基于自然计算的SAR图像分割技术的研究
|
摘要
合成孔径雷达(Synthetic Aperture Radar,简称SAR)由于其全天候、全天时的观测特性和高分辨率的特点在军事以及资源考察、环境检测、考古等方面得到了广泛的应用,成为当前遥感观测的重要手段,SAR图像的分析和处理随之成为重要的研究课题。作为SAR图像分析和处理的关键步骤,SAR图像的分割一直得到广泛的关注。本文探讨了SAR图像分割的主要问题,研究并给出了SAR图像分割的算法和技术。本论文的主要工作及取得的结果包括：
1.结合SAR图像的空间特征和灰度信息,将图像分割转换成空间矩阵的求极值的问题,应用智能搜索算法,实现了分割阈值的自动获取。仿真结果表明,结合空间矩阵的分割方法对人工目标有较好的分割效果。
2.SAR图像中通常包含有丰富的纹理信息,根据灰度共生矩阵(GLCM)计算的纹理特征,结合免疫算法,提出一种结合纹理特征的免疫无监督聚类算法。仿真结果显示,在目标呈现一定的纹理时,该方法有较高的分割精度。
3.从理论上证明了有限次的小波变换可以减小相干斑噪声对纹理分析的影响,提高GLCM纹理特征值的计算精度。提出一种新的基于小波变换的纹理分割方法。仿真结果显示,该方法也有较高的分割精度。
4.应用隐马尔可夫模型(HMM)对SAR图像进行建模,通过学习得到图像统计模型的参数,并根据得到的模型参数计算图像之间的距离,该方法有很广泛的应用领域。基于图像距离的计算,给出一种新颖的分割算法。仿真结果显示,该方法对纹理的尺度和纹理的细节有较强的鲁棒性,且对SAR图像的相干斑噪声不敏感,分割效果较好。
5.针对SAR图像分割和目标识别的目的,提出一种SAR图像挖掘的框架,并构造了SAR图像的数据立方体的模型。数据挖掘的技术和数据立方体中对图像的多维特征的描述,有助于实现SAR图像的快速分割和目标识别。
Due to the character of high resolution and the fact that it can be used to observe in all weather and all time, Synthetic Aperture Radar (SAR) has been widely used in military areas, resource observation, environment detection, archeological areas, etc. Therefore, the analysis and processing of SAR images have been important research topics. SAR image segmentation is an important step in SAR image analysis and processing and has attracted much attention. This thesis addresses the key issues in SAR image segmentation and makes research and proposes algorithms and technologies for SAR image segmentation. The thesis includes the following research works and new results:
1. The problem of SAR image segmentation is converted into the problem of optimization of spatial matrix by combining spatial characters and gray information of SAR image. The segmentation threshold can be automatic obtained by using intelligent searching algorithm. The simulation results show that the algorithm based on spatial matrix can have good performance for artificial objects of images.
2. SAR images often have abundant texture information. According to the texture characters derived from the computation of Gray Level Co-occurrence Matrix (GLCM), an unsupervised immune clustering algorithm is proposed based on the immune algorithm. The simulation results indicate that high segmentation resolution can be achieved for images with certain textures.
3. This thesis theoretically proves that wavelet transform can reduce the effect of coherent noise and improve the precision of texture analysis and then proposes a segmentation algorithm based on wavelet transform. The simulation results indicate that the wavelet transform based algorithm has high segmentation resolution.
4. Hidden Markov Model (HMM) is used to model SAR image. The parameters of the statistical model can be obtained by learning. Distance between images can be computed by using the obtained parameters. A segmentation algorithm is proposed based on the image distance. The simulation results show that the algorithm is robust to texture scale and details and not sensitive to the coherent noise hence and has low complexity and better segmentation.
5. A data cube model for SAR image is constructed to describe the characters of SAR image. The multi-dimensional description of the SAR image database and image data mining techniques can help to achieve fast segmentation and object recognition of SAR image.
1.结合SAR图像的空间特征和灰度信息,将图像分割转换成空间矩阵的求极值的问题,应用智能搜索算法,实现了分割阈值的自动获取。仿真结果表明,结合空间矩阵的分割方法对人工目标有较好的分割效果。
2.SAR图像中通常包含有丰富的纹理信息,根据灰度共生矩阵(GLCM)计算的纹理特征,结合免疫算法,提出一种结合纹理特征的免疫无监督聚类算法。仿真结果显示,在目标呈现一定的纹理时,该方法有较高的分割精度。
3.从理论上证明了有限次的小波变换可以减小相干斑噪声对纹理分析的影响,提高GLCM纹理特征值的计算精度。提出一种新的基于小波变换的纹理分割方法。仿真结果显示,该方法也有较高的分割精度。
4.应用隐马尔可夫模型(HMM)对SAR图像进行建模,通过学习得到图像统计模型的参数,并根据得到的模型参数计算图像之间的距离,该方法有很广泛的应用领域。基于图像距离的计算,给出一种新颖的分割算法。仿真结果显示,该方法对纹理的尺度和纹理的细节有较强的鲁棒性,且对SAR图像的相干斑噪声不敏感,分割效果较好。
5.针对SAR图像分割和目标识别的目的,提出一种SAR图像挖掘的框架,并构造了SAR图像的数据立方体的模型。数据挖掘的技术和数据立方体中对图像的多维特征的描述,有助于实现SAR图像的快速分割和目标识别。
Due to the character of high resolution and the fact that it can be used to observe in all weather and all time, Synthetic Aperture Radar (SAR) has been widely used in military areas, resource observation, environment detection, archeological areas, etc. Therefore, the analysis and processing of SAR images have been important research topics. SAR image segmentation is an important step in SAR image analysis and processing and has attracted much attention. This thesis addresses the key issues in SAR image segmentation and makes research and proposes algorithms and technologies for SAR image segmentation. The thesis includes the following research works and new results:
1. The problem of SAR image segmentation is converted into the problem of optimization of spatial matrix by combining spatial characters and gray information of SAR image. The segmentation threshold can be automatic obtained by using intelligent searching algorithm. The simulation results show that the algorithm based on spatial matrix can have good performance for artificial objects of images.
