摘要
多源图像融合技术是以图像为研究对象的信息融合,隶属于多源信息融合范畴内的一个重要分支--可视信息融合,是一种综合了传感器理论、模数信号转换、数字图像处理、计算机视觉以及人工智能等多种学科的现代高新技术,在军事应用和民用等众多领域都有着广泛的应用。近年来,基于变换域的多分辨率分解的像素级图像融合算法被广泛应用在多源图像融合领域中,有效地克服了空间域中的频谱失真问题,并取得了较好的效果。
本论文在前人对像素级多源图像融合的研究工作的基础上,在多尺度变换的图像融合中,针对应用广泛的小波变换对二维图像中视觉效果最突出的大量曲线和曲面的奇异性不能最优的表示,只能用点奇异去逼近线面奇异,造成图像的轮廓、纹理等特征的模糊的缺点,研究了具有多尺度、多方向、各向异性和平移不变性的一种超完备的多尺度变换方法--非采样Contourlet变换(NonsubsampledContourlet Transform,NSCT)。而后以NSCT为基础,主要对红外和可见光图像融合与多聚焦图像融合的融合算法进行研究,并且在Matlab7.5和VC++6.0工具上对提出的所有算法进行了验证。
本论文的主要工作可以总结为以下五点:
1.深入研究具有具有多尺度、多方向、各向异性和平移不变性的非采样Contourlet变换理论,并且通过仿真实验呈现了NSCT变换对图像进行分解和重构的效果,构建了NSCT用于图像融合的算法框架和具体步骤。
2.针对多源图像融合领域中的红外和可见光图像融合,提出了一种有效的基于改进OTSU区域分割和非采样Contourlet变换相结合的红外和可见光图像融合算法。根据红外和可见光成像传感器的成像特性,对源图像进行区域分割和图像的联合区域表示,再针对各区域的NSCT分解系数设计相应的融合规则的方法,实现了系数的最优化融合,有效的提高了红外和可见光融合图像的质量。
3.通过对非负矩阵分解(Non-negative Matrix Factorization, NMF)的理论分析,深入研究了投影梯度非负矩阵分解理论(Projected Gradient Non-negative MatrixFactorization,PGNMF)并将其引入图像融合中,仿真实验的融合结果表明PGNMF不管是直接用于源图像融合还是用于NSCT分解后的低频系数融合规则中,都能够得到较好效果的融合图像,并且减小了算法的计算复杂度和耗时,使得其用于对图像质量要求不是很高而对实时性有要求的快速图像融合算法中成为可能。而且分别对红外和可见光图像、多聚焦图像两类不同传感器组合的图像进行融合实验,也在一定程度上体现了该算法的鲁棒性。
4.通过对粒子群优化算法的理论研究,针对其存在的早熟收敛和粒子缺乏多样性而导致陷入局部最优的问题,借鉴了人工免疫中的克隆选择学说的思想,提出了一种改进克隆选择的免疫粒子群算法(Improve Clonal Selection ParticalSwarm Optimization,ICSPSO),进而将其成功的应用在多聚焦图像融合领域,将图像融合问题转化为融合质量最优化的问题,很大程度上提高了融合图像的可靠性和融合效果,较好的融合效果和低时间消耗使得ICSPSO融合算法成为一种高效的快速图像融合算法。
5.将压缩感知理论引入高分辨率图像融合中,提出了压缩感知的融合算法与压缩感知和NSCT相结合的融合算法,实验结果表明将这两种基于压缩感知的图像融合算法用于高分辨率图像融合,在牺牲微小的图像质量的前提下可以大幅度的降低融合算法的耗时,所以压缩感知理论的引入,为高分辨率图像融合给予了一种具有可行性的低耗时方法。
The multi-source image fusion technique take the image as the object of study inthe information fusion field, one of the most important branches of the Multi-sourceinformation fusion-Visual Information Fusion. It s a mordern high-tech combinedsensor theory, analog to digital signal conversion, digital image processing, computervision, artificial intelligence and many other disciplines, has been widely used inmany range of areas such as military and civilian applications. In recent years, themulti-resolution decomposition based on transform domain pixel-level image fusionalgorithms have widely used in the field of multi-source image fusion, effectivelyovercomed the spatial spectrum distortion and have obtained the better effect.
In this dissertation, on the basis of the previous pixel-level multi-source imagefusion algorithms research, in the field of multi-scale image fusion, we found that thewidely used method which called wavelet transform has some limitations. It cannoteffectively represent the most prominent visual effects such as the line discontinuities and the curve discontinuities in the two-dimensional image, and onlyuse the singular points to approximate the singular lines or curved surfaces. Thislimitation resulted in the mistiness of the profile and texture in the image. Therefore,aim at the wavelet s limitations, the research works in this dissertation focus onan overcomplete multi-scale transformation method-the nonsubsampled contourlettransform (NSCT) which has property such as multi-scale, multi-direction, anisotropyand translational invariance.Then we primarily research with the infrared and visiblelight image fusion algorithm and the multi-focus image fusion algorithm, moreover all the proposed algorithms are verified by Matlab7.5and VC++6.0tools.
The main contributions of this dissertation can be summarized in the followingfive points:
1. In-depth and comprehensive research with the nonsubsampled contourlettransform theory which has property such as multi-scale, multi-direction, anisotropyand translational invariance. After that we present the effects of the simulationexperiment in image decomposition and reconstruction with NSCT. At last weconstructed the framework and specific steps of the image fusion algorithms usedNSCT.
