多光谱与全色图像融合方法的研究
|
摘要
为使多光谱与高空间分辨率全色图像的融合效果在努力保持光谱信息的同时尽可能提高其空间分辨率,论文主要对多光谱与全色图像融合算法进行了深入研究,通过大量的融合实验得到了一系列有价值的结论,完成了一定的创新性工作,具体的工作内容如下:
在多分辨率分析的特征匹配基础上,提出了一种基于Mallat小波变换与空间投影结合的图像配准算法。该算法采用投影匹配原理将二维数据变为一维进行匹配计算,降低了配准所需要的时间。另外,采用逐层细化的分层搜索策略可减少匹配误差从而提高配准精度。
在综合分析àtrous小波变换和Curvelet变换的优点基础上,提出了一种基于àtrous-Curvelet变换的融合算法。分解后的系数依据所在高,低频层的不同特点,采取多重加权规则进行融合。该算法能在保留多光谱图像光谱信息的基础上,有效地提高融合图像的空间分辨率。
针对遥感图像影像分辨率低的问题,提出了一种基于区域模糊推理的NSCT域融合算法。该算法有效地克服了传统融合方法中存在的融合图像模糊,抗噪能力差的缺点。
针对传统脉冲耦合神经网络(PCNN)模型参数无法自动设定的难题,结合lαβ彩色空间转换,提出了一种基于双通道自适应PCNN的图像融合算法。该算法充分考虑到像素间的相关性及噪声突变的影响,融合效果优于多尺度分析方法。
Remote sensing data have different spatial resolution, spectral resolution and time-phasic resolution. Image fusion technology can combine their respective advantages in order to make up for information loss of single image, enhance image information analysis capabilities, and improve target classification accuracy and dynamic monitoring range. For the some outstanding problems of multispectral and panchromatic fusion algorithm such as the conflict between improving spatial resolution and maintaining spectral quality, this thesis makes analysis and research from the pixel level, feature level and decision-making level, and then puts forward the corresponding solution. The main research content and innovative results are as follows:
1. In the aspect of image pre-processing, with regard to the difficulty of structure extract in registration algorithm, a novel image registration algorithm based on space projection in Mallat wavelet domain is proposed. As for low-frequency components, space projection character matching is used, and then the results of matching are applied in the high-frequency components to achieve coarse-fine matching, while as for the highest resolution component, normalized cross-correlation matching is used , finally the simulation results are given and analyzed. Experimental results show that according to space projection principle, the proposed algorithm convert two-dimensional data into one-dimensional 0-1 character string to matching comparison, which not only can reduce search space, but also greatly decline registration time. In addition, the hierarchical search strategy with layer by layer can reduce the matching error and improve registration accuracy. Compared with the common registration algorithms of cross-correlation and Hausdorff distance, the proposed algorithm is dominant both in the registration time and matching accuracy, which is ready for image fusion in the next phase.
2. In the aspect of pixel level fusion, with regard to low resolution of fusion image, two multi-scale decomposition tools—àtrous wavelet transform and discrete Curvelet transform are firstly introduced into image fusion field, and then with the advantages of translation invariance inàtrous wavelet transform and multi-orientation decomposition in Curvelet transform, a novel image fusion algorithm based onàtrous- Curvelet transform is proposed, which is combined with IHS color space conversion. Different weighted fusion rules are adopted according to coefficient features of high and low frequent layer. The conditional weighted fusion rules that regional characteristics product as active measurement and correlation coefficient as matching degree are adopted in high frequent section, while the average weighted rules are used in low frequent section. Finally, the fusion image can be achieved by IHS inverse transform. Experimental results show that the proposed algorithm can effectively improve spatial resolution of fusion image on the basic of retaining spectral information, and then fusion effect of this algorithm is better than that of other multi-resolution analysis algorithms. In addition, space and spectral quality usually depends on threshold selection, so choosing proper threshold should be based on different applications and characters of original images.
3. In the aspect of feature level fusion, the current fusion rules that the largest absolute value selection rule the weighted average rules have some disadvantages such as loss of fusion information and sensitivity to noise. In order to overcome these shortcomings and let fusion image contain much information of original images, a novel image fusion algorithm based on fuzzy reasoning in NSCT domain is proposed, which is combined with IHS color space conversion. Fusion rule setting of this algorithm is confirmed according to reginal features of NSCT transform coefficients, through the introduction of fuzzy reasoning principle to determine weighted value of the corresponding coefficients of original images. Experimental results show that the proposed algorithm both in suppressing spectral distortion and improving spatial quality is superior to the current fusion algorithms based on multi-resolution analysis, and then can overcome the shortcomings of poor anti-noise capability in traditional fusion rules. On the one hand, as a new multi-scale geometric transformation, NSCT has better direction selectivity and translation invariance, which can fully reflect image geometric information. On the other hand, adopting the weighted fuzzy reasoning fusion rules can effectively solve some uncertainties problems, and then these rules can be also extended to medical and other areas of image fusion.
4. In the aspect of decision-making level fusion, with regard to high computational complexity of multi-resolution analysis algorithm, a novel image fusion algorithm based on dual-channel adaptive PCNN is proposed. Firstly, the multispectral image is converted from RGB space to lαβspace that is more in line with color transmission character. Next, the achromatic channel (l )image and panchromatic image are adaptively decomposed by simplifying tralditional PCNN model and defining image definition as the coupled joint coefficient, and then the largest entropy ignition time series are sent to decision factor to achieve the new achromatic channel image. Finally, fusion image is acquired by lαβinverse transform onαcomponent,βcomponent of original multispectral image and the new achromatic channel component (l ). Experimental results show that the proposed algorithm can not only solve the difficult problem on how to set traditional PCNN parameters automatically, but also with view to the correlation among pixels set and noise impact, fusion effect of this algorithm is better than that of other mutiresoluion fusion algorithms such as wavelet transform both on subjective and objective evaluation. Meanwhile, this algorithm can reduce the computational complexity.
在多分辨率分析的特征匹配基础上,提出了一种基于Mallat小波变换与空间投影结合的图像配准算法。该算法采用投影匹配原理将二维数据变为一维进行匹配计算,降低了配准所需要的时间。另外,采用逐层细化的分层搜索策略可减少匹配误差从而提高配准精度。
在综合分析àtrous小波变换和Curvelet变换的优点基础上,提出了一种基于àtrous-Curvelet变换的融合算法。分解后的系数依据所在高,低频层的不同特点,采取多重加权规则进行融合。该算法能在保留多光谱图像光谱信息的基础上,有效地提高融合图像的空间分辨率。
针对遥感图像影像分辨率低的问题,提出了一种基于区域模糊推理的NSCT域融合算法。该算法有效地克服了传统融合方法中存在的融合图像模糊,抗噪能力差的缺点。
针对传统脉冲耦合神经网络(PCNN)模型参数无法自动设定的难题,结合lαβ彩色空间转换,提出了一种基于双通道自适应PCNN的图像融合算法。该算法充分考虑到像素间的相关性及噪声突变的影响,融合效果优于多尺度分析方法。
Remote sensing data have different spatial resolution, spectral resolution and time-phasic resolution. Image fusion technology can combine their respective advantages in order to make up for information loss of single image, enhance image information analysis capabilities, and improve target classification accuracy and dynamic monitoring range. For the some outstanding problems of multispectral and panchromatic fusion algorithm such as the conflict between improving spatial resolution and maintaining spectral quality, this thesis makes analysis and research from the pixel level, feature level and decision-making level, and then puts forward the corresponding solution. The main research content and innovative results are as follows:
1. In the aspect of image pre-processing, with regard to the difficulty of structure extract in registration algorithm, a novel image registration algorithm based on space projection in Mallat wavelet domain is proposed. As for low-frequency components, space projection character matching is used, and then the results of matching are applied in the high-frequency components to achieve coarse-fine matching, while as for the highest resolution component, normalized cross-correlation matching is used , finally the simulation results are given and analyzed. Experimental results show that according to space projection principle, the proposed algorithm convert two-dimensional data into one-dimensional 0-1 character string to matching comparison, which not only can reduce search space, but also greatly decline registration time. In addition, the hierarchical search strategy with layer by layer can reduce the matching error and improve registration accuracy. Compared with the common registration algorithms of cross-correlation and Hausdorff distance, the proposed algorithm is dominant both in the registration time and matching accuracy, which is ready for image fusion in the next phase.
