多聚焦图像融合研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
多聚焦图像融合作为图像融合的一个重要分支,正日益广泛地应用于机器视觉、目标识别、数码相机等领域。该技术旨在能从针对同一场景不同聚焦的图像中提取出聚焦区域融合成所有目标对象都是清晰的。现实应用中,一些光学镜头往往不能使同一场景多个目标都在同一聚集区域,这种情况下致使图像不是全面清晰的。这就产生了如何从多幅图像中融合出全面清晰图像的问题。因此对多聚焦图像融合技术开展研究有着重要意义。
     本文主要在多聚焦图像的融合现有研究成果的基础上做了进一步的研究。研究主要内容如下:
     1、研究了基于PCA分块结合高通滤波的多聚焦图像融合算法。依据多聚焦图像的特征结合PCA,探讨了一种新的清晰度指标,并以此为基础上讨论了图像融合算法。
     2、研究了基于焦点区域检测的多聚焦图像融合算法。利用像素与邻域内像素方差判断清晰与否,在此基础上讨论了焦点区域的检测的图像融合算法。
     3、以小波变换为基础,针对图像的低频部分的融合进行了研究,由此探讨了基于低频边缘特征和能量特征的融合规则。
     4、研究了基于空域和频域的图像融合的基础上,探讨了一种基于图像分块和小波变换的多聚焦图像融合算法。
a image with sufficient information by integrating the sharply focused regions seen in the different images need to be considered. So it is valuable for studying multi-focus image fusion.
     Multi-focus image fusion is the main topic in this paper. Some results obtained are improved and perfected. The work of this paper includes four parts as follows:
     1. We have investigated the multi-focus image fusion algorithm based on PCA and high-pass filtering. A definition index is discussed according to multi-focus image feature and PCA.Finally,the algorithm given is simulated.
     2. A scheme based on focus region detection has been researched. The pixel is distinguished by the variance of the pixel to its neighborhood, and then perform the region detection.
     3. Image fusion algorithm based on wavelet has been investigated.The fusion rule based on the low-frequency edge-based features and energy to the low-frequency region is given.
     4. We have researched image fusion method based on image block and wavelet by means of respective advantage of space domain and frequency domain image fusion algorithms.
     Multi-focus image fusion as an important branch of image fusion is the most important topic, and is widely applied in many fields such as computer vision,digital camera and object identification. It aims at obtaining a composite image with more detailed and complete information content from multi-focus images. There are sensors which cannot generate images of objects at various distances with equal clarity. Ways of
引文
[1] Jia-peng Wu, Zhao-xuan Yang ,etal.Wavelet Transform And Fuzzy Reasoning Based Image Fusion Alogrithm.Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China, 2-4 Nov. 2007:73-77.
    [2] Youshi Ye, Baojun Zhao Linbo Tang,etal.SAR and Visible Image Fusion based on Local non-negative Matrix Factorization. The Ninth International Conference on Electronic Measurement & Instruments ICEMI’2009:263-266.
    [3]康原原,李彬,等.基于小波变换和纹理测度的多模医学图像融合.Proceedings of the 26th Chinese Control Conference July, 2007, Zhangjiajie, Hunan, China: 26-31.
    [4] Z.Xue,R.S.Blum.YLi . Fusion of Visual and IR Images for Coneealed WeaPen Detection.Proeeedings of International Conefrence on Inoformation Fusion,AnnaPolis, Maryland,2002,1180一1192.
    [5]王珂,欧阳宁.小波分析在多聚焦图像融合中的应用.电光与控制, Mar .2008,15(3):64-67.
    [6] Ishita De, Bhabatosh Chanda.A simple and efficient algorithm for multifocus image fusion using morphological wavelets. Signal Processing 86 (2006) :924–936.
    [7] Daily M.I,Farr T.and Elachi C.Geologic interpretation from composited radar and landsat imagery,Photogrammetric Engineering and Remote Sensing,1979,45(8),1109-1116.