2. Aiming at the infrared and visible light image fusion in the field ofmulti-source image fusion, we propose one kind of effective infrared and visible lightimage fusion algorithm which combined the improved OTSU regional segmentationand NSCT. On the basis of the characteristic of infrared and visible light imagesensors, regional segmentation and regional association are used in the source imagesat first, and then project the corresponding fusion rules to the NSCT decompositioncoefficients in different regions. This fusion algorithm achieved a most optimizedfusion method of the coefficients and effectively improved the quality of the infraredand visible light fused image.
3. By theoretical analyzed the non-negative matrix factorization (NMF) theory,we detailed study on the projected gradient non-negative matrix factorization(PGNMF) and introduced it to the image fusion field. Experimental results indicatethat PGNMF either directly used in the source image fusion or used in the fusion rulesof NSCT decomposition low-frequency coefficient, it s able to reduce thecomputational complexity and time-consuming, when acquire manifest better fusedimage at the same time. Therefore, the proposed fusion algorithm can be used forreal-time image fusion system which called for less quality requirement of fusedimage. Moreover, we take both of the infrared and visible light image and themulti-focus image to experiment with the proposed fusion algorithm, to some extent,reflect the robustness of the algorithms.
4. By theoretical analyzed the particle swarm optimization (PSO) theory, wefound that PSO method is likely to converge prematurely and the lack of particlediversity lead the swarm to converge to the local optimum. Aimed at the disadvantageof PSO, combined with the artificial immune clonal selection theory, we proposed animproved clonal selection particle swarm optimization (ICSPSO), and the improvedalgorithm had application in multi-focus image fusion field successfully. The fusionalgorithm not only transforms the image fusion question as the optimization problemsbut also enhanced the fused image reliability and the fusion effect to a great extent.The better fusion effect and the lower time consumption causes ICSPSO fusionalgorithm to become one kind of effective fast image fusion algorithm.
5. Introduced the compressed sensing (CS) theory to the image fusion field andproposed a new high-resolution image fusion algorithm based on CS. We alsocombined the CS and NSCT to resolve the high-resolution image fusion problem.Experimental results indicate that under the premise of slightly reducing the quality offused image, the proposed algorithm can greatly reduce the time-consuming. Therefor,the high-resolution image fusion algorithm based on compressed sensing is feasibleand effective, also can greatly reduce the time-consuming of the algorithm.
引文
[1] Kokar M, Kim K. Review of Multisensor Data Fusion Architecture andTechniques[C]. Proceedings of the International Symposium on Intelligent Control.Chicago USA.1993,261-266.
[2] Zhang Z, Blum R S. A categorization of multiscale-decomposition-based imagefusion scheme with a performance study for a digital cameraapplication[J].Proceedings of the IEEE,1999,87(8):1315-1326.
[3] Varshney P K. Multi-sensor data fusion[J].Electronics and CommunicationEnginering Journal,1997,9(12):245-253.
[4] Park J H, Kim K K, Yang Y K. Image Fusion Using Multiresolution Analysis[C].Geosciences and Remote Sensing Symposium,2001,2:709-711.
[5] Pohl C, Van Genderen J L. Multisensor image fusion in remote sensing: concepts,methods and applications[J].International Journal of Remote sensing,1998,19(5):823-854.
[6] S P Constantinos, M S Pattichis, E Micheli-Tzanakou. Medical imaging fusionapplications: An overview[C].Conference Record of the35th Asilomar Conference onSignals Systems and Computers,2001,2:1263-1267.
[7] Z Wang, D Ziou,C Armenakis, et al A comparative analysis of image fusionmethods[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(6):1391-1402.
[8] Yuan-Tsung Chen, Ming-Shi Wang. Three-dimensional reconstruction and fusionfor multi-modality spinal images[J].Computerized Medical Imaging andGraphics,2004,28(1):21-31.
[9] D D Sworder, J E Boyd, G A Clapp. Image fusion for tracking manoeuvringtargets[J].International Journal of Systems Science,1997,28(1):1-14.
[10] Kwak Keun Chang, Pedrycz Witold. Face recognition: A study in informationfusion using fuzzy integral[J].Pattern Recognition Letters,2005,26(6):719-733.
[11] Lipchen Alex Chan, Sandor Z Der, Nasser M Nasrabadi. Dualband FLIR fusionfor automatic target recognition[J].Information Fusion,2003,4(1):35-45.
[12] Mark E, Olszewski, Andreas Wahle, Steven C Mitchell, et al. Segmentation ofintravascular ultrasound images: a machine learning approach mimicking humanvision[C]. International Congress Series,2004,1268:1045-1049.
[13] C Nasel. Visualization of intracranial vessel anatomy using high resolution MRIand a simple image fusion technique[J].European Journal of Radiology,2005,54(1):107-111.
[14] L Wald. Some terms of reference in data fusion[J].IEEE Transactions onGeoscience and Remote Sensing,1999,37(3):1190-1193.
[15] A Bastiere. Methods for multisensor classification of airborne targets integratingevidence theory[J].Aerospace Science and Technology,1998,2(6):401-411.
[16] Hazim Kemal Ekenel, Bulent Sankur. Multiresolution face recognition[J].Imageand Vision Computing,2005,23(5):469-477.