2. SAR images often have abundant texture information. According to the texture characters derived from the computation of Gray Level Co-occurrence Matrix (GLCM), an unsupervised immune clustering algorithm is proposed based on the immune algorithm. The simulation results indicate that high segmentation resolution can be achieved for images with certain textures.
3. This thesis theoretically proves that wavelet transform can reduce the effect of coherent noise and improve the precision of texture analysis and then proposes a segmentation algorithm based on wavelet transform. The simulation results indicate that the wavelet transform based algorithm has high segmentation resolution.
4. Hidden Markov Model (HMM) is used to model SAR image. The parameters of the statistical model can be obtained by learning. Distance between images can be computed by using the obtained parameters. A segmentation algorithm is proposed based on the image distance. The simulation results show that the algorithm is robust to texture scale and details and not sensitive to the coherent noise hence and has low complexity and better segmentation.
5. A data cube model for SAR image is constructed to describe the characters of SAR image. The multi-dimensional description of the SAR image database and image data mining techniques can help to achieve fast segmentation and object recognition of SAR image.
引文
[1]D. Stewart, D. Blackwell, A. Blake, R. Cook, and C. Oliver. An optimal approach to SAR. The VLSI journal.1986,4.209-238
[2]Dong Y., Forster B.C., Milne A.K. Comparison of radar image segmentation by Gaussian-and Gamma-Markov random field models. International Journal of Remote Sensing.2003,24(4).711-722
[3]C. Lemarechal, R. Fjortoft, P. Marthon, E. Cubero-Castan, and A. Lopes. Sar image segmentation by morphlogical methods. Proc. SAR Image Analysis, Modelling, and Technique III. SPIE.1998,9
[4]Ives, R.W., Eichel, P. Magotra, N. Application of pixel segmentation to the low rate compression of complex SAR imagery. IEEE international geoscience and remote sensing symposium. Seattle, WA (United States).1998,7.6-10
[5]Derin H, Kelly P A, Vezina G, et al. Modeling and segmentation of speckled images using complex data. IEEE Transaction on Geoscience and Remote Sensing.1990, 28(1).76-87
[6]Leen-Kiat Soh and Costas tsatsoulis. Segmentation of satellite imagery of natural scenes using data mining. IEEE Transactions on Geoscience and Remote Sensing. 1999,3,37(2).1086-1099
[7]R.Fjortoft, A.Lopes, J. Bruniquel, Ph. Marthon. Optimal edge detection and edge localization in complex SAR images with correlated speckle. IEEE Transactions on Geoscience and Remote Sensing.1999,9,37(5).2272-2281
[8]Vidya Venkatachalam, Robert D. Nowak, Richard G. Baraniuk, Mario A. T. Figueiredo. Unsupervised SAR image segmentation using recursive partitioning. Proceedings of SPIE.2000,8.121-129
[9]刘振华,于文震,毛士艺.SAR图像组合降斑算法.电子学报.2004,32(3).363-367
[10]Rupert D. Paget. Nonparametric Markov Random Field Models for Natural Texture Images. Submitted as a requirement for the degree of Doctor of Philosophy (Ph.D.), The University of Queensland.1999,2
[11]J.H.Holland. Genetic algorithm and classifier system. foundations and applications. Proceedings of the Second International Conference on Genetic Algorithms.1987. 82-89
[12]J.D.Farmer, N.H.Packard and AS.Perelson. The immunity system, adaptation, and machine learning. Physics.1986,22.187-204
[13]H.Bersini, F.J.Varela. Hints for adaptive problem solving gleaned from immune networks. Proceedings of the first workshop on parallel problem solving from nature. Springer & Verlag,1990
[14]王磊,潘进,焦李成.免疫算法.电子学报.2000,6,28(7).74-78
[15]曹先彬,罗文坚,王煦法.基于免疫网络调节的改进遗传算法.高技术通讯.2000,10.23-27。
[16]S Forrest, et al. Self-nonself discrimination in a computer. Proceedings of the 1994 IEEE Symposium on Research in Security and Privacy. Los Alamitos, CA. IEEE Computer Society Press,1994
[17]边肇祺,张学工等.模式识别.北京：清华大学出版社,1999
[18]Sahoo P K. A Survey of threshold techniques. Computer Vision Graphics Image Process.1988,41.233-260