    [8] C.Vogler,D.Metaxas . Parallel Hidden Markov Models for American Sign Language Recognition.Proceedings of the International Conference on Computer Vision,1999:116-122.
    [9]李弼程,罗建书.小波分析及应用,电子工业出版社, 2003,5:199一200
    [10] WAKD L.Some terms of reference in data fusion.IEEE Transactions on Geoscience and Remote Sensing,1999,37(3):1190-1193.
    [11] Chavez P S Jr, Sides S C, Ande-rson J A.Comparison of three different methods to merge multiresolution and mult-ispectral data:Landsat TM and SPOT panc-hromatic. Photogrammetric Engineering and Remote Sensing, 1991, 57(3): 295-303.
    [12]瞿继双,王超,王正志.基于数据融合的遥感图像处理技术.中国图像图形学报,2002,7(1 0) :985-991.
    [13]曹杰,龚声蓉.一种新的基于小波变换的多聚焦图像融合算法.计算机工程与应用.2007.43(24) :47-50.
    [14] X.Yang, W.Yang, J.Pei.Different focus points images fusion based on wavelet decomposition, Proceedings of Third International Conference on Information Fusion, vol. 1, 2000:3–8.
    [15] Yu Song ,Mantian Li , Qingling Li an-d ,Lining Sun. A New Wavelet Base-d Multi-focus Image Fusion Scheme a-nd Its Application on Optical Micros-copy, Proceedings of the 2006 IEE-E International Conference on Robot-ics and Biomimetics-December 17 20, 2006, Kunming, China.
    [16]龚昌来.基于局部能量的小波图像融合方法.激光与红外,2008,38(12):1266-1269.
    [17]浦西龙,吕建平.一种基于小波变换的多分辨率图像融合算法.计算机工程与应用,2007,43(20):65-67.
    [18]曾基兵,陈怀新,王卫星.基于改进局部方差的小波图像融合方法.计算机工程与应用,2007,43(32):72-73.
    [19] PENNEC E,MALLAT S.Image Compression with Geometrical Wavelets. Proceedings of the IEEE International Conference on Image Processing.Canada:Vancouver,2000,9:661-664
    [20] PENNEC E,MALLAT S.Bandelet Image Approximation and Compression.SIAM Journal of Multiscale Modeling and Simulation,2005,4(3):992—1039.
    [21] Candes E J ,Donoho D L .Curvelet—A surprisingly effective non adaptive represent tion for objects with edges. [A] .TN:Vaderbilt University Press,2000:105—120.
    [22]杨俊,赵忠明.基于Curvelet变换的多聚焦图像融合方法.光机工程,2007,34(6):67-71.
    [23] Donoho M N,Vetterli M.The Contourlet Transform:An efficient Directional Multi resolution Image Representation[J].IEEE Transactions on Image Processing,2005,14;2091-2106.
    [24] Miao Qiguang,Wang Baoshu . A Novel Image Fusion Method Using Contourlet Transform,Proceeding of 4th International Conference on Communications, Circuits and Systems(ICCCAS2006).China:Guilin,2006,1:549-552.
    [25]杨谬,郭宝龙,倪伟,等.基于区域特性的Contourlet域多聚焦图像融合算法.西安交通大学学报,2007,41(4):448—452
    [26]马义德,林冬梅等.PCNN与粗集理论用于多聚焦图像融合.电子科技大学学报. Vol.38.no.4pp.485-488
    [27] M. Subbarao, T. S. Choi, and A. Nikzad . Focusing techniques, SPIE Conference OE/Technology 1823, pp. 163–174, 1992
    [28]闫敬文,卓琳,屈小波.图像融合研究最新进展,厦门理工学院学报,2007,14(4):44-49
    [29] S Sharma . Applied Multivariate Techn-iques . John Wiley &Sons , Inc. New York,NY,USA,1995
    [30] M.Kirby,L.Sirovich.Application of the Karhunen-Loeve Procedure for the Charact-erization of Human Faces.IEEE TRANS-ACTONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, January 199-0,12(1):102-108
    [31] Ahmed N,Rao K R . Orthogonal Transforms for Digital Signal Processing. New York:Springer,1975
    [32]胡广书.数字信号处理理论、算法与实现.北京:清华大学出版社,2003,368-370
    [33] Chen Huaixin . A Multiresolution Image Fusion Based on Principle Component Analysis.Fourth International Conference on Image and Graphics,2007,737-741
    [34] Shutao Li, James T,etal.Multifocus image fusion using artificial neural networks. Pattern Recognition Letters 23 (2002) 985–997
    [35]李婷,谭勇.基于优化权值的多聚焦图像融合方法.计算机工程与应用,2008,44(15):192-194.