[17] Daily M I, Farr T, Elachi C. Geologic interpretation from composited radar andLandsat imagery[J]. Photogrammetric Engineering and Remote Sensing,1979,45(8):1109-1106.
[18] G.Cliche,F.Bonn,P.Teillet.Intergration of the SPOT Pan.channel into itsmultispectral mode for image sharpness enhancement[J].PhotogrammetricEngineering and Remote Sensing.1985,51:311-316.
[19] Burt P J, Adelson E H. The Laplacian pyramid as a compact image code[J]. IEEETransactions on Communications,1983,31(4):532-540.
[20] Burt P J. The pyramid as a structure for efficient computation[C].In:Multiresolution Image Processing and Analysis, London: Springer-Verlag,1984,6-35.
[21] Ranchin T, Wald L. The wavelet transform for the analysis of remotely sensedimages[J].International Journal of Remote Sensing,1993,14(3):615-619.
[22] William F Herriington, Jr, Berthold K P Horn, et al. Application of the discretehaar wavelet transform to image fusion for nighttime driving[C].2005IEEEIntelligent Vehicles Symposium.2005:273-277.
[23] E J Pennec, S Mallat. Image Compression with geometrical wavelets[A]. In Proc.Of ICIP2000[C]. Vancouver, Canada, September,2000:661-664.
[24] E J Candes. Momoscale Ridgelets for the Representation of Image with Edges[R].USA: Department of Statisitics, Stanford University,2000.
[25] M N Do, M Vetterli. Contourlet[A]. J Stoeckler, G V Welland. Beyond Wavelets
[C]. Academic Press,2002.
[26] Eslami R, Radha H. Wavelet based contourlet transform and its application toimage coding[A]. IEEE International Conference on Image Processing[C]. Singapor,2004.3189-3192.
[27] CUNHA A L, ZHOU J P, DO M N. The nonsubsampled Contourlet transform:theory, design and applications[J]. IEEE Trans on Image Processing,2006,15(10):3089-3101.
[28] http://nightvision.com/news/news_detail.asp?news_ID=24.
[29]http://www.baesystems.com/Newsroom/NewsReleases/2007/autoGen_10772913162.html.
[30] http://www.thalesfist.com.
[31]http://www.flightinternational.com/falanding_168251.htm.
[32]http://www.mod.uk/dpa/projects/fres/.
[33] G K Matsopoulos, S Marshall. Application of morphological pyramids: Fusion ofMR and CT phantoms. Journal of Visual Communication and Image Representation,1995,6(2):196-207.
[34]周前样,敬忠良,姜世忠.不同光谱和空间分辨率遥感图像融合方法的理论研究.遥感技术与应用.2003.18(1):41-46
[35] Haihui Wang. A New Multiwavelet-Based Approach to Image Fusion[J].Journalof Mathematical Imaging and Vision,2004,21(2):177-192.
[36] Quan H Y, Yang Y, Song N H, et al. An image fusion approach based on secondgeneration wavelet transform[J].System Engineering and Electronics,2001,23(5):74-79.
[37] Zhaobin Wang, Yide Ma. Medical image fusion using m-PCNN[J].Informationfusion,9(2008):176-185.
[38]许廷发,秦庆旺,倪国强.基于MD642融合系统的à trous小波实时图像融合算法[J].光学精密工程,2008,16(10):2045-2050.
[39] Jiang X Y, Gao Z Y, Zhou L W. Multispectral image fusion using wavelettransform[J].Acta Electronica Sinica,1997,8(25):105-108.
[40] Yang X, Yang W H, Pei J H. Different focus points images fusion basedon wavelet decomposition[J].Acta Electronica Sinica,2001,29(6):846-848.
[41] Min Li, Wei Cai, Zheng Tan. A region-based multi-sensor image fusion schemeusing pulse-coupled neural networks[J].Pattern Recognition Letters,27(2006):1948-1956.
[42] Qu Xiaobo, Yan Jingwen, Xiao Hongzhi, et al. Image fusion algorithm based onspatial frequency-motivated pulse coupled neural networks in nonsubsampledcontourlet transform domain[J].Acta Automatic Sinica,2008,34(12):1508-1514.
[43] Song Yajun, Gao Kun, Ni Guoqiang, Lu Rong. Implementation of real-timeLaplacian pyramid image fusion processing based on FPGA[C]. Proc of SPIE,2007,6833(683316):1-8.
[44] Wei Huang, Zhongliang Jing. Evaluation of focus measures in multi-focus imagefusion[J].Pattern Recognition Letters,28(2007):493-500.
[45] Wang Qiang, Ni Guoqiang, Chen Bo. An image fusion of quincunx samplinglifting scheme and small time DSP-based system[C].Proc of SPIE,2007,6833(683317):1-10.
[46] Wenzhong Shi, ChangQing Zhu, Yan Tian, et al. Wavelet-based image fusion andquality assessment[J].International Journal of Applied Earth Observation andGeoinformation,2005,6(3):241-251.
[47] Zhenhua Li, Zhongliang Jing, Xuhong Yang, et al. Color transfer based remotesensing image fusion using non-separable wavelet frame transform[J].PatternRecognition Letters,2005,26(13):2006-2014.
[48] Qiguang Miao, Baoshu Wang. A novel image fusion method using WBCT andPCA[J].Chinese Optics Letters,2008,6(2):104-107.
[49] Yun Zhang, Gang Hong. An IHS and wavelet integrated approach to improvepan-sharpening visual quality of natural colour IKONOS and QuickBirdimages[J].Information Fusion,2005,6(3):225-234.