[19]D.R.Paudyal, Apisit Eiumnoh, Josef Aschbacher. Textural information in SAR images for land-cover application. In Proc. IGARS Conference. Florence, Italy, 1994,7.987-989
[20]G.Heene. On the useof a multispectral markov random field model for texture analysis in multitemporal SAR imagery. Fifth International Symposium on Signal Processing and its Applications.1999,8,939-942
[21]IEEE Standard 610.4-1990. IEEE Standard Glossary of Image Processing and Pattern Recognition Terminology. IEEE Press, New York,1990
[22]John R. Smith, Shih-Fu Chang. Automated binary texture feature sets for image retrieval. In Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc.,1996,3
[23]Robert M. Haralick, K. Shanmugam. Texture features for image classification. IEEE Trans. On Sys, Man, and Cyb.1973,3(6):610-621
[24]S C Liew, H Lim, L K Kwoh and G K Tay. Texture analysis of SAR images. Proc. of International Geoscience and Remote Sensing Symposium,1995.1412-1414
[25]胡金艳,张太镒,张春梅.基于分数布朗运动和概率神经网络的自然纹理分类.电子与信息学报.2003,3,26(3).389-393
[26]D.R.Paudyal, Apisit Eiumnon, Josef Aschbacher. Textural information in SAR images for land-cover applications. In Proc. IGARS Conference. Florence, Italy, 1994,7.987-989
[27]Anne H. Schistad Solberg, Anil K. Jain. A study of invariance properties of textural features in SAR images. In Proc. IGARS Conference. Florence, Italy.1994,7. 670-672
[28]Robert M. Haralick, K. Shanmugam. Texture features for image classification. IEEE Trans. On Systems, Man and Cybernetics.1972,11,3(6).610-621
[29]Belhadj Ziad, Bouhlel Nizar, Sevestre Ghalila Sylvie and Boussema Mohamed Rached. Heterogeneous SAR texture characterization by means Of markov random fields. In Proceeding of IGARSS,2000,2.579-581
[30]L. Bruzzone, S.B. Serpico, and G. Vernazza. Effects of parameter tuning and de-speckle filtering on the accuracy of SAR image classification based on gray-level co-occurrence matrix features. Proc. of IGARSS'97, Singapore,1997,8(11).764-766
[31]G. Trianni, M. Tosi F., Dell'Acqua and P. Gamba. Fusion of texture measures for urban area characterization. Proceedings of the 7th International Conference on Information Fusion, Stockholm, Sweden,2004, June 28-July 1.991-998
[32]Yoshiki Yamagata, Yoshifumi Yasuoka. Classification of wetland vegetation by texture analysis method using ERS-land JERS-1 Images. CGER'S Supercomputer Activit Report,1992.76-79
[33]Pierce, L.E., H. Xie, M.C. Dobson, and F.T. Ulaby. Texture features for classification with ERS/JERS composites. In Proc. of IEEE Geoscience and Remote Sensing Symp. Seattle, WA,1998,7(1).348-350
[34]J.M. Kellndorfer, H. Xie, F.T. Ulaby and M.C. Dobson. Combined multi-temporal ERS-1/JERS-1 imagery for land-cover classification. In Proc. of IEEE Geoscience and Remote Sensing Symp. Seattle, WA,1998,7(1).228-231
[35]薛笑荣,张艳宁,赵荣椿,段锋.基于小波变换的SAR图像分割.计算机工程.2003,4,30(7)：11-12
[36]R. M. Haralick. Statistical and structural approaches to texture. Proc. IEEE.1979, 67.786-804
[37]Dutra, LV and R. Huber. Feature extraction and selection for ERS-1/2 InSAR classification. International Journal of Remote Sensing.1999,20(5).993-1016
[38]Leen-Kiat Soh and Costas tsatsoulis. Segmentation of satellite imagery of natural scenes using data mining. IEEE Trans on Geoscience and Remote Sensing.1999, 37(2).1086-1099.
[39]J.A.Modestino, J.Zhang. A markov random field model based approach to image interpretation. IEEE Tran. On Pattern Analysis and Machine Intelligence.1992,14. 606-615
[40]C.C.Gotlieb and H.E.Kreyszig. Texture descriptors based on co-occurrence matrices. Computer Vision, Graphics, and Image Processing.1990,51.70-86
[41]N. Kamath, K. Sunil Kumar and U. B. Desai. Joint segmentation and image interpretation using hidden Markov models. In Proc. of the Int. Conf. on Pattern Recognition. Brisbane, Australia,1998(11).1840-1842
[42]MacQueen. Some methods for classification and analysis of multiattribute instances. Proceedings of the Fifty Berkeley Symposium on Mathematics, Statistics and Probability.1967,1.281-296
[43]李宏东,姚天翔.模式分类.北京.机械工业出版社,2003.423-424
[44]Chang T, Kuo C C J. Texture analysis and classification with tree structured wavelet transform. IEEE Trans. Image Processing.1993,3(4).429-441.