2. In the aspect of pixel level fusion, with regard to low resolution of fusion image, two multi-scale decomposition tools—àtrous wavelet transform and discrete Curvelet transform are firstly introduced into image fusion field, and then with the advantages of translation invariance inàtrous wavelet transform and multi-orientation decomposition in Curvelet transform, a novel image fusion algorithm based onàtrous- Curvelet transform is proposed, which is combined with IHS color space conversion. Different weighted fusion rules are adopted according to coefficient features of high and low frequent layer. The conditional weighted fusion rules that regional characteristics product as active measurement and correlation coefficient as matching degree are adopted in high frequent section, while the average weighted rules are used in low frequent section. Finally, the fusion image can be achieved by IHS inverse transform. Experimental results show that the proposed algorithm can effectively improve spatial resolution of fusion image on the basic of retaining spectral information, and then fusion effect of this algorithm is better than that of other multi-resolution analysis algorithms. In addition, space and spectral quality usually depends on threshold selection, so choosing proper threshold should be based on different applications and characters of original images.
3. In the aspect of feature level fusion, the current fusion rules that the largest absolute value selection rule the weighted average rules have some disadvantages such as loss of fusion information and sensitivity to noise. In order to overcome these shortcomings and let fusion image contain much information of original images, a novel image fusion algorithm based on fuzzy reasoning in NSCT domain is proposed, which is combined with IHS color space conversion. Fusion rule setting of this algorithm is confirmed according to reginal features of NSCT transform coefficients, through the introduction of fuzzy reasoning principle to determine weighted value of the corresponding coefficients of original images. Experimental results show that the proposed algorithm both in suppressing spectral distortion and improving spatial quality is superior to the current fusion algorithms based on multi-resolution analysis, and then can overcome the shortcomings of poor anti-noise capability in traditional fusion rules. On the one hand, as a new multi-scale geometric transformation, NSCT has better direction selectivity and translation invariance, which can fully reflect image geometric information. On the other hand, adopting the weighted fuzzy reasoning fusion rules can effectively solve some uncertainties problems, and then these rules can be also extended to medical and other areas of image fusion.
4. In the aspect of decision-making level fusion, with regard to high computational complexity of multi-resolution analysis algorithm, a novel image fusion algorithm based on dual-channel adaptive PCNN is proposed. Firstly, the multispectral image is converted from RGB space to lαβspace that is more in line with color transmission character. Next, the achromatic channel (l )image and panchromatic image are adaptively decomposed by simplifying tralditional PCNN model and defining image definition as the coupled joint coefficient, and then the largest entropy ignition time series are sent to decision factor to achieve the new achromatic channel image. Finally, fusion image is acquired by lαβinverse transform onαcomponent,βcomponent of original multispectral image and the new achromatic channel component (l ). Experimental results show that the proposed algorithm can not only solve the difficult problem on how to set traditional PCNN parameters automatically, but also with view to the correlation among pixels set and noise impact, fusion effect of this algorithm is better than that of other mutiresoluion fusion algorithms such as wavelet transform both on subjective and objective evaluation. Meanwhile, this algorithm can reduce the computational complexity.
引文
[1] Llinas J, Edward W. Multisensor data fusion [M]. Boston: Artech House, 1990.
[2] J. L. Van Genderen, C. Pohl. Image fusion: issues, teehniques and applications [C]. Intelligent Image Fusion, Proe.of EARSeL Workshop, Strasbourg, Franee, 1994, 18-26.
[3] James M. Suiter, Mary Beth Lapis, Rockwell Collins, et al. Multispectral image fusion for the small aircraft transportation system [C]. 23rd Digital Avionics Systems Conference, 2004, 1: 4. B. 4-41-13.
[4] Uner M. K, Ramac L. C, Varshney P. K. Concealed weapon detection: An image fusion approach [C]. Proc. SPIE, 1997, 2942: 123-132.
[5] T. Taxt, A. H. S. Solberg. Information fusion in remote sensing [J]. Vistas in Astronomy, 1997, 41(3):337-342.
[6] Suomi K, Oikainen J, Jauhinen J. Medical image fusion [C]. Proceeding of the First Finnish Anti-Aliasing Symposium, 1998, 1: 44-51.
[7] C. Pohl, J.L.Van Genderen. Multisensor image fusion in remote sensing: concepts, methods and application [J]. Int. J. Remote Sensing, 1998, 19(5): 823-854.
[8] M.I.Smith, J. P. Heather. Review of image fusion technology in 2005[C]. Proc. SPIE, 2005, 5782: 29~45.
[9]覃征,鲍复民,李爱国,杨博,弓亚歌.数字图像融合[M].西安:西安交通大学出版社, 2004.
[10]郭雷,李晖晖,鲍永生.图像融合[M].北京:电子工业出版社, 2008.
[11] Hall D. L, Llinas J. An introduction to multisensor data fusion [C]. In Proceeding of the IEEE, 1997, 85(1): 6-23.
[12] Klein L. A. Sensor and data fusion concepts and applications [M]. Tutorial texts, 1993, 14, SPIE Optical Engineering Press, USA, 1994.
[13]敬忠良,肖刚,李振华.图像融合一理论与应用[M],北京:高等教育出版社, 2007.
[14]濮静娟.遥感图像目视解释原理与方法[M].北京:中国科学技术出版社, 1992.
[15]赵英时,等.遥感应用分析原理与方法[M].北京:科学出版社, 2003.
[16] Chavez P. S, Sides S. C, Anderson J. A. Comparison of three difference methods to merge multiresolution and multispectral data: Landsat TM and SPOT panchromatic [J]. Photogrametric Engineering and Remote Sensing, 1991, 57:295-303.
[17]何国金,李克鲁,胡德永,从柏林,张雯华.多卫星遥感数据的信息融合:理论、方法与实践[J].中国图象图形学报,1999,4A(9):744~750.
[18] Ehlers M. Multisensor fusion techniques in remote sensing [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1991, 46(3): 19-30.
[19]周前祥,敬忠良,姜世忠.不同光谱与空间分辨率遥感图像融合方法的理论研究[J].遥感技术应用, 2003,18(1):41-46.
[20] Carper W. J, Lillesand T. M, Kiefer R. W. The use of intensity-hue-saturation transformations for merging SPOT panchromatic and multispectral image data [J]. Photogrametric Engineering and Remote Sensing, 1990, 56:459-467.
[21] Kathleen E, Philip A D. The use of intensity-hue-saturation transformation for producing color shaded relief images [J]. Photogrametric Engineering and Remote Sensing, 1994, 60: 1369-1374.
[22] Chibani Y, Houacine A. The joint use of IHS transform and redundant wavelet decomposition for fusing multispectral and panchromatic images [J]. International Journal of Remote Sensing, 2002, 23(18):3821-3833.
[23] Gross H. N, Schott J. R. Application of spectral mixture analysis and image fusion techniques for image sharpening [J]. Remote Sensing of the Enviroment, 1998, 63: 85-94.
[24] Zhang Y. A new merging method and its spectral and spatial effects [J]. International Journal of Remote Sensing, 1999, 20(10): 2003-2014.
[25] Chavez P.S, Kwarteng A.Y. Extracting spectral contrast in Landsat thematic mapper image data using selective principal component analysis [J]. Photogrametric Engineering and Remote Sensing, 1989, 55: 339-348.
[26] Jia Y. H. Fusion of Landsat TM and SAR images based on principal component analysis [J]. Remote Sensing Technology and Application, 1998, 13(1): 46-49.
