SAR图像相干斑抑制和分割方法研究
|
摘要
合成孔径雷达（SyntheticAperture Radar, SAR）通过发射宽频带信号来获取高的距离分辨率，并利用长的合成孔径来获取横向高分辨，从而获得大面积的高分辨率SAR图像。SAR具有全天候、远距离和极强的穿透力等特点并能在恶劣环境下以很高的分辨率提供地面信息。因此，SAR在地球科学、水文科学和生态科学等领域的作用越来越重要。然而，在SAR系统中，相干斑的存在使得后续基于SAR图像的理解及解译存在着很大的困难。因此，根据SAR图像中的观测值准确地估计图像真实的雷达散射截面积（Radar Cross Section, RCS）一直是SAR图像预处理的一个重要的研究课题。近些年来，根据未降斑处理或者已预降斑处理后的SAR图像，进行SAR图像的分割和后续的变化检测也一直受到雷达信号处理领域的广泛关注。
在本论文中，我们对SAR图像的降斑预处理技术，以及后续的SAR图像分割技术和两时相SAR图像变化检测技术进行了系统地研究，并提出了一系列实际有效的SAR图像降斑方法、SAR图像分割方法和两时相SAR图像的变化检测方法，主要研究成果为：
1.提出了基于各向异性高斯窗和SURE准则的非局部SAR图像降斑方法。
针对传统空域非局部均值（Non-local means, NLM）方法在SAR图像相干斑抑制中存在相似区域提取不足和方向信息捕获不足的问题，提出了一种基于各向异性高斯方向窗和史蒂文无偏风险估计（Stein’s unbiased risk estimation, SURE）准则融合的非局部均值算法。该方法利用多个不同方向的各向异性高斯窗来匹配SAR图像的局部空间几何结构，比传统的方形窗能更好地保护SAR图像中的方向性结构。然后，采用比率测度测量策略来衡量两个图像块的相似程度。最终，结合Stein’s无偏风险估计（SURE）准则来融合不同方向的各向异性高斯窗的非局部平均结果。文中针对多幅测试SAR图像进行了对比实验，实验结果表明：提出的方法在有效抑制SAR图像相干斑的同时很好地保留了SAR图像的几何结构信息，为后续的SAR图像理解与解译奠定了良好的基础。
2.提出了基于自适应各向异性高斯方向窗的非局部三维Otsu图像空域门限分割方法。
针对传统三维最大类间方差（3D-Otsu）门限分割方法中的滤噪性能和小目标保持性能的不足，提出了一种基于各向异性自适应高斯方向窗的3D-Otsu门限分割的新方法。新方法对3D-Otsu的邻域窗口设置方法做了改进，使用中心点的局部平稳特征来自适应地确定邻域各向异性高斯方向加权窗口的尺寸大小、尺度和滤波方向。然后基于非局部多方向相似度测量，从而更有效地捕捉图像中的模式冗余。最终，结合像素点灰度值、加权均值、加权中值构建三维直方图，从而基于最大类间方差计算门限矢量并进行分割。该方法有着更好的门限分割效果，并具有更好的滤噪性能和小目标保持性能。
3.提出了非下采样Brushlet域的基于灰度共生概率和模糊C均值聚类的SAR图像分割方法。
针对传统小波变换域SAR图像分割存在边缘保持和方向分辨率较差的不足，提出了一种在非下采样Brushlet变换域提取图像灰度共生概率特征的新方法。该方法在Brushlet的不同方向系数块中利用自适应窗口的高斯方向窗提取灰度共生概率特征，有效地解决了实际操作中的最优窗口尺寸的选取问题，并利用压缩感知来对冗余的特征进行压缩，降低了聚类复杂度。最后使用模糊C均值聚类，得到分割结果。该方法与其它对比方法相比在边缘保持和方向分辨上有明显优势，获得了更好的分割结果。
4.提出了基于非下采样Brushlet系数和谱聚类集成的SAR图像分割方法。
针对传统小波变换能量系数对边缘保持和方向分辨率较差的不足以及单一谱聚类算法对尺度参数敏感的不足，提出了一种基于非下采样Brushlet变换和谱聚类集成算法的SAR图像分割方法。解决了传统谱聚类算法对尺度参数敏感以及小波域系数特征的方向分辨能力的不足的问题。该方法比传统的随机单尺度参数的谱聚类方法的性能有所改进，并且避免了单一谱聚类中的尺度参数选择问题。分割性能相对于传统的算法有明显优势，并且对图像的边缘和方向性细节保持得较好。
5.提出了基于非下采样Brushlet和SURE-LET准则SAR图像变化检测方法。
针对传统空域两时相SAR图像变化检测存在相邻像素间相似特征捕捉和方向分辨率较差的不足以及SAR图像相干斑噪声建模的困难，提出了一种基于Stein’s无偏风险估计（SURE）阈值线性展开（linear expansion of threshold, LET）和非下采样Brushlet变换的SAR图像二维最大类间方差（2D-otsu）变化检测方法。该方法基于两幅SAR图像的差异图，结合非下采样Brushlet域的各向异性局部高斯非线性加权均值计算和空域最小化均方误差的线性组合来获取相干斑噪声抑制后的均值特征，并结合差异图的灰度特征最终实现变化区域的检测。非下采样Brushlet变换解决了小波角分辨率的问题，可获得各个方向、频率和位置的方向纹理的精确定位。SURE-LET方法不必为原始差异图像假设统计模型，并使得算法仅解决一个线性方程系统，快速而有效。该方法在SAR图像变化检测中优于传统的算法，并且由于非下采样Brushlet变换和各向异性高斯方向窗的引入，能够在变化区域检测的同时很好地保留纹理边缘等细节信息。
Synthetic Aperture Radar (SAR) can obtain high range-resolution by transmittingwideband radar signal and high azimuth-resolution by long synthetic aperture.Therefore, high-resolution SAR image with large-size can be captured. SAR has theability to image the earth’s surface in nearly all weather conditions for long distance.Together with its high spatial resolution, the SAR has a more and more important role atfields of geosciences, hydrology and bionomics, etc. While, the subsequent SAR imageunderstanding is difficult because of the presentation of SAR speckle. Therefore, interm of the observation value of the SAR image, the estimation of the true value of theRadar cross section (RCS) is an important research topic of SAR image pre-processing.These years, the subsequent SAR image segmentation and change detection have moreand more attentions in the Radar signal processing fields.
In this dissertation, the SAR image despeckling technology, SAR imagesegmentation and change detection methods are studied, and a series of practicaleffective methods are proposed. The author’s major contributions are outlined asfollows:
1. The non-local despeckling method for SAR image based on anisotropicGaussian directional window and Stein unbiased risk estimation (SURE) aggregationhas been proposed.
Aimed at the shortage of similar region and directional information capture lack forSAR image despeckling using conventional non-local means method (NLM), a newNLM SAR image despeckling method is proposed based on anisotropic Gaussiandirectional window and Stein unbiased risk estimation (SURE) aggregation. Thismethod is based on multiple different directional anisotropic Gaussian windows, whichcan match the local geometric structure and can capture more pattern redundancy thanthe square window in the conventional NLM. Then, the ratio measurement strategy isutilized to compute the similarity of two patches. Finally, the results of NLM withdifferent anisotropic Gaussian windows are aggregated using the Stein unbiased riskestimation criterion. For multiple SAR images, the experiment results show that the newmethod has advantages in the SAR image despeckling performance, and can wellpreserve the local geometric structure information, which is essential for understandingand interpretation of SAR image.