[45]M. Unser. Texture classification and segmentation using wavelet frames. IEEE Trans. Image Processing,1994,4.1549-1560
[46]侯彪,刘芳,焦李成.基于小波变换的高分辨率SAR港口目标自动分割.红外与毫米波学报.2002,10,21(5).385-389
[47]倪玲,张剑清,姚巍,基于小波的SAR影像纹理分析.武汉大学学报(自然科学版).2004,29(4).367-370
[48]薛笑荣,张艳宁,赵荣椿,段锋.基于小波变换的SAR图像分割.计算机工程.2003,4,30(7).11-12
[49]薛笑荣,张艳宁,赵荣椿,申家振,胡伏原.利用小波尺度共生矩阵和灰度共生矩阵的SAR图像分类.中国体视学与图像分析.2002,12,7(4).193-197
[50]Y. Rangsanseri. Comparison between co-occurrence and wavelet features for characterization of urban environments by SAR Data. Asia Pacific Microwave Conference.2000
[51]Mark A. Schulze and Qing X. Wu. Noise Reduction in Synthetic Aperture Radar Imagery Using a Morphology-based Nonlinear Filter. In Proceeding of Digital Image Computing. Techniques and Applications,1995.661-665
[52]J.-S. Lee. Speckle suppression and anylysis for synthetic aperture radar images. Optical Engineering.1986,25(5).636-642
[53]L.J. Porcello, N.G. Massey. Speckle reduction in synthetic-aperture radars. Journal of the Optical Society of America.1976,66(11).1305-1311
[54]G.V. April and E.R.Harvey. Speckle statistics in four-look synthetic aperture radar imagery. Optical Engineering.1991,30(4).375-381
[55]Robert M. Haralick, K. Shanmugam. Texture Features for Image Classification. IEEE Trans. On Systems, Man and Cybernetics.1972,11,3(6).610-621
[56]M.J. Swain and D.H. Ballard. Color indexing. International Journal of Computer Vision,1991,7(1).11-32
[57]J. Hafner, H.S. Sawhney. Efficient color histogram indexing for quadratic form distance functions. IEEE Trans. on Pattern Analysis and Machine Intelligence. 1995,17(7).729-736
[58]M. Stricker and M. Orengo. Similarity of color images. Conf. on Storage and Retrieval for Image and Video Databases Ⅲ.1993,2.381-392
[59]M. Stricker and A. Dimai. Color indexing with weak spatial constraints. Conf. on Storage and Retrieval for Image and Video Databases Ⅳ.1995,29-40
[60]W.Hsu, T.Chua, and H.Pung. An integrated color-spatial approach to content-based image retrieval. Proc. of the ACM Multimedia.1995,11.305-313
[61]T.Chua, K.Tan, and B.Ooi. Fast signature-based color-spatial image retrieval. Proc. Of the Multimedia Computing and Systems. Ottawa, Ontario.1997,6.362-369
[62]J.A.Modestino and J.Zhang. A markov random field model based approach to image interpretation. IEEE Tran. On Pattern Analysis and Machine Intelligence. 1992,14:606-615
[63]林学闫,王宏等译.计算机视觉：一种现代方法.北京,电子工业出版社,2004.474-482
[64]Han.J, Nishio.S, Kawano.H, and Wang.W. Generalization-based data mining in object-oriented databases using an object-cube model. Data and Knowledge Engineering.1998,25:55-96
[65]han.J, Stefanovic.N, and Koperski.K. Selective materialization. AN efficient method for spatial data cube construction. In Proc.1998 Pacific-Asia Conf. Knowledge Discovery and Data Mining.1998,4
[66]M.C.Burl, C.Fowlkes and J.Roden. Mining for image content. In Proc. Conf. Systemics, Cybernetics, and Informatics/Information Systems:Analysis and Synthesis. Orlando, FL.1999,6.
[67]J. P. Eakins and M. E. Graham. Content-based image retrieval. a repot to the JISC technology applications program. Northumbria Image Data Research Institute,
[68]M.Datcu, K.Seidel. Bayesian methods:applications in information aggregation and image data mining. Internatinal Archivers of Photogrammetry and Remote Sensing. 1999,6,32.68-73
[69]M.C. Burl. Mining for image content. Conf. on Information Systems, Analysis and Synthesis. Orlando, Florida.2005
[70]P.Stanchev, et al. Using Image Mining for Image retrieval. IASTED conf. Computer Science and Technology.2003,3,214-218
[71]C.Gibson, Stephen, et al. Intelligent mining in image databases, with applications to satellite imaging and to web search. Data Mining and Computational.2001, 309-336
[72]R. F. Cromp and W. J. Campbell. Data mining of multi-dimensional remotely sensed images. International Conference on Information and Knowledge Management.1993
[73]N.Katayama and S. Satoh. The SR-tree. An index structure for high-dimensional nearest neighbor queries. In proceedings of the 1997 ACM SIGMOD Conference. Tucson, Arizona,1996,5.369-380
[74]J. Zhang, W. Hsu and M. L. Lee. An Information-driven Framework for Image Mining. In Proceedings of 12th International Conference on Database and Expert Systems Applications. Munich, Germany,2001,9
[75]S.Haykin. Neural Networks:a comprehensive foundation. Prentice Hall: Englewood Cliffs.1999.