[27]王宏,敬忠良,李建勋.多分辨率图像融合的研究与发展[J].控制理论与应用, 2004, 21(1):145-151.
[28]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报, 2003, 31(12A): 1975-1981.
[29] Burt P. J, Adelson E.H. The Laplacian pyramid as a compact image code [J]. IEEE Trans. on Communications, 1983, 31(4):532-540.
[30] Toet A, Ruyven L. J. Valeton J. M. Merging thermal and visual images by a contrast pyramid [J]. Optical Engineering, 1989, 28(7):789-792.
[31] Burt P. J. A gradient pyramid basis for pattern selective image fusion [C]: Proc. of the Society for Information Display Conference. San Jose, USA: SID Press, 1992:467-470.
[32] Burt P. J, Kolczynski R.J. Enhanced image capture though fusion[C]: Proc. 4th Int. Conf. on Computer Vision, Berlin, Germany, 1993:173-182.
[33] Ranchin T, Wald L. The wavelet transform for the analysis of remotely sensed images. International Journal of Remote Sensing, 1993, 14(3):615-619.
[34] Li H, Manjunath B.S, Mitra S. Multisensor image fusion using the wavelet transform [J]. Graphical Models and Image Process, 1995, 57(3):235-245.
[35] Haihui Wang, Jiaxiong Peng, Wei Wu. A fusion algorithm of remote sensing image based on discrete wavelet packet [C]. Proceedings of Second International Conference on Matchine Learning and Cybernetics, Xi’an, 2003, 11: 2557-2562.
[36]强赞霞.遥感图像的融合及应用[D].华中科技大学博士论文, 2005.
[37]何贵青,郝重阳.特征量积和IHS变换的多源遥感图像融合方法[J].火力与指挥控制, 2006, 31(11): 88-90.
[38] J. Nùňez, X. Otazu, O. Fors, A. Prades, V. Palà, R. Arbiol. Multiresolution-based image fusion with additive wavelet decomposition [J]. IEEE Trans. Geosci. Remote Sens., 1999, 37(3): 1204-1211.
[39]吴艳,杨万海,李明.多光谱与高分辨率图像融合算法研究[J].光子学报, 2003, 32(2): 174-178.
[40] M.Gonzalez-audidana, X.Otazu, O.Fors, A.Seco. Comparison between Mallat’s and“àtrous”discrete wavelet transform based algorithms for the fusion of multispectral and panchromatic images [J]. International Journal of Remote Sensing, 2005, 26(3): 595-614.
[41] Zhang Z, Blum R S. A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application [C]. Proceeding of the IEEE, 1999, 87(8): 1315-1326.
[42] G. Piella. A general framework for multiresolution image fusion: from pixels to regions [J]. Information Fusion, 2003, 9: 259–280.
[43] Zhijun Wang, Djemel Ziou, Costas Armenakis, Deren Li, and Qingquan Li. A Comparative Analysis of Image Fusion Methods [J]. 2005, 43(6): 1391-1402.
[44] Nikolakopoulos, K.G. Comparision of four different fusion techniques for IKONOS data. Goescience and Remote Sensing Symposium [C], Proceeding. 2004 IEEE international, 2004, 4:2534-2537.
[45] Gonzalo Pajares, Jesús Manuel de la Cruz. A wavelet-based image fusion tutorial [J]. Pattern Recognition, 2007, 37: 1855-1872.
[46] Zhang Z, Blum R.S. A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application [C]. Proceedings of the IEEE, 1999, 87(8): 1315-1326.
[47] Donoho D.L. Orthonormal ridgelets and linear singularities [R]. Tech. Report, Department of Statistics, Stanford University, 1998.
[48] Candes E.J. Monoscale ridgelet for the representation of images with edges [R]. Dept. Statist, Standford, CA, Tech. Rep., 1999.
[49] Candès E. J, Donoho D. L. Curvelets-A surprisingly effective nonadaptive representation for objects with edges [M]. L L Schumaker, et al. Curves and Surfaces. Nashville: Vanderbilt University Press, 1999.
[50] Candès E J, Donoho D L. New tight frames of curvelets and optimal representations of objects with Piecewise-C2 singularities [J]. Comm. On Pure and Appl, 2004, 57:219-266.
[51] Pennec E L, Mallat S. Image compression with geometrical wavelets[C]. Proceeding of 8th IEEE Internationgal Conference on Image Processing, Vancouver, Canada,September, 2000:661-664.
[52] Do M N, Vetterli M. Contourlet: A directional multiresolution image representation [C]. Processings of IEEE International Conference on Image Processing, Rochester, 2002:357-360.
[53] Cunha A L, Zhou J P, Do M N, The Nonsubsampled Contourlet transform: theory, design, and applications [J]. IEEE Transactions on Image Processing, 2006, 15(10):3089-3101.
[54] Sharma R K, Leen T K, Pavel M. Probabilistic image sensor fusion [M]. Advance in Neural Information Processing Systems, The MIT Press, 1999, 11:824-830.
[55] Yang J, Blum R.S. A statistical signal processing approach to image fusion for concealed weapon detection [C]. IEEE International Conference on Image Processing, 2002, 1: 513-516.
[56] J. A. Jessler, A. O. Hero. Space-alternating generalized expectation maximization algorithm [J]. IEEE Trans. Signal Processing, 1994, 42(10): 2664-2677.
[57] Hakan Bakircioglu, Taskin Kocak. Survey of random neural network applications [J]. European Journal of Operational Research, 2000, 126:319-330.
[58] Zhang Zhaoli, Sun Shenghe, Zheng Fuchun. Image fusion based on median filter and SOFM neural networks: a three-step scheme [J]. Signal Processing, 2001, 81:1325-1330.
[59] Yiyao L, Venkatesh Y V, Ko C. C. A knowledge-based neural network for fusing edge maps of multisensory images [J]. Information Fusion, 2001, 2: 121-133.
[60] Schistad A. H, Jian A. K, Taxt T. Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images [J]. IEEE Trans. on Geoscience and Remote Sensing, 1994, 32(4):768-778.
[61] Zadeh L.A. Fuzzy sets [J]. Information and Control, 1965, (8):338-353.
[62] Colin N, Moruzzie M. Radar target recognition by fuzzy logic [C]. Proc Int Conf Fuzzy Systems, USA, 1997:257-262.
[63] Roux L, Desachy J. Information fusion for supervised classification in a satellite image [C]. Proc Int Conf Fuzzy Systems, USA, 1995:1119-1125.
[64]刘源.基于模糊信息处理的数据融合方法研究[D].西安电子科技大学博士论文, 1999.
[65] C. S. Xydeas, V petrovic. Objective image fusion performance measure [J]. Electronic Letters, 2000, 36(4): 308-309.
[66] Guihong Qu, Dali Zhang, Pingfan Yan. Information measure for performance of image fusion [J]. Electronic Letters, 2002, 38(7): 548-551.
[67] Ramesh C, Ranjith T. Fusion performance measures and a lifting wavelet transform based algorithm for image fusion [C]. Proceedings of 5th International Conference on Information Fusion, 2002, 1:317-320.
[68]韦志辉,程军.基于小波变换的一种新的图像质量评价方法[J].南京理工大学学报, 2000, 20(1):102-106.
[69] Qiang Wang, Yi Shen, Ye Zhang. A quantitative method to evaluating the performance of hyper spectral data fusion [C]. Proceedings of 19th IEEE Instrumentation and Measurement Technology Conference, Alaskan, USA, 2002,2:919-923.
[70] Xiao Gang, Jing Zhongliang, Wu Jianmin, Liu Congyi. Synthetically evaluation system for multi-source image fusion and experiment analysis [J]. Journal of Shanghai Jiaotong University, 2006, 11(3):263-270.
[71] Wald L, Ranchin T, Mangolinim. Fusion of satellite images of different spatial resolution, assessing the quality of resulting images [J]. Photogrammetric Engineering and Remote Sensing, 1997, 63(3):691-699.