2. Spatial threshold-segmentation method of SAR image based on adaptiveGaussian weighted directional window and three-dimensional Otsu method has beenproposed.
Aimed at the shortage of the abilities of noise removing and small targetpreservation for the conventional three-dimensional (3D) Otsu thresholding method, a new three-dimensional Otsu method based on adaptive Gaussian weighted directionalwindow is proposed. The new method improves the window setting method of the3DOtsu. The window size, scale and filtering angles are adaptively determined by the localstationarity characters. Then, based on the non-local multiple directions similaritymeasurement, the pattern redundancy in the image can be captured effectively. Finally,the3D histogram is constructed based on the gray value, weighted mean value andweighted median value. And the threshold vector is computed by the maximumbetween-class variance method to segment the image. The proposed method has thebetter segmentation performance, with better performance for noise removal and smalltarget preservation.
3. SAR image segmentation method in overcomplete Brushlet domain based onGray-Level Cooccurrence Probability and Fuzzy C-Mean (FCM) clustering has beenproposed.
Aimed at the shortage of edge preservation and low direction-resolution for SARimage segmentation based on the conventional wavelet transform domain, a newsegmentation method is proposed based on Gray-Level Cooccurrence Probability(GLCP)features in the overcomplete Brushlet domain. This method compresses the redundantGLCP features extracted by the adaptive window Gaussian filtering in differentdirection coefficient blocks using compressed sensing, then the Fuzzy C-Mean (FCM)clustering method is utilized to complete the clustering and obtain the segmentationresult. The experiment results show that the new method has advantages in the edgepreservation and direction extraction, and obtains better segmentation results withrespect to other methods.
4. SAR image segmentation method based on overcomplete Brushlet transform andspectral cluttering ensemble has been proposed.
Aimed at the shortages of edge preservation and low direction-resolution based onthe conventional wavelet transform domain and the sensitivity of the scaling parameterof the spectral cluttering, a new segmentation method is proposed based onovercomplete Brushlet transform and spectral cluttering ensemble. This method solvesthe sensitivity problem of the spectral cluttering and low direction-resolution of thewavelet transform. This method has better performance than the conventional spectralcluttering, and avoids the selection problem of the scaling parameter. The new methodhas better segmentation performance than the conventional methods, and hasadvantages in the preservations of the edge and direction details.
5. SAR image change detection method in overcomplete Brushlet domain based onStein unbiased risk estimation has been studied.
Aimed at the shortage of similarity character capture and low direction-resolutionfor SAR image change detection and the difficult for the modeling of speckle noise, a new2D-otsu SAR image change detection method is proposed based on Stein unbiasedrisk estimation (SURE) and linear expansion of threshold (LET) in the overcompleteBrushlet domain. Based on the diversity image, this method combines the localanisotropic Gaussian weighted nonlinear mean procedure in the overcomplete Brushletdomain and linear combination with the minimum mean squared error in the originaldomain to obtain mean character after the speckle noise is removed. Then, changedetection is processed with combining the mean character and gray-level character. Theovercomplete Brushlet resolves the problem of low direction-resolution, and canaccurate positioning the texture of each direction, frequency and position. The SUREand LET principles together give a fast and efficient algorithm that only solves a linearsystem of equations, without the prior knowledge of the speckle noise model. The newmethod has advantages in the change detection performance, and can well preserve thedetailed information such as the texture edge.
在本论文中，我们对SAR图像的降斑预处理技术，以及后续的SAR图像分割技术和两时相SAR图像变化检测技术进行了系统地研究，并提出了一系列实际有效的SAR图像降斑方法、SAR图像分割方法和两时相SAR图像的变化检测方法，主要研究成果为：
1.提出了基于各向异性高斯窗和SURE准则的非局部SAR图像降斑方法。
针对传统空域非局部均值（Non-local means, NLM）方法在SAR图像相干斑抑制中存在相似区域提取不足和方向信息捕获不足的问题，提出了一种基于各向异性高斯方向窗和史蒂文无偏风险估计（Stein’s unbiased risk estimation, SURE）准则融合的非局部均值算法。该方法利用多个不同方向的各向异性高斯窗来匹配SAR图像的局部空间几何结构，比传统的方形窗能更好地保护SAR图像中的方向性结构。然后，采用比率测度测量策略来衡量两个图像块的相似程度。最终，结合Stein’s无偏风险估计（SURE）准则来融合不同方向的各向异性高斯窗的非局部平均结果。文中针对多幅测试SAR图像进行了对比实验，实验结果表明：提出的方法在有效抑制SAR图像相干斑的同时很好地保留了SAR图像的几何结构信息，为后续的SAR图像理解与解译奠定了良好的基础。
2.提出了基于自适应各向异性高斯方向窗的非局部三维Otsu图像空域门限分割方法。
针对传统三维最大类间方差（3D-Otsu）门限分割方法中的滤噪性能和小目标保持性能的不足，提出了一种基于各向异性自适应高斯方向窗的3D-Otsu门限分割的新方法。新方法对3D-Otsu的邻域窗口设置方法做了改进，使用中心点的局部平稳特征来自适应地确定邻域各向异性高斯方向加权窗口的尺寸大小、尺度和滤波方向。然后基于非局部多方向相似度测量，从而更有效地捕捉图像中的模式冗余。最终，结合像素点灰度值、加权均值、加权中值构建三维直方图，从而基于最大类间方差计算门限矢量并进行分割。该方法有着更好的门限分割效果，并具有更好的滤噪性能和小目标保持性能。
3.提出了非下采样Brushlet域的基于灰度共生概率和模糊C均值聚类的SAR图像分割方法。
针对传统小波变换域SAR图像分割存在边缘保持和方向分辨率较差的不足，提出了一种在非下采样Brushlet变换域提取图像灰度共生概率特征的新方法。该方法在Brushlet的不同方向系数块中利用自适应窗口的高斯方向窗提取灰度共生概率特征，有效地解决了实际操作中的最优窗口尺寸的选取问题，并利用压缩感知来对冗余的特征进行压缩，降低了聚类复杂度。最后使用模糊C均值聚类，得到分割结果。该方法与其它对比方法相比在边缘保持和方向分辨上有明显优势，获得了更好的分割结果。
4.提出了基于非下采样Brushlet系数和谱聚类集成的SAR图像分割方法。
针对传统小波变换能量系数对边缘保持和方向分辨率较差的不足以及单一谱聚类算法对尺度参数敏感的不足，提出了一种基于非下采样Brushlet变换和谱聚类集成算法的SAR图像分割方法。解决了传统谱聚类算法对尺度参数敏感以及小波域系数特征的方向分辨能力的不足的问题。该方法比传统的随机单尺度参数的谱聚类方法的性能有所改进，并且避免了单一谱聚类中的尺度参数选择问题。分割性能相对于传统的算法有明显优势，并且对图像的边缘和方向性细节保持得较好。
5.提出了基于非下采样Brushlet和SURE-LET准则SAR图像变化检测方法。
针对传统空域两时相SAR图像变化检测存在相邻像素间相似特征捕捉和方向分辨率较差的不足以及SAR图像相干斑噪声建模的困难，提出了一种基于Stein’s无偏风险估计（SURE）阈值线性展开（linear expansion of threshold, LET）和非下采样Brushlet变换的SAR图像二维最大类间方差（2D-otsu）变化检测方法。该方法基于两幅SAR图像的差异图，结合非下采样Brushlet域的各向异性局部高斯非线性加权均值计算和空域最小化均方误差的线性组合来获取相干斑噪声抑制后的均值特征，并结合差异图的灰度特征最终实现变化区域的检测。非下采样Brushlet变换解决了小波角分辨率的问题，可获得各个方向、频率和位置的方向纹理的精确定位。SURE-LET方法不必为原始差异图像假设统计模型，并使得算法仅解决一个线性方程系统，快速而有效。该方法在SAR图像变化检测中优于传统的算法，并且由于非下采样Brushlet变换和各向异性高斯方向窗的引入，能够在变化区域检测的同时很好地保留纹理边缘等细节信息。
Synthetic Aperture Radar (SAR) can obtain high range-resolution by transmittingwideband radar signal and high azimuth-resolution by long synthetic aperture.Therefore, high-resolution SAR image with large-size can be captured. SAR has theability to image the earth’s surface in nearly all weather conditions for long distance.Together with its high spatial resolution, the SAR has a more and more important role atfields of geosciences, hydrology and bionomics, etc. While, the subsequent SAR imageunderstanding is difficult because of the presentation of SAR speckle. Therefore, interm of the observation value of the SAR image, the estimation of the true value of theRadar cross section (RCS) is an important research topic of SAR image pre-processing.These years, the subsequent SAR image segmentation and change detection have moreand more attentions in the Radar signal processing fields.