[76]K. Lin, H. V. Jagadish and C. Faloutsos. The TVtree. An index structure for high-dimensional data. The VLDB Journal,1993,3(4).517-542
[77]T. Sellis, N. Roussopoulos and C. Faloutsos. The R+ tree. A dynamic index for multi-dimensional objects. In Proc 12th VLDB,1986
[78]C. Ordonez and E. Omiecinski. Discovering association rules based on image content. Proceedings of the IEEE Advances in Digital Libraries Conference.1999
[79]A.Vailaya, A. T. Figueiredo, A. K. Jain, and H. J. Zhang. Image classification for content-based indexing. IEEE Transactions on Image Processing,2001,1,10(1). 117-130
[80]D. White and R. Jain. Similarity indexing. Algorithms and performance. In Proc. SPIE Storage and Retrieval for image and Video Databases.1995
[81]C.F.Shu, R.C.Jain. Vector field analysis for oriented patterns. IEEE Transaction on Pattern Analysis and Machin Intelligence.1994,9,16(9).946-950
[82]J. Z. Wang, J. Li. System for Screening Objectionable Images Using Daubechies' Wavelets and Color Histograms. Proc. of Interactive Distributed Multimedia Systems and Telecommunication Services.1997,1309.20-30
[83]E.Chang, C.Li and J.Wang. Searching Near-Replicas of Image via Clustering. Proc. of SPIE Symposium of Voice, Video, and Data Communications, Multimedia Storage and Archiving Systems Ⅵ. Boston, MA, USA.1999,9
[84]J. T. Robinson. The K-D-B tree. A search structure for large multidimensional dynamic indexes. In Proceeding of the ACM SIGMOD Conference.1981,6:10-18
[85]W. Y. Ma and B. S. Manjunath. A texture thesaurus for browsing large aerial photographs. Journal of the American Society for Information Science.1998,49(7). 633-648
[86]K.L.Tan, B.C.Ooi and L.F.Thiang. Retrieving similar shapes effectively and efficiently. Multimedia Tools and Applications.2003,2,19(2).111-134
[87]K. L Tan, B. C. Ooi and C. Y. Yee. An evaluation of color-spatial retrieval techniques for large image databases. Multimedia Tools and Applications.2001, 14(1).55-78
[88]Baraldi A, Parmiggian F. An investigation of the texture characteristics associated with gray level co-occurrence matrix statistical parameters. IEEE Transaction on Geoscience and Remote Sensing.1995,33(2).293-300
[89]吴均,赵忠明.利用基于小波的尺度共生矩阵进行纹理分析.遥感学报.2001,5(2).100-103
[90]李晓华,沈兰荪.基于小波压缩域的统计纹理特征提取方法.电子学报.2004,31(B12).2123-2126
[91]Justin K.Romberg, Hyeokho Choi and Richard G.Baraniuk. Bayesian tree-structured image modeling using wavelet-domain hidden markov models. IEEE Transactions on Image Processing.2001,10(7).1056-1068
[92]Song-Chun Zhu. Statistical modeling and conceptualization of visual patterns. IEEE transaction on Pattern analysis and Machine Intelligence.2003,25(6). 91-712.
[93]张翠,郦苏丹,王正志.基于MRF场的SAR图像分割方法.遥感技术与应用.2001,3,16(1).66-68
[2]Dong Y., Forster B.C., Milne A.K. Comparison of radar image segmentation by Gaussian-and Gamma-Markov random field models. International Journal of Remote Sensing.2003,24(4).711-722
[3]C. Lemarechal, R. Fjortoft, P. Marthon, E. Cubero-Castan, and A. Lopes. Sar image segmentation by morphlogical methods. Proc. SAR Image Analysis, Modelling, and Technique III. SPIE.1998,9
[4]Ives, R.W., Eichel, P. Magotra, N. Application of pixel segmentation to the low rate compression of complex SAR imagery. IEEE international geoscience and remote sensing symposium. Seattle, WA (United States).1998,7.6-10
[5]Derin H, Kelly P A, Vezina G, et al. Modeling and segmentation of speckled images using complex data. IEEE Transaction on Geoscience and Remote Sensing.1990, 28(1).76-87
[6]Leen-Kiat Soh and Costas tsatsoulis. Segmentation of satellite imagery of natural scenes using data mining. IEEE Transactions on Geoscience and Remote Sensing. 1999,3,37(2).1086-1099
[7]R.Fjortoft, A.Lopes, J. Bruniquel, Ph. Marthon. Optimal edge detection and edge localization in complex SAR images with correlated speckle. IEEE Transactions on Geoscience and Remote Sensing.1999,9,37(5).2272-2281
[8]Vidya Venkatachalam, Robert D. Nowak, Richard G. Baraniuk, Mario A. T. Figueiredo. Unsupervised SAR image segmentation using recursive partitioning. Proceedings of SPIE.2000,8.121-129
[9]刘振华,于文震,毛士艺.SAR图像组合降斑算法.电子学报.2004,32(3).363-367
[10]Rupert D. Paget. Nonparametric Markov Random Field Models for Natural Texture Images. Submitted as a requirement for the degree of Doctor of Philosophy (Ph.D.), The University of Queensland.1999,2