[72]魏文忠.多光谱图像融合中配准技术的研究及小波应用[M].北京,北京理工大学出版社, 1995.
[73] L. G. Brown. A survey of image registration techniques[R]. ACM Comput. Surveys, 1992, 24(4):325-376.
[74] Leila M. G. Fonseca, Max H. M. Costa. Automatic registration of satellite images [J]. IEEE Computer Society, 1997:219-226.
[75] F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, P. Sutens. Multimodality image registration by maximization of mutual information [J]. IEEE Trans. Med. Imag., 1997, 16(2):187-198.
[76] Lewis J.P. Fast normalized cross-correlation [M], Industrial Light & Magic, Vision Interface, 1995.
[77]罗钟铉,刘成明.灰度图象匹配的快速算法[J].计算机辅助设计与图形学学报, 2005,17(5):966-970.
[78]张志佳,黄莎白,史泽林.新的基于边缘特征的图像相关匹配方法[J].红外与激光工程, 2003, 32(6):635-638.
[79] D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge. Comparing images using the Hausdorff distance [J], IEEE Trans. on Pattern Analysis and Machine Intelligence, 1993, 15:850-863.
[80] Averbuch A, Keller Y. FFT based image registration[C]. Proceedings of 2002 IEEE Internatinal Conference on Acoustics Speech and Signal Processing. USA IEEE, 2002, 4:3608-3611.
[81] Chen Q. S, Defrise M, Deconinck F. Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1994, 16(12):1156-1168.
[82] Jane You, Prabir Bhattacharya. A wavelet-based coarse-to-fine image matching scheme in a parallel virtual machine environment [J]. IEEE Trans. on Image Processing, 2000, 9(9):1547-1559.
[83] Yefeng Zheng, Doermann.D. Robust point matching for nonrigid shapes by preserving local neighborhood structures [J]. IEEE Trans. on PAMI, 2006, 28(4):643-649.
[84]陈鹰,林怡.基于提升小波的影像变换与匹配[J].测绘学报, 2006, 35(1):19-23.
[85] Mallat S. A theory for multiresolution signal decomposition: the wavelet representation [J]. IEEE Transaction on Pattern Analysis and machine Intelligence, 1989, 11(7): 674-693.
[86] Mallat S, Zhong S. Characterization of signals from multiscale edges [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(7): 710-732.
[87] Mallat S, Hwang W L. Singularity detection and processing with wavelets [J]. IEEE Transactions on Information Theory, 1992, 38(2): 617-643.
[88]孙远,周刚慧,赵立初,施鹏飞.灰度图像匹配的快速算法[J].上海交通大学学报,2000, 34(5):702-704.
[89] Fuh C.S, Liu H.B. Projection for pattern recognition [J], Image and Vision Computing, 1998, 16:677-687.
[90]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[J].计算机学报, 2004, 27(9):1278-1283.
[91] Lisa Gottesfeld Brown. A survey of image registration techniques. Department of Computer Science [M], Columbia University New York, 1992.
[92]张赞霞,彭嘉雄,王洪群.基于傅里叶变换的遥感图像配准算法[J].红外与激光工程, 2004, 33(4):385-387.
[93] T.Ranchin, L.Wald. Fusion of high spatial and spectral resolution images: the ARSIS concept and its implementation [J]. Photogram. Eng. Remote Sensing, 2000, 66(1): 49-61.
[94]陈武凡.小波分析及其在图像处理中应用[M].北京:科学出版社, 2002.
[95] M. Li, S. J.Wu. A new image fusion algorithm based on wavelet transforms [C]. Proc. of 5th International Conference on Computational Intelligence and Multimedia Applieations,2003,154-159.
[96] E.H.Zhang, C.H.Guo, Z.Z.Bian. Retinal image fusion based on wavelet transforms [C]. Proc. of 2nd International Conference on Machine Learning and Cyberneties, 2003, 2198-2201.
[97]肖刚,敬忠良, Henry Leung,王淑.基于小波统计特性的遥感图像像素与特征联合最优融合方法[J].遥感学报, 2005, 9(4):381-386.
[98] Chibani Y, Houacine A. On the use of the redundant wavelet transform for multisensory image fusion [C]. Proc. Int. Conf. on Electronics, Circuits and Systems, 2000:442-445.
[99]后斌,乔伟峰,孙在宏.基于IHS变换与àtrous小波分解的遥感影像融合[J].南京师大学报(自然科学版),2006, 29(1): 116-120.
[100]刘刚,敬忠良,孙韶媛,李建勋,李振华.基于多孔小波和模糊区域特征的图像融合方法[J].计算机工程, 2005, 31(16): 33-35.
[101] Y. F. Gu, Y. Liu, C Y. Wang, Y Zhang. Curvelet-based image fusion Algorithm for effective anomaly detection in hyperspectral imagery [J]. Journal of Physics:Conference Series 48, 2006, 324-328.
[102] L. Alparone, S. Baronti, A. Garzelli, F. Nencini. Remote sensing image fusion using the curvelet transforms [J]. International Journal on Information Fusion, Elsevier, 2007, 8(2):143-15.
[103]蒋年德,王耀南,毛建旭.基于Curvelet变换的遥感图像融合研究[J].仪器仪表学报, 2008, 29(1):61-66.
[104] Mallat S. Multiresolution approximations and wavelet orthonormal bases of L2(R) [J]. Transactions of the American Mathematical Society, 1989, 315(1): 69-87.
[105] Donoho D.L, Duncan M.R. Digital curvelet transform: strategy, implementation and experiments [C]. Proc. SPIE, 2000, 4056: 12-29.
[106] Candes E.J, Donoho D.L. Curvelets and curvilinear integrals [J]. Journal of Approximation Theory. 2001, 113:59-90.
[107] Candès E J, Demanet L, Donoho D L, et al. Fast discrete curvelet transforms. Appied and Computational Mathe ematics [R], Califormia Institute of Technology, 2005:1-43.
[108]李晖晖,郭雷,刘航.基于二代curvelet变换的图像融合研究[J].光学学报, 2006, 26(5): 657-662.
[109] Petrovic V, Xydeas C. Cross band pixel selection in multi-resolution image fusion [C]. Proc. of SPIE, 1999, 3719:319-326.
[110]李玲玲.像素级图像融合方法研究与应用[D].华中科技大学博士论文, 2005:111-118.
[111] G. Piella. A general framework for multiresolution image fusion: from pixels to regions [J]. Information Fusion, 2003, 9: 259–280.
[112]李晖晖,郭雷,刘航.基于梯度选取规则的小波变换在图像融合中的研究[J].计算机工程与应用, 2005, 12: 76-78.
[113]杨旭红,敬忠良,李建勋.基于影像局部光谱特征的遥感影像融合[J].计算机工程, 2005, 31(11):35-37.
[114] Ingrid Daubechies著,李建平,杨万年译.小波十讲[M].北京:国防工业出版社, 2004: 127-153.
[115] Zhang Z, Blum R.S. A region-based image fusion scheme for concealed weapon detection[C]. Proc. 31st Annu. Conf. Information Science and Systems, Baltimore, 1997:168-173.
[116] Liu Gang, Jing Zhongliang, Sun Shaoyuan, Li Jianxun. Region-based multisensor image fusion method [J]. Journal of Systems Engineering and Electronics. 2005, 16(3): 521-526.
[117] D R Barron, O D J Thomas. Image fusion through consideration of texture components [J]. Electronics Letters, 2001, 37(12):746-748.
[118]李光鑫,王珂,张立保.加权多分辨率图像融合的快速算法[J].中国图象图形学报, 2005, 10(12):1529-1536.
[119] Minh N Do, Martin Vetterli. The Contourlet transform: an efficient directional multiresolution image representation [J]. IEEE Trans. on Image Processing, 2004:1-16.