In this dissertation, the SAR image despeckling technology, SAR imagesegmentation and change detection methods are studied, and a series of practicaleffective methods are proposed. The author’s major contributions are outlined asfollows:
1. The non-local despeckling method for SAR image based on anisotropicGaussian directional window and Stein unbiased risk estimation (SURE) aggregationhas been proposed.
Aimed at the shortage of similar region and directional information capture lack forSAR image despeckling using conventional non-local means method (NLM), a newNLM SAR image despeckling method is proposed based on anisotropic Gaussiandirectional window and Stein unbiased risk estimation (SURE) aggregation. Thismethod is based on multiple different directional anisotropic Gaussian windows, whichcan match the local geometric structure and can capture more pattern redundancy thanthe square window in the conventional NLM. Then, the ratio measurement strategy isutilized to compute the similarity of two patches. Finally, the results of NLM withdifferent anisotropic Gaussian windows are aggregated using the Stein unbiased riskestimation criterion. For multiple SAR images, the experiment results show that the newmethod has advantages in the SAR image despeckling performance, and can wellpreserve the local geometric structure information, which is essential for understandingand interpretation of SAR image.
2. Spatial threshold-segmentation method of SAR image based on adaptiveGaussian weighted directional window and three-dimensional Otsu method has beenproposed.
Aimed at the shortage of the abilities of noise removing and small targetpreservation for the conventional three-dimensional (3D) Otsu thresholding method, a new three-dimensional Otsu method based on adaptive Gaussian weighted directionalwindow is proposed. The new method improves the window setting method of the3DOtsu. The window size, scale and filtering angles are adaptively determined by the localstationarity characters. Then, based on the non-local multiple directions similaritymeasurement, the pattern redundancy in the image can be captured effectively. Finally,the3D histogram is constructed based on the gray value, weighted mean value andweighted median value. And the threshold vector is computed by the maximumbetween-class variance method to segment the image. The proposed method has thebetter segmentation performance, with better performance for noise removal and smalltarget preservation.
3. SAR image segmentation method in overcomplete Brushlet domain based onGray-Level Cooccurrence Probability and Fuzzy C-Mean (FCM) clustering has beenproposed.
Aimed at the shortage of edge preservation and low direction-resolution for SARimage segmentation based on the conventional wavelet transform domain, a newsegmentation method is proposed based on Gray-Level Cooccurrence Probability(GLCP)features in the overcomplete Brushlet domain. This method compresses the redundantGLCP features extracted by the adaptive window Gaussian filtering in differentdirection coefficient blocks using compressed sensing, then the Fuzzy C-Mean (FCM)clustering method is utilized to complete the clustering and obtain the segmentationresult. The experiment results show that the new method has advantages in the edgepreservation and direction extraction, and obtains better segmentation results withrespect to other methods.
4. SAR image segmentation method based on overcomplete Brushlet transform andspectral cluttering ensemble has been proposed.
Aimed at the shortages of edge preservation and low direction-resolution based onthe conventional wavelet transform domain and the sensitivity of the scaling parameterof the spectral cluttering, a new segmentation method is proposed based onovercomplete Brushlet transform and spectral cluttering ensemble. This method solvesthe sensitivity problem of the spectral cluttering and low direction-resolution of thewavelet transform. This method has better performance than the conventional spectralcluttering, and avoids the selection problem of the scaling parameter. The new methodhas better segmentation performance than the conventional methods, and hasadvantages in the preservations of the edge and direction details.
5. SAR image change detection method in overcomplete Brushlet domain based onStein unbiased risk estimation has been studied.
Aimed at the shortage of similarity character capture and low direction-resolutionfor SAR image change detection and the difficult for the modeling of speckle noise, a new2D-otsu SAR image change detection method is proposed based on Stein unbiasedrisk estimation (SURE) and linear expansion of threshold (LET) in the overcompleteBrushlet domain. Based on the diversity image, this method combines the localanisotropic Gaussian weighted nonlinear mean procedure in the overcomplete Brushletdomain and linear combination with the minimum mean squared error in the originaldomain to obtain mean character after the speckle noise is removed. Then, changedetection is processed with combining the mean character and gray-level character. Theovercomplete Brushlet resolves the problem of low direction-resolution, and canaccurate positioning the texture of each direction, frequency and position. The SUREand LET principles together give a fast and efficient algorithm that only solves a linearsystem of equations, without the prior knowledge of the speckle noise model. The newmethod has advantages in the change detection performance, and can well preserve thedetailed information such as the texture edge.
引文
[1].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[2].焦李成，张向荣，侯彪.智能SAR图像处理与解译.北京：科学出版社,2009.
[3]. C. J. Oliver. Review article: Information from SAR images. J. Phys. D: Appli.Phys.,1991,24:1493-1514.
[4]. D. R. Wehner. High-Resolution Radar,2nded., Boston, MA: Artech House,1995.
[5].陈国忠. SAR图像纹斑噪声抑制算法研究.博士研究生学位论文.上海交通大学.2008.
[6].崔一.基于SAR图像的目标检测研究.博士研究生学位论文.清华大学.2011.
[7].陈少波. SAR图像相干斑抑制算法研究.博士研究生学位论文.华中科技大学.2010.
[8]. X. R. Zhang, L. C. Jiao, F. Liu, et al. Spectral Clustering Ensemble Applied to SARImage Segmentation. IEEE Trans. Geoscience and Remote Sensing,2008,46(7):2126-2136.