[11]J.H.Holland. Genetic algorithm and classifier system. foundations and applications. Proceedings of the Second International Conference on Genetic Algorithms.1987. 82-89
[12]J.D.Farmer, N.H.Packard and AS.Perelson. The immunity system, adaptation, and machine learning. Physics.1986,22.187-204
[13]H.Bersini, F.J.Varela. Hints for adaptive problem solving gleaned from immune networks. Proceedings of the first workshop on parallel problem solving from nature. Springer & Verlag,1990
[14]王磊,潘进,焦李成.免疫算法.电子学报.2000,6,28(7).74-78
[15]曹先彬,罗文坚,王煦法.基于免疫网络调节的改进遗传算法.高技术通讯.2000,10.23-27。
[16]S Forrest, et al. Self-nonself discrimination in a computer. Proceedings of the 1994 IEEE Symposium on Research in Security and Privacy. Los Alamitos, CA. IEEE Computer Society Press,1994
[17]边肇祺,张学工等.模式识别.北京：清华大学出版社,1999
[18]Sahoo P K. A Survey of threshold techniques. Computer Vision Graphics Image Process.1988,41.233-260
[19]D.R.Paudyal, Apisit Eiumnoh, Josef Aschbacher. Textural information in SAR images for land-cover application. In Proc. IGARS Conference. Florence, Italy, 1994,7.987-989
[20]G.Heene. On the useof a multispectral markov random field model for texture analysis in multitemporal SAR imagery. Fifth International Symposium on Signal Processing and its Applications.1999,8,939-942
[21]IEEE Standard 610.4-1990. IEEE Standard Glossary of Image Processing and Pattern Recognition Terminology. IEEE Press, New York,1990
[22]John R. Smith, Shih-Fu Chang. Automated binary texture feature sets for image retrieval. In Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc.,1996,3
[23]Robert M. Haralick, K. Shanmugam. Texture features for image classification. IEEE Trans. On Sys, Man, and Cyb.1973,3(6):610-621
[24]S C Liew, H Lim, L K Kwoh and G K Tay. Texture analysis of SAR images. Proc. of International Geoscience and Remote Sensing Symposium,1995.1412-1414
[25]胡金艳,张太镒,张春梅.基于分数布朗运动和概率神经网络的自然纹理分类.电子与信息学报.2003,3,26(3).389-393
[26]D.R.Paudyal, Apisit Eiumnon, Josef Aschbacher. Textural information in SAR images for land-cover applications. In Proc. IGARS Conference. Florence, Italy, 1994,7.987-989
[27]Anne H. Schistad Solberg, Anil K. Jain. A study of invariance properties of textural features in SAR images. In Proc. IGARS Conference. Florence, Italy.1994,7. 670-672
[28]Robert M. Haralick, K. Shanmugam. Texture features for image classification. IEEE Trans. On Systems, Man and Cybernetics.1972,11,3(6).610-621
[29]Belhadj Ziad, Bouhlel Nizar, Sevestre Ghalila Sylvie and Boussema Mohamed Rached. Heterogeneous SAR texture characterization by means Of markov random fields. In Proceeding of IGARSS,2000,2.579-581
[30]L. Bruzzone, S.B. Serpico, and G. Vernazza. Effects of parameter tuning and de-speckle filtering on the accuracy of SAR image classification based on gray-level co-occurrence matrix features. Proc. of IGARSS'97, Singapore,1997,8(11).764-766
[31]G. Trianni, M. Tosi F., Dell'Acqua and P. Gamba. Fusion of texture measures for urban area characterization. Proceedings of the 7th International Conference on Information Fusion, Stockholm, Sweden,2004, June 28-July 1.991-998
[32]Yoshiki Yamagata, Yoshifumi Yasuoka. Classification of wetland vegetation by texture analysis method using ERS-land JERS-1 Images. CGER'S Supercomputer Activit Report,1992.76-79
[33]Pierce, L.E., H. Xie, M.C. Dobson, and F.T. Ulaby. Texture features for classification with ERS/JERS composites. In Proc. of IEEE Geoscience and Remote Sensing Symp. Seattle, WA,1998,7(1).348-350
[34]J.M. Kellndorfer, H. Xie, F.T. Ulaby and M.C. Dobson. Combined multi-temporal ERS-1/JERS-1 imagery for land-cover classification. In Proc. of IEEE Geoscience and Remote Sensing Symp. Seattle, WA,1998,7(1).228-231
[35]薛笑荣,张艳宁,赵荣椿,段锋.基于小波变换的SAR图像分割.计算机工程.2003,4,30(7)：11-12
[36]R. M. Haralick. Statistical and structural approaches to texture. Proc. IEEE.1979, 67.786-804
[37]Dutra, LV and R. Huber. Feature extraction and selection for ERS-1/2 InSAR classification. International Journal of Remote Sensing.1999,20(5).993-1016
[38]Leen-Kiat Soh and Costas tsatsoulis. Segmentation of satellite imagery of natural scenes using data mining. IEEE Trans on Geoscience and Remote Sensing.1999, 37(2).1086-1099.