[50] Li Xin, Ni Guoqiang, Chen Xiaomei. The Realization of Real-Time ImageFusion System with Multi-DSP[C].Proceedings of SPIE,2002,4925:369-375.
[51] Eltoukhy H A, Kavusi S. A computationally efficient algorithm for multi-focusimage reconstruction[C].Proceedings of SPIE Electronic Imaging,2003,332-341.
[52] Shetigara V., A generalised component substitution technique for spatialenhancement of multispectral image using a higher resolution data set[J].Photogrammetric Engineering and Remote Sensing.1992,58(5):561-567.
[53] Jia Y H. Fusion of Landsat TM and SAR images based on principal componentanalysis[J].Remote Sensing Technology and Application,1998,13(1):46-49.
[54] Toet A, Walraven J. New false color mapping for image fusion. OpticalEngineering,1996,35(3):650-658.
[55] Waxman A M, Fay D A, Gove A N, et al.. Color night vision: fusion ofintensified visible and thermal IR imagery. Synthetic Vision for Vehicle Guidance andControl, Proceedings of SPIE,1995,2463:58-68.
[56]倪国强,戴文,李勇量,等.基于响尾蛇双模式细胞机理的可见光/红外图像彩色融合技术的优势和前景展望.北京理工大学学报,2004,24(2):95-100.
[57] Geng B. Y., Xu J. Z., Yang J. Y. An approach based on the features of space-frequency domain for fusion of edge maps obtained through multisensors [J]. SystemsEngineering and Electronics.2002,22(4):18-22.
[58] Smith S, Scarff L A. Combining visual and IR images for sensor fusion: twoapproaches[C].Proceedings of SPIE,1992,1668:102-112.
[59] W A Wright, F Bristol. Quick Markov random field image fusion[C].Proceedingsof SPIE,1998,3374:302-308.
[60] R Azencott, B Chalmond, F Coldefy. Markov fusion of a pair of noise images todetect intensity valleys[J].International Journal of Computer Vision,1995,16(2):135-145.
[61] Sharma R.K.,Leen T.K.,Pavel M.Bayesian sensor image fusion using local lineargenerative models[J].Optical Engineering,2001,40(7):1364-1376.
[62] R.K.Sharma,M.Pavel.Adaptive and statistical image fusion[J].Society forInformation Display,1996.XXVII:969-972.
[63] J.M.Lafert,F.Heitz,P.Perez,et al..Hierarchical statistical models for the fusion ofmultiresolution image data[C].Proceedings of the International Conference onComputer Vision.Cambridge,USA.1995.908-913.
[64] WaldL. An EuroPean proposal forterms of referenee in data fusion. InternationalArchives of Photogrammetry and Remote Sensing.1998,XXXII(7):651-654.
[65] Kam M.Rorres C,Chang W,Zhu X. Performance and geometric interpretation fordecision fusion with memory. IEEE Transactions on Systems, Man, and Cybernetic2Part A:Systems and Humans,1999,29(2):52-62.
[66] Jeon B, Landgrebe D A. Decision fusion approach for multitemporalclassifieation. IEEE Transactions on Geoscience and Remote Sensing(Special Issueon Data Fusion),1999,37(3):1227-1233.
[67] Li Shutao, Kwok James T, Wang Yaonan. Multi-focus image fusion usingartificial neural networks[J].Pattern Recognition Letters,2002,23(8):985-997.
[68] Zhang Z L, Sun S H, Zheng F C. Image fusion based on median filters andSOFM neural networks: a three-step scheme[J].Signal Processing,2001,81(6):1325-1330.
[69] Li S T, Kwork J T, Wang Y N. Multifocus image fusion using artificialnetworks[J].Pattern Recognition Letters,2002,23:985-997.
[70] Gail A Carpenter, Siegfried Martens, Ogi J Ogas. Self-organizing informationfusion and hierarchical knowledge discovery: a new framework using ARTMAPneural networks[J].Neural Networks,2005,18(3):287-295.
[71]苗启广,王宝树.一种自适应PCNN多聚焦图像融合新方法[J].电子与信息学报,2006,28(3):466-470.
[72] Wei Huang, Zhong Liang-jing. Multi-focus image fusion using pulse coupleneural networks[J]. Pattern Recognition Letters,2007,28(9):1123-1132.
[73] Qu Xiaobo, Yan Jing-wen. Image Fusion Algorithm Based on SpatialFrequency-Motivated Pulse Coupled Neural Networks in Nonsubsampled ContourletTransform Domain[J]. Acta Automatica Sinica.2008,34(12):1509-1514.
[74] Toet A.Image fusion by a ratio of low-pass pyramid.Pattern Recognition Letters,1989,9(4):245-253.
[75] Toet A,Ruyven L J,Valeton J M.Merging thermal and visual images by a contrastpyramid.Optical Engineering,1989,28(7):789-792.
[76] Toet A.Multiscale contrast enhancement with applications to image fusion.Optical Engineering,1992,31(5):1026-1031.
[77] Matsopoulos G K,Marshall S.Application of morphological pyramids:fusion ofMR and CT phantoms.Journal of Visual Communication and Image Representation,1995,6(2):196-207.
[78] Petrovic V S,Xydeas C S.Gradient-based multiresolution image fusion.IEEETransactions on Image Processing,2004,13(2):228-237.