[9]. H. X. Feng, L. C. Jiao, B. Hou. SAR image despeckling based on adaptive windowand shape adaptive discrete wavelet transform. J. Infrared Millim. Waves，2009,28(3):212-217.
[10]. M. Walessa, M. Datcu. Model-based despeckling and information extractionfrom SAR images. IEEE Trans. Geoscience and Remote Sensing,1992,30(5):568-577.
[11]. F. T. Ulaby, F. Kouyate and B. Brisco. Texture information in SAR images.IEEE Trans. Geoscience and Remote Sensing,1986,24:235-245.
[12]. R. K. Raney. SAR response to partially coherent phenomena. IEEE Trans.Antennas Propagat.,1980,26(6):777-787.
[13]. S. N. Madsen. Spectral Properties of Homogeneous and NonhomogeneousRadar Images. IEEE Trans. Aerospace Electronic system,1987,23(4):583-588.
[14]. R. Touzi. Extration of point target response characteristics from complex SARdata. IEEE Trans. Geoscience and Remote Sensing,1992,30(11):1158-1161.
[15]. E. Jakeman. On the statistics of K-distribution noise. J. Phys. C,1980,13:31-48.
[16]. D. J. Lewinski. Nonstationary probabilistic target and clutter scattering models.IEEE Trans. Antennas Propagat.,1983,31:490-498.
[17]. R. S. Saunders, et al. The Magellan Venus Radar Mapping Mission. J. Geophys.Res.,1990,95:8339-8355.
[18]. W. T. K. Johnson. Magellan Imaging Radar Mission to Venus. Proc. of IEEE,1991,79(6):777-790.
[19]. JoBea Way, et al. The Evolution of Synthetic Aperture Radar Systems andTheir Progression to the EOS SAR. IEEE Trans. Geoscience and Remote Sensing,1991,29(6):962-985.
[20]. R. K. Raney. Transfer Functions for Partially Coherent SAR Systems. IEEEIEEE Trans. Aerospace and Electronic system,1983,19(5):740-749.
[21].合成孔径雷达图像处理.孙洪译.电子工业出版社，2005.
[22]. H. Derin, P. A. Kelly, G. Vezina, et al. Modeling and segmentation of speckledimages using complex data. IEEE Trans. Geoscience and Remote Sensing,1990,28(1):76-87.
[23]. H. Hctzhein. Using Martingale represeniation to adapt models for non-linearfiltering. In: Proceeding of International conference on Signal Proeessing. Beijing，China，1993:32-35.
[24]. E. Rignot, R. Chellappa. Segmentation of synthetic-aperture-radar complexdata. Jounal of the optical Society of Amric，1991，A8(9):1499-1509
[25]. B. R. Frieden, A. T. Bajkova. Bayesian cross-entroy reconstruction of compleximages. Applied Optics，1994，33(2):219-226.
[26]. S. Quegan. Parameter estimation for Polarimetric measurements fromvegetated areas. Proc. Third Intemational Workshop on Radar Polarimetry. Nantes，1995:626-635.
[27]. J.W. Goodman. Statistical properties of Laser speckle patterns, Laseer Speckleand Related phenomena. J. C. Daintry (ed), New York: Weley,1972.
[28]. S. J. Lee. Digital image enhaneement and noise filtering by use of localstatisties. IEEE Trans. Pattern analysis and machine Intelligence，1980，2(2):165-168.
[29]. S. V. Frost. A model for radar images and its application to adaptive digitalfiltering of multiplicative noise. IEEE Trans. Pattern analysis and machine Intelligence，1982，4(2):157-166.
[30]. D.T. Kuan， A. A. Sawchuk， T. C. Strand，et al. Adaptive noise smoothingfilter for images with signal-dependent noise. IEEE Trans. Pattern analysis and machineIntelligence，1985，2:165-177.
[31]. A. Lopes， R. Touzi， E. Nezry. Adaptive speckle filters and sceneheterogeneity. IEEE Trans. Geoscience and Remote Sensing，1990，28(6):992-1000.
[32]. S. J. Lee，J. H. Wen， T. L Anisworth， et al. Improved sigma Filter forspeckle filtering of SAR imagery. IEEE Trans. Geoscience and Remote Sensing，2009，47(1):202-213.
[33]. S. Foucher, G. B. Benie. MAP speckle filtering in SAR images. inProc.IGARASS，Washington，DC，1990:1683-1686.
[34]. C. J. Oliver. Review artiele: information from SAR images. J.Phys. D:Appli.Phys，1991，24:1493-1514.
[35]. B. D. Guether, N. George,C. R. Cchristensen, et al. Speckle noise and objectcontrast. Photo sci.and Eng.,1981,21:192-199.
[36]. Y. Hawwar, A. Reza. Spatially adaptive multiplicative noise image denoisingtechnique. IEEE Trans. Image Proeessing,2002,11(12):1397-1404.
[37]. D. L. Donoho. De-noising by soft thresholding. IEEE Trans. Inform. Theory,1995,41:613-627.
[38]. H. Chipman, E. Kolaczyk, R. Mc Culloch. Adaptive bayesian waveletsshringkage. Armer statust. Assoc.,1997,92:1413-1421.
[39]. Y. Dong, B. C. Froster, A. K. Milne, et al. Speckle suppression using recursivewave1ct transforms. International Joural of Remote Sensing,1998,19(2):317-330.
[40]. S. Fukuda, H. hirosawa. Suppression of speckle in synthetic aperature radarimages. International Joumal of Remote Sensing,1998,19(3):507-519.
[41]. S. G. Chang, B. Yu, M. Vetterli. Spatially adaptive wavelet thresholding withcontext modeling for imaging denoising. IEEE Trans. Image Proeessing,2000,9:1522-1523.
[42]. H. Xie, L. E. Pierce, F. T. Ulaby. SAR speckle reduction using waveletdenoising and Markov random field modeling. IEEE Trans. Geoscience and RemoteSensing,2002,40(10):2196-2212.
[43]. Y. Dong, A. K. Milne, B. C. Froster. Toward edge sharpening: a SAR specklefiltering algorithm. IEEE Trans. Geoscience and Remote Sensing,2001,39(4):851-863.
[44]. F. Argenti, L. Alparone. Speckle removal from SAR images in theundecimated wavelet domain. IEEE Trans. Geoscience and Remote Sensing,2002,40(11):2363-2374.
[45]. H. Xie, L. E. Pieree, F. T. Ulaby. Spatially adaptive Radar speckle reductionusing wavelet denoising and Markov Random fields. In proc. IGARSs.2001.
[46].杨晓慧，焦李成，李登峰.基于复Bandelcts的自适应SAR图像相干斑抑制.电子学报，2009，9(37):2575-1555.
[47].励金祥，金炜，杨任尔等.合成孔径雷达图像的contourlet域空间滤波降斑噪声算法.光学技术，2009，2(35):310-314.
[48].王文波，张晓东，费浦生等.基于contourlet变换的自适应sAR图像相干斑噪声抑制算法.光学学报，2009，20(29):2726-2731.
[49]. Y. J. Yu， Action S T. Speckle reduction anisotropic diffusion. IEEETransactions on Image Processing，2002，11(11):1260-1270.