[39]J.A.Modestino, J.Zhang. A markov random field model based approach to image interpretation. IEEE Tran. On Pattern Analysis and Machine Intelligence.1992,14. 606-615
[40]C.C.Gotlieb and H.E.Kreyszig. Texture descriptors based on co-occurrence matrices. Computer Vision, Graphics, and Image Processing.1990,51.70-86
[41]N. Kamath, K. Sunil Kumar and U. B. Desai. Joint segmentation and image interpretation using hidden Markov models. In Proc. of the Int. Conf. on Pattern Recognition. Brisbane, Australia,1998(11).1840-1842
[42]MacQueen. Some methods for classification and analysis of multiattribute instances. Proceedings of the Fifty Berkeley Symposium on Mathematics, Statistics and Probability.1967,1.281-296
[43]李宏东,姚天翔.模式分类.北京.机械工业出版社,2003.423-424
[44]Chang T, Kuo C C J. Texture analysis and classification with tree structured wavelet transform. IEEE Trans. Image Processing.1993,3(4).429-441.
[45]M. Unser. Texture classification and segmentation using wavelet frames. IEEE Trans. Image Processing,1994,4.1549-1560
[46]侯彪,刘芳,焦李成.基于小波变换的高分辨率SAR港口目标自动分割.红外与毫米波学报.2002,10,21(5).385-389
[47]倪玲,张剑清,姚巍,基于小波的SAR影像纹理分析.武汉大学学报(自然科学版).2004,29(4).367-370
[48]薛笑荣,张艳宁,赵荣椿,段锋.基于小波变换的SAR图像分割.计算机工程.2003,4,30(7).11-12
[49]薛笑荣,张艳宁,赵荣椿,申家振,胡伏原.利用小波尺度共生矩阵和灰度共生矩阵的SAR图像分类.中国体视学与图像分析.2002,12,7(4).193-197
[50]Y. Rangsanseri. Comparison between co-occurrence and wavelet features for characterization of urban environments by SAR Data. Asia Pacific Microwave Conference.2000
[51]Mark A. Schulze and Qing X. Wu. Noise Reduction in Synthetic Aperture Radar Imagery Using a Morphology-based Nonlinear Filter. In Proceeding of Digital Image Computing. Techniques and Applications,1995.661-665
[52]J.-S. Lee. Speckle suppression and anylysis for synthetic aperture radar images. Optical Engineering.1986,25(5).636-642
[53]L.J. Porcello, N.G. Massey. Speckle reduction in synthetic-aperture radars. Journal of the Optical Society of America.1976,66(11).1305-1311
[54]G.V. April and E.R.Harvey. Speckle statistics in four-look synthetic aperture radar imagery. Optical Engineering.1991,30(4).375-381
[55]Robert M. Haralick, K. Shanmugam. Texture Features for Image Classification. IEEE Trans. On Systems, Man and Cybernetics.1972,11,3(6).610-621
[56]M.J. Swain and D.H. Ballard. Color indexing. International Journal of Computer Vision,1991,7(1).11-32
[57]J. Hafner, H.S. Sawhney. Efficient color histogram indexing for quadratic form distance functions. IEEE Trans. on Pattern Analysis and Machine Intelligence. 1995,17(7).729-736
[58]M. Stricker and M. Orengo. Similarity of color images. Conf. on Storage and Retrieval for Image and Video Databases Ⅲ.1993,2.381-392
[59]M. Stricker and A. Dimai. Color indexing with weak spatial constraints. Conf. on Storage and Retrieval for Image and Video Databases Ⅳ.1995,29-40
[60]W.Hsu, T.Chua, and H.Pung. An integrated color-spatial approach to content-based image retrieval. Proc. of the ACM Multimedia.1995,11.305-313
[61]T.Chua, K.Tan, and B.Ooi. Fast signature-based color-spatial image retrieval. Proc. Of the Multimedia Computing and Systems. Ottawa, Ontario.1997,6.362-369
[62]J.A.Modestino and J.Zhang. A markov random field model based approach to image interpretation. IEEE Tran. On Pattern Analysis and Machine Intelligence. 1992,14:606-615
[63]林学闫,王宏等译.计算机视觉：一种现代方法.北京,电子工业出版社,2004.474-482
[64]Han.J, Nishio.S, Kawano.H, and Wang.W. Generalization-based data mining in object-oriented databases using an object-cube model. Data and Knowledge Engineering.1998,25:55-96
[65]han.J, Stefanovic.N, and Koperski.K. Selective materialization. AN efficient method for spatial data cube construction. In Proc.1998 Pacific-Asia Conf. Knowledge Discovery and Data Mining.1998,4
[66]M.C.Burl, C.Fowlkes and J.Roden. Mining for image content. In Proc. Conf. Systemics, Cybernetics, and Informatics/Information Systems:Analysis and Synthesis. Orlando, FL.1999,6.