[79] Liu Z,Tsukada K,Hanasaki K,et al..Image fusion by using steerable pyramid.Pattern Recognition Letters,2001,22:929-939.
[80] Liu G,Jing Z L,Sun S Y,et al.Image fusion based on expectation maximizationalgorithm and steerable pyramid.Chinese Optics Letters,2004,2(7):386-389.
[81] Mallat S G, A Theory for Multiresolution Signal Decomposition: The WaveletRepresentation[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1989,11(7):674-693.
[82]彭玉华.小波变换与工程应用[M].北京:科学出版社,2003,1-108.
[83]孙延奎.小波分析及其应用[M].北京:机械工业出版社,2005,1-260.
[84] Yansun Xu, J B Weaver, D M Healy, et al. Wavelet Transform Filters: A SpatiallySelective Noise Filtration Technique[J].IEEE Transactions on Image Processing,1994,3(6):747-758.
[85] Quan Pan, Lei Zhang, Guanzhong Dai, et al. Two Denoising Methods byWavelet Transform[J]. IEEE Transaction on Signal Processing,1999,47(12):3401-3406
[86] A. Lewis, G. Knowles. Image Compressing Using the2-D WaveletTransform[J].IEEE Transaction on Image Processing,1992,1(2):244-250.
[87] Ranchin T,Wald L.The wavelet transform for the analysis of remotely sensedimages. International Journal of Remote Sensing,1993,14(3):615-619.
[88] Li H,Manjunath B S,Mitra S K.Multisensor image fusion using the wavelettransform. Graphical Models and Image Processing,1995,57(3):235-245.
[89] Nunez J,Otazu X,Fors O,et al..Multiresolution-based image fusion with additivewavelet decomposition.IEEE Transactions on Geoscience and Remote Sensing,1999,37(3):1204-1211.
[90] Li S T,Kwork J T,Wang Y N.Using the discrete wavelet frame transform to mergeLandsat TM and SPOT panchromatic images.Information Fusion,2002,3:17-23.
[91] Li Z H,Jing Z L,Yang X H,et al..Color transfer based remote sensing imagefusion using non-separable wavelet frame transform.Pattern Recognition Letters,2005,26(13):2006-2014.
[92] Petrovic V S.,Xydeas C S.Cross-band pixel selection in multiresolution imagefusion. Proceedings of SPIE,1999,3719:319-326.
[93] Pu T,Ni G.Contrast-based image fusion using the discrete wavelet transform.Optical Engineering,2000,39(8):2075-2082.
[94]王洪华,杜春萍.基于多进制小波的多源遥感影像融合.中国图象图形学报:A辑,2002,7(4):341-345.
[95] Wu J,Huang H L,Tian J W,et al..Remote sensing image data fusion based on localdeviation of wavelet packet transform.In:IEEE7th International Symposium onAutonomous Decentralized Systems,Chengdu,China,2005,372-377.
[96]张登荣,张宵宇,愈乐,等.基于小波包移频算法的遥感图像融合技术.浙江大学学报(工学版),2007,41(7):1098-1100.
[97] Lewis J J,O Callaghan R J,Nikolov S G,et al.Pixel and region based image fusionwith complex wavelets.Information Fusion,2007,8(2):119-130.
[98] Miao Qiguang, Wang Baoshu. A novel image fusion method using Contourlettransform[C].2006International Conference On Communications, Circuits andSystems Proceedings, Guilin1,2006:548-552.
[99] Miao Qiguang, Wang Baoshu. The Contourlet for image fusion[C].Proc of SPIE,2006,6264(62640Z):1-8.
[100]李光鑫,王珂.基于Contourlet变换的彩色图像融合算法[J].电子学报,2007,35(1):112-117.
[101] Yajun Song, Kun Gao, Guoqiang Ni. A novel infrared image fusion algorithmbased on Contourlet transform[C].Proc of SPIE,2007,6835(68351P):1-8.
[102] M J Shensa. The discrete wavelet transform: Wedding the àtrous and mallatalgorithm[J].IEEE Transactions on Signal Processing,1992,40(10):2464-2482.
[103] Zhou J P, Cunha A L, Do M N. Nonsubsampled contourlet transform:Construction and application in enhancement[C].In: IEEE Int Conf on Image Proc,Genoa, Italy,2005,469-472.
[104] Candes E.J..Ridgelet:theory and applications.PH.D.dissertation.Stanford Univ,1998.9.
[105] Miao Qiguang, Wang Baoshu. A novel algorithm of image fusion using finiteRidgelet transform[C].Proc of SPIE,2006,6242(62420Y):1-8.
[106] Kun Liu, Lei Guo, Weiwei Chang, et al. algorithm of image fusion based onfinite Ridgelet transform[C].Proc of SPIE,2007,6786(67860D):1-7.
[107] Candès E J,Donoho D L. Curvelets-a surprisingly effective nonadaptiverepresentation for objects with edges. Curves and Surfaces[M].Nashville:VanderbiltUniversity Press,2000
[108] Myungjin Choi, Rae Young Kim, Myeong-Ryong Nam, et al. Fusion ofmultispectral and panchromatic Satellite images using the curvelet transform[J].IEEETransaction on Geoscience and Remote Sensing Letters,2005,2(1):136-140.
[109]李晖晖,郭雷,刘航.基于第二代Curvelet变换的图像融合研究[J].光学学报,2006,26(5):657-662.