[50]. P. Perona， J. Malik. Scale-space and edge deteetion using anisotropicdiffusion. IEEE Trans. Pattern Analysis and Machine Intelligence，1990，2(7):629-639.
[51]. S. Aja-Femandez， C. Alberola-Lopez. On the estimation of the coefficient ofvariation for anisotropic diffusion speckle filtering. IEEE Trans. Image Processing，2006，15(9):2694-2701.
[52]. K. Karl，C. F. Westin，R. Kikinis，et al. Oriented Speckle Reducing AnisotropicDiffsion. IEEE Trans. Image Proeessing，2006，16(5):1412-1424.
[53]. L. I. Rudin， P. L. Lions， S. Ohser. Multiplicative denoising and deblurring:Theory and algorithims. In S.Osher and N. Paragios, editors， Geothetric Level Sets inImaging Vision， and GraPhics，2003:103-119.
[54]. L. I. Rudin， S. Osher， E. Fatemi. Nonlinear total variation based noiseremoval algorithms. Physica D.，1992，60:259-268.
[55]. G. Aubert, J. F. Aujol. A variational approach to remove multiplicative noise.CMLA，2006-11.
[56]. F. Li， C. M. Shen， L. Pi. A new diffusion-based variational model for imagedenoising and segmentation. Journal of mathematical Imaging and Vision，2006，26:115-125.
[57].黎芳.几何分析方法在图像处理中的应用.博士学位论文.上海:华东师范大学，2007.
[58].邹谋炎.反卷积和信号复原.国防科技图书出版社，2001
[59].孙即祥.数字图象处理.石家庄:河北教育出版社,1993.
[60].劳丽.聚类算法研究及在图像分割中的应用.博士学位论文.广州:华南理工大学,2006.
[61]. Z. Pan, J. Lu. A bayes-based region-growing algorithm for medical imagesegmentation. Comput Sci Eng,2007,9:32-38.
[62]. L. Band. Topographical partition of watersheds with digital elevation models.Water Resources Research,1986,22(1):15-24.
[63]. L. Vincent, P. Soille. Watersheds in digital spaces：an efficient algorithm basedon immersion simulations. IEEE Trans．Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[64]. L. Bertelli, B. Sumengen, B. S. Manjunath, et al. A variational framework formulti-region pairwise similarity-based image segmentation. IEEE Trans. PatternAnalysis and Machine Intelligence,2008,30(8):1400-1414.
[65]. N. Otsu. A threshold selection method from gray-level histogram. IEEE Trans.On System, Man and Cybernetics,1979,9(1):62-66.
[66]. L. G. Shapiro, G. C. Stockman. Computer vision. New Jersey: Prentice Hall,2001.
[67]. O. D. Trier, A. K. Jain. Goal-directed evaluation of binarization methods. IEEETrans. Pattern Anal. Mach. Intell.,1995, PAMI-17:1191-1201.
[68]. J. Bernsen. Dynamic thresholding of gray level images. ICPR'86: Proc. Intl.Conf. Patt. Recog. Paris, France,1986:1251-1255.
[69]. F. Chan, F. Lam, H. Zhu. Adaptive thresholding by variational method. IEEETrans. Image Processing,1991,7:469-473.
[70]. J. Dunn. A fuzzy relative of the ISODATA process and its use in detectingcompact well separated cluster. J Cybemet,1974,3:32-57.
[71]. J. Bezdek. Pattern recognition with fuzzy objective function algorithms. NewYork: Plenum,1981.
[72]. J. Ruspini. A new approach to clustering. Information control,1969,19:22-32.
[73]. J. Bezdek. A convergence theorem for the fuzzy ISODATA clusteringalgorithm. IEEE Trans. Pattern Analysis and Machine Intelligence,1980,1(2):1-8.
[74]. D. Pham. Spatial models for fuzzy clustering. Computer Vision and ImageUnderstanding,2001,84(2):285-297.
[75]. M. Kass, A. Witkin, D. Terzopoulos. Snakes: active contour models.International Journal of Computer Vision,1987,1(4):321-331.
[76].李培华,张田文.主动轮廓线模型(蛇模型)综述.软件学报,2000,11(6):751-757.
[77].陈波,赖剑煌.用于图像分割的活动轮廓模型综述.中国图象图形学报,2007,12(1):11-20.
[78]. L. H. Staib, J. S. Duncan. Boundary fitting with parametrically deformablemodels. IEEE Trans. Pattern Analysis and Machine Intelligence,1992,14(11):1061-1075.
[79]. C. Xu, J. L. Prince. Snakes, shapes and gradient vector flow. IEEE Trans onImaging Processing,1998,7(3):359-369.
[80].闫成新,桑农,张天序.基于图论的图像分割研究进展.计算机工程与应用,2006,42(5):11-14.
[81]. L. A. Zadeh. Fuzzy sets. Information and Control,1965,8(3):338-353.
[82].刘尚旺.基于改进选择性视觉注意模型的语义图像分割研究.博士学位论文.西北农林科技大学.2012.
[83].黄勇. SAR图像变化检测及相关技术研究.博士学位论文.电子科技大学.2006.
[84]. A. Singh. Digital Change Deteetion Technique Using Remotely-Sensed Data，Int. J. of Remote Sensing，10:989-1003.
[85].范海生,马蔼乃,李京.采用图象差值法提取土地利用变化信息方法，遥感学报，2001,5(l):63-67.
[1].刘永坦.雷达成像技术.哈尔滨：哈尔滨工业大学出版社,1999-10：3-4.
[2]. J. C. Curlander, R. H. McDonough. Synthetic Aperture Radar: Systems and SignalProcessing. John Wiley&Sons, Inc. New York.1991.
[3].陈国忠.SAR图像纹斑噪声抑制算法研究.博士学位论文，上海交通大学.2008
[4].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[5].陈少波. SAR图像相干斑抑制算法研究.博士学位论文，华中科技大学.2010.
[6]. K. Tomiyasu. Preliminary Results of a Spectral Analysis of Simulated ComplexPulse Response History of a Synthetic Aperture Radar Pixel. IEEE Trans. Geosci.Remote Sensing.,1984,22(6):577-581.
[7]. C. Elachi. Spaceborne Radar Remote Sensing: Applications and Techniques. IEEEPress,1988.
[8]. R. K. Raney. SAR response to partially coherent phenomena. IEEE Trans. AntennasPropagat.,1980,26(6):777-787.
[9]. R. Touzi. A review of speckle filtering in the context of estimation theory, IEEETrans. Geosci. Remote Sens.2002,40(11):2392-2404.
[10]. B. E. A. Saleh and M. Rabbani. Linear filtering of speckled images. Opt.Commun.,1980,35:327-331.
[11]. A. D. Goldfinger. Estimation of spectra from speckle images. IEEE Trans.Aerospace Elect. Syst.,1982,18:675-681.
[12]. D. T. Kuan, A. A. Sawchuk, T.C. Strand, and P. Chavel. Adaptive noisesmoothing filter for images with signal-depedent noise. IEEE Trans. Pattern Anal.Machine Intell.,1985,2:165-177.
[13]. F. T. Ulaby, F. Kouyate, and B. Brisco. Texture information in SAR images.IEEE Trans. Geosci. Remote Sensing,1986,24:235-245.