[120] Minh N Do, Martin Vetterli. Pyramidal directional filter banks and curvelets [C]. Proc. IEEE Int. Conf. on Image processing. Thessaloniki, Greece, 2001, 3:158-161.
[121]王耀南.智能信息处理技术[M].北京:高等教育出版社, 2003.
[122] Jocelyn C, Gilles M, Patrick L. Fuzzy fusion techniques for linear features detection in multitemporal SAR images [J]. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37(3): 1292-1305.
[123] Tuan D.P, Hong Y. Fusion of handwritten numeral classifiers based on fuzzy and genetic algorithms [C]. Proc. North America Fuzzy Information Processing Society, New York, 1997:257-262.
[124]沈景悦,吴秀清,刘严岩.一种基于模糊融合的遥感图像目标识别方法[J].计算机工程与应用, 2005, 41(16):83-85.
[125] Liu Gang, Jin Zhongliang, Sun Shaoyuan. Multiresolution image fusion scheme based on fuzzy region feature [J]. Journal of Zhejiang University. 2006, 7(2):117-122.
[126]强赞霞,彭嘉雄,王洪群.基于小波变换局部方差的遥感图像融合[J].华中科技大学学报(自然科学版), 2003, 31(6): 89-91.
[127]浦恬,方庆咭,倪国强.基于对比度的多分辨率图像融合[J].电子学报, 2000, 28(12):116-118.
[128] Dauphin G, Beghdadi A, De Lesegno P. V. A local directional bandlimited contrast [C]. Proceedings of 7th International Symposium on Signal Processing and Applicaions. Paris, France, 2003:197-200.
[129] Ying M S. Perturbation of fuzzy reasoning [J]. IEEE Trans. on Systems, 1999, 1(15):625-629.
[130] Yang Y. Y, Chiam T.C. Rule discovery based on rough set theory [J]. Proceedings of 3rd International Conference on Information Fusion. Electronics Letters, 2002, 38(7):313-315.
[131]陈蜜,李德仁,秦前清,贾永红.基于Contourlet变换的遥感影像融合算法[J].小型微型计算机系统, 2006, 27(11):2052-2555.
[132]张强,郭宝龙.基于非采样Contourlet变换的遥感图像融合算法[J].光学学报, 2008, 28(1):76-80.
[133] Ajith H Gunatilaka, Brian A Baertlein. Feature-level and decision-level fusion of noncoincidently sampled sensors for land mine detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2001, 23(6):80-87.
[134] Johnson J.L, Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for image [J]. Applied Optics, 1994, 33(26):6239-6253.
[135] Ranganath H.S, Kuntimad G. Image segmentation using pulse coupled neural networks [J]. IEEE World Congress on Computational Intelligence, 1994, 2:1285-1290.
[136]史飞.脉冲耦合神经网络在图像处理中的应用研究[D].兰州大学博士论文, 2003.
[137] Wei Li, Zhu Xuefeng. A new algorithm of multi-modality medical image fusion based on pulse coupled neural networks [C]. Proceedings of 1st International Conference on Natural Computation, 2005, 1:995-1001.
[138] Lindblad T, Kinser J.M. Image processing using pulse-coupled neural network [M]. Second Revised Edition. Berlin Heidelberg: Springer-Verlag, 2005.
[139] Wei Huang, Zhongliang Jing. Multi-focus image fusion using pulse coupled neural network [J]. Pattern Recognition Letters, 2007, 28(9):1123-1132.
[140] Eckhorn R. Neural mechanisms of scene segmentation: recordings from the visual cortex suggest basic circuits or linking field models [J]. IEEE Trans. on Neural Network, 1999, 10(3):464-479.
[141] Johnson J.L, Padgett M.L. PCNN models and applications [J]. IEEE Trans. on Neural Networks. 1999, 10(3):480-498.
[142] Kinser J.M. Recent research in pulse-coupled neural networks[C]. SPIE Areosense Conf., Orlan, FL, 1996.
[143] Ruderman D.L, Cronin T.W, Chiao C.C. Statistics of cone responses to natural images: implications for visual coding [J]. Journal of Optical Society of America, 1998, 15(8):2036-2045.
[144] Reinhard E, Ashikhmin M, Gooch B, Shirley P. Color Transfer between images [J]. IEEE Computer Graphics and Applications, 2001, 21(5):34-41.
[145] Welsh T, Ashikhmin M, Mueller K. Transferring color to grayscale images: ACM Trans. on Graphics: Proc. ACM SIGGRAPH [C], San Antonio, Texas, 2002, 21(3):277-280.
[146]苗启广,王宝树.基于局部对比度的自适应PCNN图像融合[J].计算机学报, 2008, 31(5):875-880.
[147] Wang Zhaobin, Ma Yide. Dual-channel PCNN and its application in the field of image fusion[C]. Proceedings of 3rd International Conference on Natural Computation, 2007, 1:755-759.
[148]李敏,蔡骋,谈正.基于修正PCNN的多传感器图像融合方法[J].中国图像图形学报, 2008, 13(2):284-290.
[149]苗启广,王宝树.一种自适应PCNN多聚焦图像融合新算法[J].电子信息学报, 2006, 28(3):466-470.
[150] Eltoukhy H. A, Kavusi S. A computationally efficient algorithm for multi-focus image reconstruction[C]. Proc. of SPIE Electronic Imaging, 2003:332-341.
[151] Kuntimad G, Ranganath H S. Perfect image segmentation using pulse coupled neural networks [J]. IEEE Transactions on Neural Networks, 1999, 10(3):591-598.
[152]刘勍,马义德,钱志柏.一种基于交叉熵的改进型PCNN图像自动分割新方法[J].中国图像图形学报, 2005, 10(5):579-584.
[2] J. L. Van Genderen, C. Pohl. Image fusion: issues, teehniques and applications [C]. Intelligent Image Fusion, Proe.of EARSeL Workshop, Strasbourg, Franee, 1994, 18-26.
[3] James M. Suiter, Mary Beth Lapis, Rockwell Collins, et al. Multispectral image fusion for the small aircraft transportation system [C]. 23rd Digital Avionics Systems Conference, 2004, 1: 4. B. 4-41-13.
[4] Uner M. K, Ramac L. C, Varshney P. K. Concealed weapon detection: An image fusion approach [C]. Proc. SPIE, 1997, 2942: 123-132.
[5] T. Taxt, A. H. S. Solberg. Information fusion in remote sensing [J]. Vistas in Astronomy, 1997, 41(3):337-342.
[6] Suomi K, Oikainen J, Jauhinen J. Medical image fusion [C]. Proceeding of the First Finnish Anti-Aliasing Symposium, 1998, 1: 44-51.
[7] C. Pohl, J.L.Van Genderen. Multisensor image fusion in remote sensing: concepts, methods and application [J]. Int. J. Remote Sensing, 1998, 19(5): 823-854.
[8] M.I.Smith, J. P. Heather. Review of image fusion technology in 2005[C]. Proc. SPIE, 2005, 5782: 29~45.
[9]覃征,鲍复民,李爱国,杨博,弓亚歌.数字图像融合[M].西安:西安交通大学出版社, 2004.
[10]郭雷,李晖晖,鲍永生.图像融合[M].北京:电子工业出版社, 2008.
[11] Hall D. L, Llinas J. An introduction to multisensor data fusion [C]. In Proceeding of the IEEE, 1997, 85(1): 6-23.
[12] Klein L. A. Sensor and data fusion concepts and applications [M]. Tutorial texts, 1993, 14, SPIE Optical Engineering Press, USA, 1994.
[13]敬忠良,肖刚,李振华.图像融合一理论与应用[M],北京:高等教育出版社, 2007.
[14]濮静娟.遥感图像目视解释原理与方法[M].北京:中国科学技术出版社, 1992.
[15]赵英时,等.遥感应用分析原理与方法[M].北京:科学出版社, 2003.