[110] Filoppi Nencini, Andrea Garzelli, Stefano Baronti, et al. Remote sensing imagefusion using the curvelet transform[J].Information Fusion,2007,8:143-156.
[111] Chengzhi Deng, Hanqiang Cao, Chao Cao, et al. Multisensor image fusionusing fast discrete curvelet transform[C].Proc of SPIE,2007,6790(679004):1-9.
[112] Pennec E. Le.,Stephone Mallat. Image compression with geometricalwavelets[A]. In Proc. Of ICIP2000[C].Academic Press,2002.
[113] Xiaobo Qu, Jingwen Yan, Guofu Xie, et al. A novel image fusion based onbandelet transform[J].Chinese Optics Letters,2007,5(10):569-572.
[114]韩崇昭,朱洪艳,段战胜.多源信息融合[M].北京:清华大学出版社,2006,364-423.
[115]洪日昌.多源图像融合算法及应用研究[D]:[博士学位论文].合肥:中国科技大,2007.
[116]汤磊.多分辨率图像融合方法与技术研究[D]:[博士学位论文].南京:中国人民解放军理工大学,2008.
[117]陈浩.基于多尺度变换的多源图像融合技术研究[D]:[博士学位论文].长春:中国科学院长春光学精密机械与物理研究所,2010.
[118] DO M.N,Vetterli M. Framing pyramids[J].IEEE Trans. Signal Proc.,2003,51(9):2329-2342.
[119] Park S.,Smith M.J.T,Mersereau R.M..A new directional filterbank for imageanalysis and classification[J].IEEE Int.Conf.Acoust.,Speech,and Signal Proc.,1999:1417-1420.
[120] M J Shensa. The discrete wavelet transform: Wedding the àtrous and mallatalgorithm[J].IEEE Transactions on Signal Processing,1992,40(10):2464-2482.
[121] Do M. N. Directional Multiresolution Image Representations. Department ofCommunication Systems, Swiss Federal Institute of Technology Lausanne,2001.
[122] Otsu. A threshold selection method from gray level histogram. IEEE Trans onSMC29,1979,9(3):62-66.
[123]王国有,邹玉兰,凌勇.基于显著性的OSTU局部递归分割算法[J].华中科技大学学报,2002,30(9):57-59.
[124]屈小波,闫敬文,杨贵德.改进拉普拉斯能量和的尖锐频率局部化Contourlet域多聚焦图像融合方法[J].光学精密工程,2009,17(5):1203-1211.
[125] D.D.Lee, H.S.Seung. Learning the parts of objects by non-negative matrixfactorization [J]. Nature,1999,401(6755):788-791.
[126] D.D.Lee, H.S.Seung. Algorithms for non-negative matrix factorization [C]. In:Advances in Neural Information Processing Systems13, Denver,2000.556-562
[127]李乐,章毓晋.非负矩阵分解算法综述[J].电子学报,2008,36(4):737-743.
[128] D Donoho,V Stodden.When does non-negative matrix factorization give acorrect decomposition into parts[A].Adv in Neur Inform Proc Syst[C].Cambridge:MIT Press,2004.1141-1148.
[129] Stan Z. Li,Hou X W,Zhang H J et al. Learning spatially localized, parts-basedrepresentation. In: Proceedings of IEEE Computer Society Conference on ComputerVision and Pattern Recognition.2001,1:207-212.
[130] P.0.Hoyor.Non-negative matrix factorization with sparseness constraints[J].Journal of Machine Learning Researeh,2004,(5):1457-1469.
[131] P.0.Hoyor. Non-negative Sparse Coding[J]. Neural Networks for SignalProeessing,2002,XII:557-565.
[132] X.R. Pu, Z. Yi, Z. Ziming, et.al. Face Recognition Using Fisher Non-negativeMatrix Factorization with Sparseness Constraints[C].Lecture Notes in ComputerScience,2005,3497:112-117.
[133] Guillamet D.,Vitria J.,Schiele B..Introducing a weighted non-negtive matrixfactorization for image classification[C]. Pattern Recogniton Letters,2003,24(14):2447-2454.
[134] C. Ding, T. Li,W. Peng, H. Park. Oethogonal non-negative matrix t-factorizationfor clustering[J]. Proceedings of the12th ACM SIGKDO international conference2006.
[135] M. Catral, L. Han, M. Neummlll, R. J. Plemmons. On reduced ranknon-negative factorization for symmetric non-negative matrices[J]. Linear Algebraand its applications,2004,393:107-126.
[136] Y. Xue, C. S. Tong, Y. Chen, W. S. Chen. Clustering-based initialization fornon-negative matrix factorization[J]. Applied Mathematics and Computation.2008,205(2):525-536.
[137] C. Boutsidis, E. Gallopoulo. SVD based initialization: A head start fornon-negative matrix factorization[C]. Pattern Recogniton,2008,41(4):1350-1362.
[138] Edward F. Gonzales, Yin Zhang. Accelerating the Lee-Seung algorithm fornon-negative matrix factorization. Technical report, Department of Computational andApplied Mathematics, Rice University,2005.
[139] Lin C J. Projected gradient methods for non-negative matrix factorization [J].Neural Computation,2007,19(10):2756-2779.
[140] Piella G., Heijmans H. A new quality metric for image fusion. In:IEEEInternational Conference on Image Processing,2003:173-176.
[141] Fabien Scalzo,George Bebis,Mircea Nicolescu,Leandro Loss,EvolutionaryLearning of Feature Fusion Hierarchies[C],IEEE ICPR2008,Dec.2008,1-4.