[14]. V. S. Frost, J. A. Stiles, et al. A model for radar images and its application toadaptive digital filtering of multiplicative noise. IEEE Trans. Pattern Anal. MachineIntell.,1982,4:157-166.
[15]. J. S. Lee. Digital image enhancement and noise filtering by use of localstatistics. IEEE Trans. Pattern Anal. Machine Intell.,1980,2:165-168.
[16]. E. Jakeman. On the statistics of K-distribution noise. J. Phys. C,1980,13:31-48.
[17]. D. J. Lewinski. Nonstationary probabilistic target and clutter scattering models.IEEE Trans. Antennas Propagat.,1983,31:490-498.
[18]. H. Zhang， Z. T. Jiao， J. Qin， et al. Study on scale scope and regionalconsistency of earth scene heterogeneity. Proc IGARSS’04. Anehorge，AK:IEEE，2004:2643-2646.
[19]. J. Zhu， J. Chen. Information-theoretic heterogeneity analysis for evaluatingthe performances of image fusion techniques. IEEE Tencon’06Proeeedings. Hongkong:IEEE,2006.
[20]. B. Aiazzi， L. Alparone， S. Baronti. Information-therotic heterogeneitymeasurement for SAR imagery. IEEE Trans. Geosci. Remote Sens.,2004,43(3):619-624.
[21]. A. Lopes, R. Touzi, E. Nezry. Adaptive speckle filters and scene heterogeneity.IEEE Trans. Geosci. Remote Sens.,1990,28(6):992-1000.
[22]. M. Beauchemin, K. Thomson，G. Edwards. The ratio of the arithmetic to thegeometric mean: A first-order statistical test for multilook SAR image homogeneity.IEEE Trans. Geosci. Remote Sens.,1996,34(2):604-666.
[23].陈杰，朱晶，周荫清等.复杂目标场景合成孔径雷达图像异质性分析与测
量方法研究.电子学报,2008,36(9):1687-1692.
[1].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[2].焦李成，张向荣，侯彪.智能SAR图像处理与解译.北京：科学出版社,2009.
[3]. C. J. Oliver. Review article: Information from SAR images. J. Phys. D: Appli.Phys.,1991,24:1493-1514.
[4].陈少波. SAR图像相干斑抑制算法研究.博士研究生学位论文.华中科技大学.2010.
[5]. M. Walessa, M. Datcu. Model-based despeckling and information extraction fromSAR images. IEEE Trans. Geosci. Remote Sensing,1992,30(5):568-577.
[6]. Y. Hawwar, A. Reza. Spatially adaptive multiplicative noise image denoisingtechnique. IEEE Trans. Image Proeessing,2002,11(12):1397-1404.
[7]. D. L. Donoho. De-noising by soft thresholding. IEEE Trans. Inform. Theory,1995,41:613-627.
[8]. S. J. Lee. Digital image enhaneement and noise filtering by use of local statisties.IEEE Trans. Pattern analysis and machine Intelligence，1980，2(2):165-168.
[9]. D. T. Kuan， A. A. Sawchuk， T. C. Strand，et al. Adaptive noise smoothing filterfor images with signal-dependent noise. IEEE Trans. Pattem Anal. Machine Intell.，1985，2:165-177.
[10]. S. V. Frost. A model for radar images and its application to adaptive digitalfiltering of multiplicative noise. IEEE Trans. Pattern Analysis and MachineIntelligence，1982，4(2):157-166.
[11]. S. Foucher, G. B. Benie. MAP speckle filtering in SAR images. inProc.IGARASS，Washington，DC，1990:1683-1686.
[12]. Y. Dong, A. K. Milne, B. C. Froster. Toward edge sharpening: a SAR specklefiltering algorithm. IEEE Trans. Geosei. Remote Sensing,2001,39(4):851-863.
[13]. F. Argenti, L. Alparone. Speckle removal from SAR images in theundecimated wavelet domain. IEEE Trans. Geosci. Remote Sensing,2002,40(11):2363-2374.
[14]. H. Xie, L. E. Pieree, F. T. Ulaby. Spatially adaptive Radar speckle reductionusing wavelet denoising and Markov Random fields. In proc. IGARSs.2001.
[15]. J. Zhang, Z. H. Wei. Fractional-order multi-scale variation PDE model andadaptive algorithm for SAR Image Denoising. Journal of Electronics&InformationTechnology，2010，32(7):1654-1659.
[16]. O. V. Lepski, E. Mammen, V. G. spokoiny. Optimal spatial adaptation toinhomogeneous smoothness: an approach based on kernel estimates with variablebandwidth selectors. Ann. Statist,1997,25(3):929-947.
[17]. X. H. Zhang, J. W. Chen, H. Y. Meng, et al. SAR image despeckling: based onnon-local means with non-subsample Shearlet and directional windows. J. InfraredMillim. Waves，2012，31(2):159-165.
[18]. A. Buades, B. Coll, J. Morel. A non local algorithm for image denoising.Computer Vision and Pattern Recognition,2005,2:60-65.
[19]. A. D. Charles, D. Vincent, S. Joseph. Anisotropic non-local means withspatially adaptive patch shapes. Lecture Notes in Computer Science,2012,6667:231-242.
[20]. H. X. Feng, B. Hou, M. G. Gong. SAR image despeckling based on localhomogeneous-region segmentation by using pixel-relativity measurement. IEEE Trans.Geosci. Remote Sensing,2011,49(7):2724-2736.
[21]. D. Gleigh, M. Datcu. Gauss-Markov model for wavelet-based SAR imagedespeckling. IEEE Signal Processing Letters,2006,13(6):365-368.
[22]. C. Kervrann, J. Boulanger. Optimal spatial adaptation for patch-based imagedenoising. IEEE Trans. Image Processing,2006,15(10):2866-2878.
[23]. K. Dabov, A. Foi, V. Katkovnik, et al. Image denoising by sparse3-Dtransform-domain collaborative filtering. IEEE Trans. Image Processing,2007,16(8):2080-2095.
[24]. M. Hebar, et al. Autobinomial model for SAR image despecking andinformation extraction. IEEE Trans. Geosci. Remote Sensing,2009,47(8):2818-2835.
[1].焦李成，张向荣，侯彪.智能SAR图像处理与解译[M].北京：科学出版社,2009
[2].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[3]. H. Derin, P. A. Kelly, G. Vezina, et al. Modeling and segmentation of speckledimages using complex data. IEEE Trans. Geoscience and Remote sensing,1990,28(1):76-87.
[4]. X. R. Zhang, L. C. Jiao, F. Liu, et al. Spectral Clustering Ensemble Applied to SARImage Segmentation. IEEE Trans. Geoscience and Remote Sensing,2008,46(7):2126-2136.
[5]. E. Rignot, R. Chellappa. Segmentation of synthetic-aperture-radar complex data.Jounal of the optical Society of Amric，1991，A8(9):1499-1509
[6]. X. Y. Xu, S. Z. Xu, L. H. Jin. Characteristic analysis of Otsu threshold and itsapplications. Pattern recognition letters,2011,32(7):956-961.
[7]. J. Gong, L. Y. Li, W. N. Chen. Fast recursive algorithm for two-dimensionalthresholding. Pattern recognition,1998,31(3):295-300.