    [36]张新曼韩九强王勇.一种遗传搜索块寻优的不同聚焦点图像融合算法,电子与信息学报,2006,28(11):2054-2057.
    [37] R. Sharma and M. Pavel.Adaptive and statistical image fusion, Society for Information Display Digest, vol. 17, no. 5,pp. 969–972, May 1996
    [38] S. Li, J. T. Kwok, and Y. Wang.Multifocus image fusion using artificial neural networks, Pattern Recognit. Lett., vol. 23, no. 8, pp985–997, 2002
    [39] W Huang,ZL Jing.Multi-focus image fusion using pulse coupled neural network. Pattern Recognition Letters, vol.28, pp.1123–1132, 2007
    [40] M Li, W Cai and Z Tan.Pulse coupled neural network based imagefusion, Second International Symposium on Neural Networks- ISSN2005, Lecture Notes in Computer Science, Vol.3497 (I), pp.741-746,2005
    [41] Baochang Xu, Zhe Chen.A multisensor image fusion algorithm based on PCNN, Fifth World Congress on Intelligent Control and Automation-WCICA 2004, Vol.4, pp. 3679-3682. 2004 .
    [42] LI Min, CAI Wei, TAN Zheng.A region-based multi-sensor image fusion scheme using pulse-coupled neural network. Pattern Recognition Letters, 2006, 27(16): 1948-1956
    [43]苗启广,王宝树.一种自适应pcnn多聚焦图像融合新方法.电子与信息学报,2006, 28(3):466-470
    [44] Peter J.Burt,Edward H.Adelson.The Laplacian Pyramid as a Compact Image Code. IEEE TRANSACTIONS ON COMMUNICATIONS, 1983,VOL. COM-3l, NO. 4, 532-540.
    [45] Toet.A. Hierarchical image fusion. Machine Vision and Applications, 1990,3:1-11.
    [46] Burt, P.J., Kolczynski,R. J.Enhanced image capture through fusion, In Fourth International Conference on Computer Vision, 1993,pp.173-182.
    [47] Mallat S G.Multifrequency channel decomposition of image and wavelet models, IEEE Trans Signal Processing, 1989,vol. 37, No. 12, pp. 2091-2110.
    [48] JingboZhang,Xue Feng,Baoling Song,Mingjie Li, and Yinghua Lu.Multi-Focus Image Fusion Using Quality Assessment of Spatial Domain and Genetic Algorithm,Human System.Interactions,Krakow,Poland,May 2008:71-75.
    [49] Q.H.Qu,D.L.Zhang and P.F.Yan.Information measure for performance of image fusion.IEEE Electron.Lett.,2002,7(38):313-315
    [50] N.Cvejic etal.Image fusion metric based on mutual information and Tsallis entropy.IEEE Electron.Lett.,2006,42(11):626-627
    [51]王宏,敬忠良,李建勋.一种基于图像块分割的多聚焦图像融合方法.上海交通大学学报,2003,37(11):1743-1750.