[16] Chavez P. S, Sides S. C, Anderson J. A. Comparison of three difference methods to merge multiresolution and multispectral data: Landsat TM and SPOT panchromatic [J]. Photogrametric Engineering and Remote Sensing, 1991, 57:295-303.
[17]何国金,李克鲁,胡德永,从柏林,张雯华.多卫星遥感数据的信息融合:理论、方法与实践[J].中国图象图形学报,1999,4A(9):744~750.
[18] Ehlers M. Multisensor fusion techniques in remote sensing [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1991, 46(3): 19-30.
[19]周前祥,敬忠良,姜世忠.不同光谱与空间分辨率遥感图像融合方法的理论研究[J].遥感技术应用, 2003,18(1):41-46.
[20] Carper W. J, Lillesand T. M, Kiefer R. W. The use of intensity-hue-saturation transformations for merging SPOT panchromatic and multispectral image data [J]. Photogrametric Engineering and Remote Sensing, 1990, 56:459-467.
[21] Kathleen E, Philip A D. The use of intensity-hue-saturation transformation for producing color shaded relief images [J]. Photogrametric Engineering and Remote Sensing, 1994, 60: 1369-1374.
[22] Chibani Y, Houacine A. The joint use of IHS transform and redundant wavelet decomposition for fusing multispectral and panchromatic images [J]. International Journal of Remote Sensing, 2002, 23(18):3821-3833.
[23] Gross H. N, Schott J. R. Application of spectral mixture analysis and image fusion techniques for image sharpening [J]. Remote Sensing of the Enviroment, 1998, 63: 85-94.
[24] Zhang Y. A new merging method and its spectral and spatial effects [J]. International Journal of Remote Sensing, 1999, 20(10): 2003-2014.
[25] Chavez P.S, Kwarteng A.Y. Extracting spectral contrast in Landsat thematic mapper image data using selective principal component analysis [J]. Photogrametric Engineering and Remote Sensing, 1989, 55: 339-348.
[26] Jia Y. H. Fusion of Landsat TM and SAR images based on principal component analysis [J]. Remote Sensing Technology and Application, 1998, 13(1): 46-49.
[27]王宏,敬忠良,李建勋.多分辨率图像融合的研究与发展[J].控制理论与应用, 2004, 21(1):145-151.
[28]焦李成,谭山.图像的多尺度几何分析:回顾和展望[J].电子学报, 2003, 31(12A): 1975-1981.
[29] Burt P. J, Adelson E.H. The Laplacian pyramid as a compact image code [J]. IEEE Trans. on Communications, 1983, 31(4):532-540.
[30] Toet A, Ruyven L. J. Valeton J. M. Merging thermal and visual images by a contrast pyramid [J]. Optical Engineering, 1989, 28(7):789-792.
[31] Burt P. J. A gradient pyramid basis for pattern selective image fusion [C]: Proc. of the Society for Information Display Conference. San Jose, USA: SID Press, 1992:467-470.
[32] Burt P. J, Kolczynski R.J. Enhanced image capture though fusion[C]: Proc. 4th Int. Conf. on Computer Vision, Berlin, Germany, 1993:173-182.
[33] Ranchin T, Wald L. The wavelet transform for the analysis of remotely sensed images. International Journal of Remote Sensing, 1993, 14(3):615-619.
[34] Li H, Manjunath B.S, Mitra S. Multisensor image fusion using the wavelet transform [J]. Graphical Models and Image Process, 1995, 57(3):235-245.
[35] Haihui Wang, Jiaxiong Peng, Wei Wu. A fusion algorithm of remote sensing image based on discrete wavelet packet [C]. Proceedings of Second International Conference on Matchine Learning and Cybernetics, Xi’an, 2003, 11: 2557-2562.
[36]强赞霞.遥感图像的融合及应用[D].华中科技大学博士论文, 2005.
[37]何贵青,郝重阳.特征量积和IHS变换的多源遥感图像融合方法[J].火力与指挥控制, 2006, 31(11): 88-90.
[38] J. Nùňez, X. Otazu, O. Fors, A. Prades, V. Palà, R. Arbiol. Multiresolution-based image fusion with additive wavelet decomposition [J]. IEEE Trans. Geosci. Remote Sens., 1999, 37(3): 1204-1211.
[39]吴艳,杨万海,李明.多光谱与高分辨率图像融合算法研究[J].光子学报, 2003, 32(2): 174-178.
[40] M.Gonzalez-audidana, X.Otazu, O.Fors, A.Seco. Comparison between Mallat’s and“àtrous”discrete wavelet transform based algorithms for the fusion of multispectral and panchromatic images [J]. International Journal of Remote Sensing, 2005, 26(3): 595-614.
[41] Zhang Z, Blum R S. A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application [C]. Proceeding of the IEEE, 1999, 87(8): 1315-1326.
[42] G. Piella. A general framework for multiresolution image fusion: from pixels to regions [J]. Information Fusion, 2003, 9: 259–280.
[43] Zhijun Wang, Djemel Ziou, Costas Armenakis, Deren Li, and Qingquan Li. A Comparative Analysis of Image Fusion Methods [J]. 2005, 43(6): 1391-1402.
[44] Nikolakopoulos, K.G. Comparision of four different fusion techniques for IKONOS data. Goescience and Remote Sensing Symposium [C], Proceeding. 2004 IEEE international, 2004, 4:2534-2537.
[45] Gonzalo Pajares, Jesús Manuel de la Cruz. A wavelet-based image fusion tutorial [J]. Pattern Recognition, 2007, 37: 1855-1872.
[46] Zhang Z, Blum R.S. A categorization of multiscale-decomposition-based image fusion schemes with a performance study for a digital camera application [C]. Proceedings of the IEEE, 1999, 87(8): 1315-1326.
[47] Donoho D.L. Orthonormal ridgelets and linear singularities [R]. Tech. Report, Department of Statistics, Stanford University, 1998.
[48] Candes E.J. Monoscale ridgelet for the representation of images with edges [R]. Dept. Statist, Standford, CA, Tech. Rep., 1999.
[49] Candès E. J, Donoho D. L. Curvelets-A surprisingly effective nonadaptive representation for objects with edges [M]. L L Schumaker, et al. Curves and Surfaces. Nashville: Vanderbilt University Press, 1999.
[50] Candès E J, Donoho D L. New tight frames of curvelets and optimal representations of objects with Piecewise-C2 singularities [J]. Comm. On Pure and Appl, 2004, 57:219-266.
[51] Pennec E L, Mallat S. Image compression with geometrical wavelets[C]. Proceeding of 8th IEEE Internationgal Conference on Image Processing, Vancouver, Canada,September, 2000:661-664.
[52] Do M N, Vetterli M. Contourlet: A directional multiresolution image representation [C]. Processings of IEEE International Conference on Image Processing, Rochester, 2002:357-360.
[53] Cunha A L, Zhou J P, Do M N, The Nonsubsampled Contourlet transform: theory, design, and applications [J]. IEEE Transactions on Image Processing, 2006, 15(10):3089-3101.
[54] Sharma R K, Leen T K, Pavel M. Probabilistic image sensor fusion [M]. Advance in Neural Information Processing Systems, The MIT Press, 1999, 11:824-830.
[55] Yang J, Blum R.S. A statistical signal processing approach to image fusion for concealed weapon detection [C]. IEEE International Conference on Image Processing, 2002, 1: 513-516.
[56] J. A. Jessler, A. O. Hero. Space-alternating generalized expectation maximization algorithm [J]. IEEE Trans. Signal Processing, 1994, 42(10): 2664-2677.
[57] Hakan Bakircioglu, Taskin Kocak. Survey of random neural network applications [J]. European Journal of Operational Research, 2000, 126:319-330.
[58] Zhang Zhaoli, Sun Shenghe, Zheng Fuchun. Image fusion based on median filter and SOFM neural networks: a three-step scheme [J]. Signal Processing, 2001, 81:1325-1330.