[8].景晓军，李剑峰，刘郁林.一种基于三维最大类间方差的图像分割算法.电子学报,2003,31(9):1281-1285.
[9]. Buades A, Coll B, Morel J. A non local algorithm for image denoising. ComputerVision and Pattern Recognition,2005,2:60-65.
[10].颜学颖，焦李成，王凌霞，万红林.一种提高SAR图像分割性能的新方法.电子与信息学报，2011,33(7):1700-1705.
[11]. W. Wang, J. H. Gao, K. Li. Structure-Adaptive Anisotropic Filter with LocalStructure Tensors. IEEE Computer Society Second International Symposium onIntelligent Technology Application, Shanghai,2008,2:1005-1010
[12]. G. Deng, L.W. Gahill. An adaptive Gaussian filter for noise reduction and edgedetection. Proc. IEEE Nuclear Science Symposium and Medical Imaging conference,San Francisco CA,1993,3:1615-1619.
[13]. W. F. Sun, Y. H. Peng, W. L. Hwang. Modified similarity metric for non-localmeans algorithm. Electronics letters,2009,45(25),1307-1309.
[14]. S. J. Ko, Y. H. Lee. Center weighted median filters and their application toimage enhancement. IEEE Transactions on Circuits and Systems,1991,38(9):984-993.
[15]. N. Wang, X. Li, X. H. Chen. Fast three-dimensional Otsu thresholding withshuffled frog-leaping algorithm. Pattern Recognition Letters,2010,31(1):1809-1815.
[16]. Q. W. Li, S. Y. Yang, S. X. Zhu. Image segmentation based on the2-Dmaximum entropy value and improved genetic algorithm.2011InternationalConference on Computer Science and Network Technology (ICCSNT),2011:1403-1406.
[17].安成锦,牛照东,李志军,陈曾平.典型Otsu算法阈值比较及其SAR图像水域分割性能分析.电子与信息学报,2010,32(9):2215-2219.
[1]. L. Bertelli, B. Sumengen, B. S. Manjunath, et al. A variational framework formulti-region pairwise similarity-based image segmentation. IEEE Trans. PatternAnalysis and Machine Intelligence,2008,30(8):1400-1414.
[2]. N.Otsu. A threshold selection method from gray-level histogram. IEEE Trans. OnSystem, Man and Cybernetics,1979,9(1):62-66.
[3]. H. X. Feng, B. Hou, M. G. Gong. SAR image despeckling based on localhomogeneous-region segmentation by using pixel-relativity measurement. IEEE Trans.Geoscience and Remote Sensing,2011,49(7):2724-2736.
[4]. E. Rignot, R. Chellappa. Segmentation of synthetic-aperture-radar complex data.Jounal of the optical Society of Amric，1991，8(9):1499-1509
[5].安成锦,牛照东,李志军,陈曾平.典型Otsu算法阈值比较及其SAR图像水域分割性能分析.电子与信息学报,2010,32(9):2215-2219.
[6].尹奎英,胡利平,刘宏伟,金林.一种复合的SAR图像去噪算法.西安电子科技大学学报,2010,37(2):224-230.
[7]. X. R. Zhang, L. C. Jiao, F. Liu, et al. Spectral Clustering Ensemble Applied to SARImage Segmentation. IEEE Trans. Geoscience and Remote Sensing,2008,46(7):2126-2136.
[8]. Y. M. Shuai, H. Sun, G. Xu. SAR Image Segmentation Based on Level Set WithStationary Global Minimum. IEEE Geoscience and Remote Sensing Letters,2008,5(4):644-648.
[9]. F. G. Meyer, R. Coifman. Brushlet: a tool for directional image analysis and imagecompression. Applied and Computional Harmonic Analysis,1997,4(2):147-187.
[10]. E. J. Candes. Ridgelet: theory and applications. Ph.D. Thesis, Department ofStatistics, Stanford University,1998.
[11]. E. J. Candes, D. L. Donoho. Curvelets-a surprisingly effective nonadaptiverepresentation for objects with edges. Technical report, Stanford Univ,1999.
[12]. S. Tan, X. R. Zhang, L. C. Jiao. A brushlet–based feature set applied to textureclassification. Int. Conf. on Computational and Information Sciences,2004,1175-1180.
[13]. E. Angelini, A. Laine, S. Takuma, S. Homma. LV volume quantification viaspatiotemporal analysis of real-time3-D echocardiography. IEEE Trans. MedicalImaging,2001,20(6):457-469.
[14].侯彪,刘芳,焦李成.基于脊波变换的直线特征检测,中国科学(E)，2003,33(1):65-73.
[15]. I. Daubechies. Ten lectures on wavelet. SIAM,1992
[16]. M. V. Wickerhauser, Smooth localized orthomormal bases, C.R.Acad.Sci.ParisI,1993:423-427.
[17]. P. Auscher, G. Weiss, M. V. Wickerhauser. Local sine and cosine bases ofcoifman and meyer and the construction of smooth wavelet. In wavelets-a tutorial intheory and applications,1992:237-256.
[18]. M. V. Wickerhauser: Adapted wavelet analysis from theory to software, A. K.Perrers,1995.
[19]. J. M. Li, H. Zhong, L. C. Jiao. SAR image segmentation based onmultiresolution GLCP in overcomplete brushlet domain. IEEE proceeding of2006International Conference on Radar, Oct,2006.
[20]. R. Jobanputra, D. A. Clausi. Texture analysis using Gaussian weighted greylevel co-occurrence probabilities. IEEE Proceedings of the First Canadian Conferenceon Computer and Robot Vision,2004.
[21]. D. A. Clausi, B. Yue. Comparing cooccurrence probabilities and Markovrandom fields for texture analysis of SAR sea ice imagery. IEEE Trans. Geoscience andRemote Sensing,2004,42(1):215-228.
[22]. V. Katkovnik, K. Egiazarian, J. Astola. Adaptive window size imagede-noising based on intersection of confidence intervals (ICI) rule. Journal ofMathematical Imaging and Vision,2002,16(3):223-235.
[23]. J. M. Park, W. J. Song, W. A. Pearlman. Speckle filtering of SAR imagesbased on adaptive windowing. IEE Proceedings of Vision, Image and Signal Process,1999:191-197.
[24]. D. L. Donoho. Compressed Sensing. IEEE Trans. Information Theory,2006,52(4):1289-1306.
[25]. E. Candès, J. Romberg, T. Tao,“Robust uncertainty principles: Exact signalreconstruction from highly incomplete frequency information,” IEEE Trans. Inform.Theory,2006,52(2):489-509.
[26]. David Donoho, Compressed sensing.(IEEE Trans. on Information Theory,52(4), pp.1289-1306, April2006)
[27]. R.G. Baraniuk, M. Davenport, R. DeVore, and M.B. Wakin,“A simple proofof the restricted isometry principle for random matrices (aka the Johnson-Lindenstrausslemma meets compressed sensing),” Constructive Approximation,2007[Online].Available: http://dsp.rice.edu/s/jlcs-v03.pdf
[28]. D. H. Liu, G. M. Shi, J. S. Zhou, et al. New method of multiple descriptioncoding for image based on compressed sensing. J.Infrared Millim. Waves,2009,28(4):298-302.
