Imagery by Optimization of Mutual Information Using a Stochastic Gradient[J],IEEE Trans.Image Processing,Dec.2003,1495-1511
[63]Ilya Zavorin,Jacqueline LeMoigne,Use of Multiresolution Wavelet Feature Pyramids for Automatic Registration of Multisensor Imagery[J],IEEE Trans.Image Processing,June 2005,770-782
[64]时永刚,邹谋炎,图像配准中统计型相似性测度的比较与分析,计算机学报2004.9,1278-1283
[65]Jochen F.Krücker,Gerald L.LeCarpentier,J.Brian Fowlkes,and Paul L.Carson,Rapid Elastic Image Registration for 3-D Ultrasound,IEEE Trans.medical imaging,vol.21,no.11,Novermber 2002,1384-1394
[66]粟塔山,最优化计算原理与算法程序设计,长沙:国防科技大学出版社,2000
[67]Barbara Zitova*,Jan Flusser,Image registration methods:a survey,Image and Vision Computing 21,June 2003
[68]Kybic,and Michael Unser,Fast Parametric Elastic Image Registration,IEEE Trans.image processing,vol.12,no.11,November 2003,1427-1442
[69]Likar B,Pemus F.A hierarchical approach ato elastic registration based mutual information[J].Image and Vision Computing,2001,31-40
[70]K.Rohr,Localization properties of direct comer detectors,Journal of Mathematical Imaging and Vision 4 1994,139-150
[71]J.A.Schnabel,D.Rueckert,M.Quist,J.M.Blackall,A.D.Castellano-Smith,T.Hartkens,G.P.Penney,W.A.Hall,H.Liu,C.L.Truwit,F.A.Gerritsen,D.L.G.Hill,D.J.Hawkes,A generic framework for non-rigid registration based on non-uniform multi-level free-form deformations,in:Proceeding of the 4th International Conference on Medical Image Computing and Computer- Assisted Intervention(MICCAI_01),Lecture Notes in Computer Science,vol.2208,2001,573-581