    [52] Dheeraj Agrawal,Dr.Al-Dahoud Ali,Dr.J.Singhai.A Modified Partition Fusion Technique Of Multifocus Images For Improved image Qualtity.Special Issue on ICIT2009 Conference-Bioinformatics and Image,UbiCC Journal,4(3):658-663
    [53] D.Fedorov,B.Sumengen,and B.S.Manjunath.multi-focus imaging using local focus estimation and mosaicking. IEEE International Conference on Image Processing,Atlanta,Georgia,2006.pp.227-231
    [54] A.Goshtasby.Fusion of multi-focus images to maximize image information.Defense and Security Symposium,Orlando,Florida,2006,PP.17-21
    [55] Yinghua Lu, Xue Feng.A Multi-focus Image Fusion Based on Wavelet and Region Detection. EUROCON 2007 The International Conference on“Computer as a Tool”[C],pp.294-298.
    [56] Min Wang, Dongliang Peng, ZhanWen Liu.Image Fusion Using A Contourlet Hmt Model.Proceedings of 007 International Symposium onIntelligent Signal Processing and Communication Systems Nov.28-Dec.1,2007 Xiamen,China.pp:678-681
    [57] Sheng Zheng, Wen-Zhong Shi.Multisource Image Fusion Method Using Support Value Transform.. IEEE TRANSACTIONS ON IMAGE PROCESSING[C], VOL. 16, NO. 7, JULY 2007.pp.1831-1838
    [58] Yinghua Lu, Dayou Liu, Xue Feng, Jun kong, Kaiyuan Zheng, Rujuan Wang.A multi-focus image fusion based on GA and morphological algorithm, Journal of Computer Science, China, in press
    [59] Li,S.,Kwok,J.T.,Wang,Y.Combination of images with diverse focuses using the spatial frequency.Inf.Fusion 2001.2:169-176.
    [60]黄卉,檀结庆.一种新的基于清晰度的多聚焦图像融合规则.计算机工程与应用,2005,14:51-52.
    [61]樊启斌.小波分析.武汉:武汉大学出版社,2008,10
    [62] Mallat S G.A . Theory for Multiresolution Signal Decomposition:The Wavelet Representation.IEEE Transaction on Pattern Analysis and Machine Intelligence,1989,11(3):674-693.
    [63]董卫军,樊养余,周明全.基于提升格式小波变换的医学图像融合技术.计算机工程与应用,2008,44(13):185-187
    [64] M Santons ,G Pajares . A New Wavelets Image Fusion Strategy.Leetu NotesinComPuterSeienee.Vol.2652,2003,PP.919一926
    [65]延昊,侯增广,谭民.基于小波变换的多尺度图像融合.计算机工程与应用,2003,39(29):131-134
    [66]李敏,张小英,毛捷.基于邻域方差加权平均的小波图像融合.理论与方法,2008,27(1):5-7
    [67]李艳敏,李孟超,孙刘杰,郑刚,庄松林.基于小波变换的红外显微图像融合.微计算机信息,2005,9(1):126-127。
    [68] Zheng-wei shen,Yu Liu,Fu-cheng Liao.Construction of 4-band Wavelet And Its Application In Multiple-source Image Fusion. Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, Hong Kong, 30-31 Aug. 2008,pp:128-133.
    [69]苗启广,王宝树.基于小波变换与局部能量的多聚焦图像融合.计算机科学,2005,32(2):229-231
    [70]罗少鹏,卢洵.基于小波分解的多聚焦图像融合研究.电子技术,2008,6(26):72-75.
    [71] Duan Chendong,Jiang Hongkai,He Zhengjia.Adaptive Wavelets Based onSecond Generation Wavelet Transform and Their Applications to Trend Analysis and Prediction[J].2004,9(3):170-176.
    [72] G.Pajares and de la Cruz JM . A wavelet-based image fusion tutorial[J].Pattern Recognitin,2004,37(9):1855-1872.
    [73] Min Li,Wei Cai,Zheng Tan.A region-based multi-sensor image fusion scheme using pulse coupled neural network.Pattern Recognition Letters,2006,27(16):1948-1956.
    [74] Strang G. . Wavelets and dilation equation: A brief introduction. SIAM Rev, 1989, 31(4):614-627.
    [75]车志宇,夏明革,何友.基于粗糙集与小波分析的图像融合算法.光电与控制,2005,12(1):18-21.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700