[142] Michael A. Zmuda, Mateen M. Rizki, Louis A. Tambunino, Hybrid evolutionarylearning for synthesizinig multi-class parttern recognition systems[J].Applied softcomputing,Volume2, Issue4,2003.2,269-282.
[143] Cheng S, Hwang C. Optimal approximation of linear systems by a differentialevolution algorithm[J]. IEEE Transction. System, Man Cybernate.A,2001,31(6):698-707.
[144] J.Kennedy, R. C. Eberhart. Particle swarm optimization[C]. Proceeding of theIEEE International Conference on Neural Networks,1995,pp.1942–1947.
[145] Shi Y, R. C. Eberhart. A Modified Particle Swarm Optimizer[C]. In:Proceedings of the IEEE International Conference on Evolutionary Computation.Piscataway, NJ: IEEE Press,1998,69-73.
[146] J.Kennedy, R. C. Eberhart. Swarm intelligence[M]. San MATEO, CA:MorganKaufmann,2001.
[147] T. Ray, K. M. Liew. A swarm metaphor for multiobjective designoptimization[J]. Engineering Optimization,2002,34(2):141-153.
[148] C. A. Coello, G. T. Pulido, M. S. Lechuga. Handing multiple objectives withparticle swarm optimization[J]. IEEE Transactions on Evolutionary Computation,2004,8(3):256-279.
[149] Shi Y, Eberhart R C. A Modified Particle Swarm Optimizer. In: Proceedings ofthe IEEE International Conference on Evolutionary Computation. Piscataway, NJ:IEEE Press,1998,69-73.
[150] Clerc M. The Swarm and the Queen: Towards a Deterministic and AdaptiveParticle Swarm Optimization. In: Proc.1999Congress on Evolutionary Computation.Washington, DC, Piscataway, NJ:IEEE Service Center,1999,1951-1957.
[151] Suganthan P N. Particle Swarm Optimizer with Neighborhood Operator. In:Proceedings of the1999Congress on Evolutionary Computation. Piscataway, NJ,IEEE Service Center,1999,1958-1962
[152] Kennedy J. Small Worlds and Mega-minds: effects of neighborhood topologyon particle swarm performance.1931-1938.1999. Piscataway, NJ, IEEE ServiceCenter. Proc. Congress on Evolutionary Computation1999.
[153] Swagatam Das, Amit KonarUday, K. Chakraborty. Improving particle swarmoptimization with differentially perturbed velocity, Electronics&Telecom Eng Dept,Jadavpur University,2005.
[154] Storn, R., Price, K. Differential evolution–A simple and efficient heuristic forglobal optimization over continuous spaces, Journal of Global Optimization,11(4)(1997)341–359.
[155] Dasqupta D, Forrest S. Artificial immune systems in industrial applications.Proc. of the Second International Conference on Intelligent Processing andManufacturing of Materials. New York: IEEE Press,1999:257-267.
[156] Gasper A, Collard P. From Gas to artificial immune systems: Improvingadaptation in time dependent optimization. Proc. of the Congress on EvolutionaryComputations,1999,3:1859-1866.
[157]丁永生,任立红.人工免疫系统:理论与应用.模式识别与人工智能,2000,13(1):52-59.
[158] Burnet F M. The Clonal Selection Theory of Acquired Immunity
[M].Cambridge University Press,1959.
[159] DeCastro L N, Zuben V. Learning and optimization using the clonal selection.issue on Artificial Immune System (AIS),2002,6(3):239-251.
[160] E.Candès, J.Romberg, T.Tao,“Robust uncertainty principles: Exact signalrecognition from highly incomplete frequency information”, IEEE Trans. Info. Theory,2006,52(2):489-509.
[161] D.Donoho,“Compressed sensing”, IEEE Trans. Info. Theory,2006,52(4):1289-1306.
[162] E.Candès, T.Tao,“Near optimal signal recovery from random projections:Universal encoding strategies?” IEEE Trans. Info. Theory,200652(12):5406-5425.
[163] M.Elad, Optimized projections for compressed sensing. IEEE Trans. SignalProc,2007,55(12):5695-5702.
[164] L.Applebanm, etc, Chirp sensing codes: deterministic compressed sensingmeasurements for fast recovery. Applied and Computational Harmonic Analysis,2009,26:283-290.
[165] A.Herman, T.Strohmer, General deviants: an analysis of perturbations incompressed sensing. IEEE Journal Selected Topics in Signal Proc,2010,4(2):342-349.
[166] J.Ma, Compressed sensing by inverse scale space and curvelet thresholding.Applied Mathematics and Computation.2008,206:980-988.
[167] S.Chretien, An alternatingl1approach to the compressed sensing problem.IEEE Signal Proc.lett.2010,17(2):181-184.
[168] E.Candès, M.Wakin, S.Boyd, Enhancing sparsity by reweightedminimization. J. Fourier Anal. Application,2008,14:877-905.
[169] J.Jin, Y.Gu, S.Mei. A stochastic gradient approach on compressive sensingsignal reconstruction based on adaptive filtering framework. IEEE Journal SelectedTopics in Signal Proc,2010,4(2):409-420.
[170] T.Blumensath, M.E.Davies, Iterative hard thresholding for compressed sensing.Appl. Comput. Harmon.Anal,2009,27:265-274.