[67]J. P. Eakins and M. E. Graham. Content-based image retrieval. a repot to the JISC technology applications program. Northumbria Image Data Research Institute,
[68]M.Datcu, K.Seidel. Bayesian methods:applications in information aggregation and image data mining. Internatinal Archivers of Photogrammetry and Remote Sensing. 1999,6,32.68-73
[69]M.C. Burl. Mining for image content. Conf. on Information Systems, Analysis and Synthesis. Orlando, Florida.2005
[70]P.Stanchev, et al. Using Image Mining for Image retrieval. IASTED conf. Computer Science and Technology.2003,3,214-218
[71]C.Gibson, Stephen, et al. Intelligent mining in image databases, with applications to satellite imaging and to web search. Data Mining and Computational.2001, 309-336
[72]R. F. Cromp and W. J. Campbell. Data mining of multi-dimensional remotely sensed images. International Conference on Information and Knowledge Management.1993
[73]N.Katayama and S. Satoh. The SR-tree. An index structure for high-dimensional nearest neighbor queries. In proceedings of the 1997 ACM SIGMOD Conference. Tucson, Arizona,1996,5.369-380
[74]J. Zhang, W. Hsu and M. L. Lee. An Information-driven Framework for Image Mining. In Proceedings of 12th International Conference on Database and Expert Systems Applications. Munich, Germany,2001,9
[75]S.Haykin. Neural Networks:a comprehensive foundation. Prentice Hall: Englewood Cliffs.1999.
[76]K. Lin, H. V. Jagadish and C. Faloutsos. The TVtree. An index structure for high-dimensional data. The VLDB Journal,1993,3(4).517-542
[77]T. Sellis, N. Roussopoulos and C. Faloutsos. The R+ tree. A dynamic index for multi-dimensional objects. In Proc 12th VLDB,1986
[78]C. Ordonez and E. Omiecinski. Discovering association rules based on image content. Proceedings of the IEEE Advances in Digital Libraries Conference.1999
[79]A.Vailaya, A. T. Figueiredo, A. K. Jain, and H. J. Zhang. Image classification for content-based indexing. IEEE Transactions on Image Processing,2001,1,10(1). 117-130
[80]D. White and R. Jain. Similarity indexing. Algorithms and performance. In Proc. SPIE Storage and Retrieval for image and Video Databases.1995
[81]C.F.Shu, R.C.Jain. Vector field analysis for oriented patterns. IEEE Transaction on Pattern Analysis and Machin Intelligence.1994,9,16(9).946-950
[82]J. Z. Wang, J. Li. System for Screening Objectionable Images Using Daubechies' Wavelets and Color Histograms. Proc. of Interactive Distributed Multimedia Systems and Telecommunication Services.1997,1309.20-30
[83]E.Chang, C.Li and J.Wang. Searching Near-Replicas of Image via Clustering. Proc. of SPIE Symposium of Voice, Video, and Data Communications, Multimedia Storage and Archiving Systems Ⅵ. Boston, MA, USA.1999,9
[84]J. T. Robinson. The K-D-B tree. A search structure for large multidimensional dynamic indexes. In Proceeding of the ACM SIGMOD Conference.1981,6:10-18
[85]W. Y. Ma and B. S. Manjunath. A texture thesaurus for browsing large aerial photographs. Journal of the American Society for Information Science.1998,49(7). 633-648
[86]K.L.Tan, B.C.Ooi and L.F.Thiang. Retrieving similar shapes effectively and efficiently. Multimedia Tools and Applications.2003,2,19(2).111-134
[87]K. L Tan, B. C. Ooi and C. Y. Yee. An evaluation of color-spatial retrieval techniques for large image databases. Multimedia Tools and Applications.2001, 14(1).55-78
[88]Baraldi A, Parmiggian F. An investigation of the texture characteristics associated with gray level co-occurrence matrix statistical parameters. IEEE Transaction on Geoscience and Remote Sensing.1995,33(2).293-300
[89]吴均,赵忠明.利用基于小波的尺度共生矩阵进行纹理分析.遥感学报.2001,5(2).100-103
[90]李晓华,沈兰荪.基于小波压缩域的统计纹理特征提取方法.电子学报.2004,31(B12).2123-2126
[91]Justin K.Romberg, Hyeokho Choi and Richard G.Baraniuk. Bayesian tree-structured image modeling using wavelet-domain hidden markov models. IEEE Transactions on Image Processing.2001,10(7).1056-1068
[92]Song-Chun Zhu. Statistical modeling and conceptualization of visual patterns. IEEE transaction on Pattern analysis and Machine Intelligence.2003,25(6). 91-712.
[93]张翠,郦苏丹,王正志.基于MRF场的SAR图像分割方法.遥感技术与应用.2001,3,16(1).66-68
© 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 |