[59] Yiyao L, Venkatesh Y V, Ko C. C. A knowledge-based neural network for fusing edge maps of multisensory images [J]. Information Fusion, 2001, 2: 121-133.
[60] Schistad A. H, Jian A. K, Taxt T. Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images [J]. IEEE Trans. on Geoscience and Remote Sensing, 1994, 32(4):768-778.
[61] Zadeh L.A. Fuzzy sets [J]. Information and Control, 1965, (8):338-353.
[62] Colin N, Moruzzie M. Radar target recognition by fuzzy logic [C]. Proc Int Conf Fuzzy Systems, USA, 1997:257-262.
[63] Roux L, Desachy J. Information fusion for supervised classification in a satellite image [C]. Proc Int Conf Fuzzy Systems, USA, 1995:1119-1125.
[64]刘源.基于模糊信息处理的数据融合方法研究[D].西安电子科技大学博士论文, 1999.
[65] C. S. Xydeas, V petrovic. Objective image fusion performance measure [J]. Electronic Letters, 2000, 36(4): 308-309.
[66] Guihong Qu, Dali Zhang, Pingfan Yan. Information measure for performance of image fusion [J]. Electronic Letters, 2002, 38(7): 548-551.
[67] Ramesh C, Ranjith T. Fusion performance measures and a lifting wavelet transform based algorithm for image fusion [C]. Proceedings of 5th International Conference on Information Fusion, 2002, 1:317-320.
[68]韦志辉,程军.基于小波变换的一种新的图像质量评价方法[J].南京理工大学学报, 2000, 20(1):102-106.
[69] Qiang Wang, Yi Shen, Ye Zhang. A quantitative method to evaluating the performance of hyper spectral data fusion [C]. Proceedings of 19th IEEE Instrumentation and Measurement Technology Conference, Alaskan, USA, 2002,2:919-923.
[70] Xiao Gang, Jing Zhongliang, Wu Jianmin, Liu Congyi. Synthetically evaluation system for multi-source image fusion and experiment analysis [J]. Journal of Shanghai Jiaotong University, 2006, 11(3):263-270.
[71] Wald L, Ranchin T, Mangolinim. Fusion of satellite images of different spatial resolution, assessing the quality of resulting images [J]. Photogrammetric Engineering and Remote Sensing, 1997, 63(3):691-699.
[72]魏文忠.多光谱图像融合中配准技术的研究及小波应用[M].北京,北京理工大学出版社, 1995.
[73] L. G. Brown. A survey of image registration techniques[R]. ACM Comput. Surveys, 1992, 24(4):325-376.
[74] Leila M. G. Fonseca, Max H. M. Costa. Automatic registration of satellite images [J]. IEEE Computer Society, 1997:219-226.
[75] F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, P. Sutens. Multimodality image registration by maximization of mutual information [J]. IEEE Trans. Med. Imag., 1997, 16(2):187-198.
[76] Lewis J.P. Fast normalized cross-correlation [M], Industrial Light & Magic, Vision Interface, 1995.
[77]罗钟铉,刘成明.灰度图象匹配的快速算法[J].计算机辅助设计与图形学学报, 2005,17(5):966-970.
[78]张志佳,黄莎白,史泽林.新的基于边缘特征的图像相关匹配方法[J].红外与激光工程, 2003, 32(6):635-638.
[79] D. P. Huttenlocher, G. A. Klanderman, W. J. Rucklidge. Comparing images using the Hausdorff distance [J], IEEE Trans. on Pattern Analysis and Machine Intelligence, 1993, 15:850-863.
[80] Averbuch A, Keller Y. FFT based image registration[C]. Proceedings of 2002 IEEE Internatinal Conference on Acoustics Speech and Signal Processing. USA IEEE, 2002, 4:3608-3611.
[81] Chen Q. S, Defrise M, Deconinck F. Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1994, 16(12):1156-1168.
[82] Jane You, Prabir Bhattacharya. A wavelet-based coarse-to-fine image matching scheme in a parallel virtual machine environment [J]. IEEE Trans. on Image Processing, 2000, 9(9):1547-1559.
[83] Yefeng Zheng, Doermann.D. Robust point matching for nonrigid shapes by preserving local neighborhood structures [J]. IEEE Trans. on PAMI, 2006, 28(4):643-649.
[84]陈鹰,林怡.基于提升小波的影像变换与匹配[J].测绘学报, 2006, 35(1):19-23.
[85] Mallat S. A theory for multiresolution signal decomposition: the wavelet representation [J]. IEEE Transaction on Pattern Analysis and machine Intelligence, 1989, 11(7): 674-693.
[86] Mallat S, Zhong S. Characterization of signals from multiscale edges [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(7): 710-732.
[87] Mallat S, Hwang W L. Singularity detection and processing with wavelets [J]. IEEE Transactions on Information Theory, 1992, 38(2): 617-643.
[88]孙远,周刚慧,赵立初,施鹏飞.灰度图像匹配的快速算法[J].上海交通大学学报,2000, 34(5):702-704.
[89] Fuh C.S, Liu H.B. Projection for pattern recognition [J], Image and Vision Computing, 1998, 16:677-687.
[90]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[J].计算机学报, 2004, 27(9):1278-1283.
[91] Lisa Gottesfeld Brown. A survey of image registration techniques. Department of Computer Science [M], Columbia University New York, 1992.
[92]张赞霞,彭嘉雄,王洪群.基于傅里叶变换的遥感图像配准算法[J].红外与激光工程, 2004, 33(4):385-387.
[93] T.Ranchin, L.Wald. Fusion of high spatial and spectral resolution images: the ARSIS concept and its implementation [J]. Photogram. Eng. Remote Sensing, 2000, 66(1): 49-61.
[94]陈武凡.小波分析及其在图像处理中应用[M].北京:科学出版社, 2002.
[95] M. Li, S. J.Wu. A new image fusion algorithm based on wavelet transforms [C]. Proc. of 5th International Conference on Computational Intelligence and Multimedia Applieations,2003,154-159.
[96] E.H.Zhang, C.H.Guo, Z.Z.Bian. Retinal image fusion based on wavelet transforms [C]. Proc. of 2nd International Conference on Machine Learning and Cyberneties, 2003, 2198-2201.
[97]肖刚,敬忠良, Henry Leung,王淑.基于小波统计特性的遥感图像像素与特征联合最优融合方法[J].遥感学报, 2005, 9(4):381-386.
[98] Chibani Y, Houacine A. On the use of the redundant wavelet transform for multisensory image fusion [C]. Proc. Int. Conf. on Electronics, Circuits and Systems, 2000:442-445.
[99]后斌,乔伟峰,孙在宏.基于IHS变换与àtrous小波分解的遥感影像融合[J].南京师大学报(自然科学版),2006, 29(1): 116-120.
[100]刘刚,敬忠良,孙韶媛,李建勋,李振华.基于多孔小波和模糊区域特征的图像融合方法[J].计算机工程, 2005, 31(16): 33-35.
[101] Y. F. Gu, Y. Liu, C Y. Wang, Y Zhang. Curvelet-based image fusion Algorithm for effective anomaly detection in hyperspectral imagery [J]. Journal of Physics:Conference Series 48, 2006, 324-328.
[102] L. Alparone, S. Baronti, A. Garzelli, F. Nencini. Remote sensing image fusion using the curvelet transforms [J]. International Journal on Information Fusion, Elsevier, 2007, 8(2):143-15.
[103]蒋年德,王耀南,毛建旭.基于Curvelet变换的遥感图像融合研究[J].仪器仪表学报, 2008, 29(1):61-66.
[104] Mallat S. Multiresolution approximations and wavelet orthonormal bases of L2(R) [J]. Transactions of the American Mathematical Society, 1989, 315(1): 69-87.
[105] Donoho D.L, Duncan M.R. Digital curvelet transform: strategy, implementation and experiments [C]. Proc. SPIE, 2000, 4056: 12-29.