[171] H.Ranbnt, etc, Compressed sensing and redundant dictionaries. IEEE Trans.Info. Theory.2008,54(5):2210-2219.
[172] E.Candès, Y.C.Eldar, etc, Compressed sensing with coherent and redundantdictionaries. Appl. Comput. Harmon. Anal. in press,2010.
[173] G.Deyre, Best basis compressed sensing. IEEE Trans. Signal Proc.2010,58(5):2613-2622.
[174] M.Raginsky, etc, Compresed sensing performance bounds under Poisson noise.IEEE Trans.Signal Proc.2010,58(8):3990-4002.
[175] R.G.Baraniuk, etc, Model-based compressive sensing. IEEE Trans. Info.Theory.2010,56(4):1982-2001.
[176] A.Herman, T.Strohmer, High-resolution radar via compressed sensing. IEEETrans. Signal Proc,2009,57(6):2275-2284.
[177] H.G.Euder, On compressive sensing applied to radar. Signal Proc,2010,90:1402-1414.
[178] C.Potter, T.Parker, Sparsity and compressed sensing in radar imaging.Proceedings of the IEEE,2010,98(6):1006-1020.
[179] M.Lustig, D.Donoho, J.M.Danly, Sparse MRI: the application of compressedsensing for rapid MR imaging, Magn. Reson. Med.2007,58:1182-1195.
[180] M.Lustig, etc, Compressed sensing MRI, IEEE Signal Proc Magazine,2008,3:72-82.
[181] D.Gao, etc, A robust image transmission scheme for wireless channels based onCS. ICIC2010, LNAI6216,334-341.
[182] A.Majumdar, K.Ward. Compressed sensing of color images. Signal Proc.2010,90:3122-3127.
[183] D.J.Holland, etc, Reducing data acquisition times in phase-encoded velocityimaging using compressed sensing. Journal of Magnetic Resonance.2010,203:236-246.
[184] A.Makalanobis, R.Muise, Object specific image reconstruction using acompressive sensing architecture for application in surveillance systems. IEEE Trans.Aerospace and Electronic Systems.2009,45(3):1167-1180.
[185] D.Giacobello, etc, Retrieving sparse patterns using a compressed sensingframework: applications to speech coding based on sparse linear prediction. IEEESignal Proc. Lett.2010,17(1):103-106.
[186] M.Mishali, Y.C.Eldar, Blind multiband signal reconstruction: compressedsensing for analog signals. IEEE Trans. Signal Proc.2009,57(3):993-1009.
[187] C.R.Berger, etc, Application of compressive sensing to sparse channelestimation. IEEE. Communication Magazine.2010,10:164-174.
[188] E. J. Candes and T. Tao. Near optimal signal recovery from random projections:Universal encoding strategies [J]. IEEE Trans. Info. Theory.2006,52(12):5406-5425.
[189] G Peyr. Best Basis compressed sensing[J]. Lecture Notes in Computer Science,2007,4485:80-91.
[190] D. L. Donoho, X. Huo. Uncertainty principles and ideal atomic decompositions[J]. IEEE Trans. Inform Theory,2001,47(7):2845-2862.
[191] R. Gribonval, M. Nielsen. Sparse decompositions in unions of bases[J]. IEEETransactions on Information Theory,2003,49(12):3320-3325.
[192] R. G. Baraniuk. Compressive Sensing[J].Signal Processing Magazine, IEEE,2007,24(4):118-121.
[193] L. Gan. Block compressed sensing of natural images,15th InternationalConference on Digital Signal Processing, pp.403-406,2007.
[194] J. P. Xu, Y. M. Pi, Z. J. Cao. Optimized projection matrix for compressivesensing, Eurasip Journal on Advances in Signal Processing,2010.
[195] Y. Tsaig, D. L. Donoho. Extensions of compressed sensing, Signal Processing,Vol.86, No.3, pp.549-571,2006.
[196] Chen S B, Donoho D L, Saunders M A. Atomic decomposition by basispursuit[J]. SIAM Journal on Scientific Computing,1998,20(1):33-61.
[197] Donoho D L, Tsaig Y. Fast Solution of l1-Norm Minimization Problems Whenthe Solution May Be Sparse[R].Technical Report, Department of Statistics, StanfordUniversity, USA,2008.
[198] Figueiredo Mario A.T., Nowak Robert D., Wright Stephen J. Gradientprojection for sparse reconstruction: Application to compressed sensing and otherinverse problems[J].IEEE Journal on Selected Topics in Signal Processing,2007,1(4):586-597.
[199] D. Needell, D. Vershynin. Uniform uncertainty principle and signal recovery viaregularized orthogonal matching pursuit. Foundations of Compitational Mathematics,2009,9(3):317-334.
[200] Marco F. Duarte, Mark A. Davenport, Dharmpal Takhar, et al. Single-PixelImaging via Compressive Sampling[J].IEEE SIGNAL PROCESSING MAGAZINE,2008,(3):83-91.
[201] D Takhar, J Laska,M Wakin, etc. A new compressive imaging cameraarchitecture using optical domain compression [A].Proceedings of SPIE[C].Bellingham WA: International Soci2ety for Optical Engineering.2006,6065.
[202] M Lustig, J M Santos, D L Donoho, etc. Kt SPARSE: High frame rate dynamicMRI exploiting spatiotemporal sparsity[A]. Proceedings of the14th Annual Meetingof ISMRM[C]. Seattle, Washington.2006.242022443.