[106] Candes E.J, Donoho D.L. Curvelets and curvilinear integrals [J]. Journal of Approximation Theory. 2001, 113:59-90.
[107] Candès E J, Demanet L, Donoho D L, et al. Fast discrete curvelet transforms. Appied and Computational Mathe ematics [R], Califormia Institute of Technology, 2005:1-43.
[108]李晖晖,郭雷,刘航.基于二代curvelet变换的图像融合研究[J].光学学报, 2006, 26(5): 657-662.
[109] Petrovic V, Xydeas C. Cross band pixel selection in multi-resolution image fusion [C]. Proc. of SPIE, 1999, 3719:319-326.
[110]李玲玲.像素级图像融合方法研究与应用[D].华中科技大学博士论文, 2005:111-118.
[111] G. Piella. A general framework for multiresolution image fusion: from pixels to regions [J]. Information Fusion, 2003, 9: 259–280.
[112]李晖晖,郭雷,刘航.基于梯度选取规则的小波变换在图像融合中的研究[J].计算机工程与应用, 2005, 12: 76-78.
[113]杨旭红,敬忠良,李建勋.基于影像局部光谱特征的遥感影像融合[J].计算机工程, 2005, 31(11):35-37.
[114] Ingrid Daubechies著,李建平,杨万年译.小波十讲[M].北京:国防工业出版社, 2004: 127-153.
[115] Zhang Z, Blum R.S. A region-based image fusion scheme for concealed weapon detection[C]. Proc. 31st Annu. Conf. Information Science and Systems, Baltimore, 1997:168-173.
[116] Liu Gang, Jing Zhongliang, Sun Shaoyuan, Li Jianxun. Region-based multisensor image fusion method [J]. Journal of Systems Engineering and Electronics. 2005, 16(3): 521-526.
[117] D R Barron, O D J Thomas. Image fusion through consideration of texture components [J]. Electronics Letters, 2001, 37(12):746-748.
[118]李光鑫,王珂,张立保.加权多分辨率图像融合的快速算法[J].中国图象图形学报, 2005, 10(12):1529-1536.
[119] Minh N Do, Martin Vetterli. The Contourlet transform: an efficient directional multiresolution image representation [J]. IEEE Trans. on Image Processing, 2004:1-16.
[120] Minh N Do, Martin Vetterli. Pyramidal directional filter banks and curvelets [C]. Proc. IEEE Int. Conf. on Image processing. Thessaloniki, Greece, 2001, 3:158-161.
[121]王耀南.智能信息处理技术[M].北京:高等教育出版社, 2003.
[122] Jocelyn C, Gilles M, Patrick L. Fuzzy fusion techniques for linear features detection in multitemporal SAR images [J]. IEEE Trans. on Geoscience and Remote Sensing, 1999, 37(3): 1292-1305.
[123] Tuan D.P, Hong Y. Fusion of handwritten numeral classifiers based on fuzzy and genetic algorithms [C]. Proc. North America Fuzzy Information Processing Society, New York, 1997:257-262.
[124]沈景悦,吴秀清,刘严岩.一种基于模糊融合的遥感图像目标识别方法[J].计算机工程与应用, 2005, 41(16):83-85.
[125] Liu Gang, Jin Zhongliang, Sun Shaoyuan. Multiresolution image fusion scheme based on fuzzy region feature [J]. Journal of Zhejiang University. 2006, 7(2):117-122.
[126]强赞霞,彭嘉雄,王洪群.基于小波变换局部方差的遥感图像融合[J].华中科技大学学报(自然科学版), 2003, 31(6): 89-91.
[127]浦恬,方庆咭,倪国强.基于对比度的多分辨率图像融合[J].电子学报, 2000, 28(12):116-118.
[128] Dauphin G, Beghdadi A, De Lesegno P. V. A local directional bandlimited contrast [C]. Proceedings of 7th International Symposium on Signal Processing and Applicaions. Paris, France, 2003:197-200.
[129] Ying M S. Perturbation of fuzzy reasoning [J]. IEEE Trans. on Systems, 1999, 1(15):625-629.
[130] Yang Y. Y, Chiam T.C. Rule discovery based on rough set theory [J]. Proceedings of 3rd International Conference on Information Fusion. Electronics Letters, 2002, 38(7):313-315.
[131]陈蜜,李德仁,秦前清,贾永红.基于Contourlet变换的遥感影像融合算法[J].小型微型计算机系统, 2006, 27(11):2052-2555.
[132]张强,郭宝龙.基于非采样Contourlet变换的遥感图像融合算法[J].光学学报, 2008, 28(1):76-80.
[133] Ajith H Gunatilaka, Brian A Baertlein. Feature-level and decision-level fusion of noncoincidently sampled sensors for land mine detection [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2001, 23(6):80-87.
[134] Johnson J.L, Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for image [J]. Applied Optics, 1994, 33(26):6239-6253.
[135] Ranganath H.S, Kuntimad G. Image segmentation using pulse coupled neural networks [J]. IEEE World Congress on Computational Intelligence, 1994, 2:1285-1290.
[136]史飞.脉冲耦合神经网络在图像处理中的应用研究[D].兰州大学博士论文, 2003.
[137] Wei Li, Zhu Xuefeng. A new algorithm of multi-modality medical image fusion based on pulse coupled neural networks [C]. Proceedings of 1st International Conference on Natural Computation, 2005, 1:995-1001.
[138] Lindblad T, Kinser J.M. Image processing using pulse-coupled neural network [M]. Second Revised Edition. Berlin Heidelberg: Springer-Verlag, 2005.
[139] Wei Huang, Zhongliang Jing. Multi-focus image fusion using pulse coupled neural network [J]. Pattern Recognition Letters, 2007, 28(9):1123-1132.
[140] Eckhorn R. Neural mechanisms of scene segmentation: recordings from the visual cortex suggest basic circuits or linking field models [J]. IEEE Trans. on Neural Network, 1999, 10(3):464-479.
[141] Johnson J.L, Padgett M.L. PCNN models and applications [J]. IEEE Trans. on Neural Networks. 1999, 10(3):480-498.
[142] Kinser J.M. Recent research in pulse-coupled neural networks[C]. SPIE Areosense Conf., Orlan, FL, 1996.
[143] Ruderman D.L, Cronin T.W, Chiao C.C. Statistics of cone responses to natural images: implications for visual coding [J]. Journal of Optical Society of America, 1998, 15(8):2036-2045.
[144] Reinhard E, Ashikhmin M, Gooch B, Shirley P. Color Transfer between images [J]. IEEE Computer Graphics and Applications, 2001, 21(5):34-41.
[145] Welsh T, Ashikhmin M, Mueller K. Transferring color to grayscale images: ACM Trans. on Graphics: Proc. ACM SIGGRAPH [C], San Antonio, Texas, 2002, 21(3):277-280.
[146]苗启广,王宝树.基于局部对比度的自适应PCNN图像融合[J].计算机学报, 2008, 31(5):875-880.
[147] Wang Zhaobin, Ma Yide. Dual-channel PCNN and its application in the field of image fusion[C]. Proceedings of 3rd International Conference on Natural Computation, 2007, 1:755-759.
[148]李敏,蔡骋,谈正.基于修正PCNN的多传感器图像融合方法[J].中国图像图形学报, 2008, 13(2):284-290.
[149]苗启广,王宝树.一种自适应PCNN多聚焦图像融合新算法[J].电子信息学报, 2006, 28(3):466-470.
[150] Eltoukhy H. A, Kavusi S. A computationally efficient algorithm for multi-focus image reconstruction[C]. Proc. of SPIE Electronic Imaging, 2003:332-341.
[151] Kuntimad G, Ranganath H S. Perfect image segmentation using pulse coupled neural networks [J]. IEEE Transactions on Neural Networks, 1999, 10(3):591-598.
[152]刘勍,马义德,钱志柏.一种基于交叉熵的改进型PCNN图像自动分割新方法[J].中国图像图形学报, 2005, 10(5):579-584.