[29]. J. D. Coker, A. H. Tewfik. Compressed sensing and multistatic SAR. IEEEproceeding of2009International Conference on Acoustics, Speech and SignalProcessing,2009,19(24):1097-1100.
[1]. R. J. Dekker. Texture analysis and classification of ERS SAR images for mapupdating of urban areas in The Netherlands. IEEE Trans. Geosci. Remote Sens.,2003,41(9):1950-1958.
[2]. Q. Zhao, J. C. Principe. Support vector machines for SAR automatic targetrecognition. IEEE Trans. Aerosp. Electron. Syst.,2001,37(2):643-654.
[3]. J. S. Lee, I. Jurkevich. Segmentation of SAR images. IEEE Trans. Geosci. RemoteSens.,1989,27(6):674-680.
[4]. A. E. Zaart, D. Ziou, S. Wang, Q. Jiang. Segmentation of SAR images usingmixture of gamma distribution. Pattern Recognit.,2002,35(3):713-724.
[5]. P. R. Kersten, J.-S. Lee, T. L. Ainsworth. Unsupervised classification ofpolarimetric synthetic aperture radar images using fuzzy clustering and EM clustering,”IEEE Trans. Geosci. Remote Sens.,2005,43(3):519-527.
[6]. W. Chumsamrong, P. Thitimajshima, Y. Rangsanseri. Synthetic aperture radar(SAR) image segmentation using a new modified fuzzy c-means algorithm. in Proc.IEEE Symp. Geosci. Remote Sens., Honolulu, HI,2000:624-626.
[7]. R. Samadani. A finite mixtures algorithm for finding proportions in SAR images.IEEE Trans. Image Process.,1995,4(8):1182-1185.
[8]. Y. Dong, B. C. Forster, A. K. Milne. Comparison of radar image segmentation byGaussian and Gamma-Markov random field models. Int. J. Remote Sens.,2003,24(4):711-722.
[9]. H. Deng, D. A. Clausi. Unsupervised segmentation of synthetic aperture radar seaice imagery using a novel Markov random field model. IEEE Trans. Geosci. RemoteSens.,2005,43(3):528-538.
[10]. C. Lemaréchal, R. Fj rtoft, P. Marthon. SAR image segmentation bymorphological methods. Proc. SPIE,1998,3497:111-121.
[11]. B. Ogor, V. Haese-coat, J. Ronsin. SAR image segmentation by mathematicalmorphology and texture analysis. in Proc. IGARSS,1996:717-719.
[12]. C. Fowlkes, S. Belongie, F. Chung, J.Malik. Spectral grouping using theNystr m method. IEEE Trans. Pattern Anal. Mach. Intell.,2004,26(2):214-225.
[13]. J. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Trans. PatternAnal. Mach. Intell.,2000,22(8):888-905.
[14]. M. Fiedler. Algebraic connectivity of graphs. Czechoslovak Math. J.,1973,23:298-305.
[15]. A. Y. Ng, M. I. Jordan, Y. Weiss. On spectral clustering: Analysis and analgorithm. in Advances in Neural Information Processing Systems (NIPS), vol.14, T.Dietterich, S. Becker, and Z. Ghahramani, Eds. Cambridge, MA: MIT Press,2002.
[16]. C. Ding, X. He, H. Zha, M. Gu, H. Simon. A min-max cut algorithm for graphpartitioning and data clustering. in Proc. IEEE Int. Conf. Data Mining,2001:107-114.
[17]. S. X. Yu, J. Shi. Multiclass spectral clustering. in Proc. Int. Conf. Comput. Vis.,2003,1:313-319.
[18]. F. R. Bach, M. I. Jordan. Blind one-microphone speech separation: A spectrallearning approach. in Advances in Neural Information Processing Systems,2005, vol.17. Cambridge, MA: MIT Press.
[19]. P. K. Chan, M. D. F. Schlag, J. Y. Zien. Spectral k-way ratio-cut partitioningand clustering. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst.,1994,13(9):1088-1096.
[20]. L. Zelnik-Manor, P. Perona. Self-tuning spectral clustering. in Advances inNeural Information Processing Systems, vol.17, L. K. Saul, Y. Weiss, and L. Bottou,Eds. Cambridge, MA: MIT Press,2005.
[21]. M. Breitenbach, G. Z. Grudic. Clustering through ranking on manifolds. inProc.22nd Int. Conf. Mach. Learn., Bonn, Germany,2005:73-80.
[22]. A. Krogh, J. Vedelsby. Neural network ensembles, cross validation, and activelearning. in Advances in Neural Information Processing Systems. Cambridge, MA: MITPress,1995:231–238.
[23]. L. Hansen, P. Salamon.Neural network ensembles. IEEE Trans. Pattern Anal.Mach. Intell.,1990,12(10):993-1001.
[24]. A. Strehl, J. Ghosh. Cluster ensembles—A knowledge reuse framework forcombining multiple partitions, J. Mach. Learn. Res.,2002,3(3):583-617.
[25]. X. Z. Fern, C. E. Brodley. Random projection for high dimensional dataclustering: A cluster ensemble approach. in Proc.20th Int. Conf. Mach. Learn.,2003:186-193.
[26]. T. K. Ho. The random subspace method for constructing decision forests. IEEETrans. Pattern Anal. Mach. Intell.,1998,20(8):832-844.
[27]. A. H. S. Solberg, A. K. Jain. Texture fusion and feature selection applied toSAR imagery. IEEE Trans. Geosci. Remote Sens.,1997,35(2):475-479.
[28]. R. M. Haralick, K. Shanmugam, I. Dinstein. Textural features for imageclassification. IEEE Trans. Syst., Man, Cybern.,1973,3(6):610-621.
[29]. F. G. Meyer, R. Coifman. Brushlet: a tool for directional image analysis andimage compression. Applied and Computional Harmonic Analysis,1997,4(2):147-187.
[30]. D. A. Clausi, B. Yue. Comparing cooccurrence probabilities and Markovrandom fields for texture analysis of SAR sea ice imagery. IEEE Trans. Geosci. RemoteSens.,2004,42(1):215-228.
[31]. D. A. Clausi, Y. Zhao. Rapid extraction of image texture by cooccurrenceusing a hybrid data structure. Comput. Geosci.,2002,28(6):763-774.
[32]. D. G. Barber, E. F. LeDrew. SAR sea ice discrimination using texture statistics:A multivariate approach. Photogramm. Eng. Remote Sens.,1991,57(4):385-395.
[33]. D. A. Clausi. An analysis of co-occurrence texture statistics as a function ofgrey level quantization. Can. J. Remote Sens.,2002,28(1):45-62.
[34]. L. J. Du, J. S. Lee, K. Hoppel, S. A. Mango. Segmentation of SAR imagesusing the wavelet transform. Int. J. Imaging Syst. Technol.,1992,4(4):319-329.
[35]. L. Breiman. Bagging predictors. Mach. Learn.,1996,24(2):123-140.
[36]. Y. Freund. Boosting a weak learning algorithm by majority. Inf. Comput.,1995,121(2):256-285.
[37]. A. Topchy, A. K. Jain, W. Punch. A mixture model for clustering ensembles. inProc. SIAM Int. Conf. Data Mining,2004:379-390.
[38]. M. H. C. Law, A. P. Topchy, A. K. Jain. Multiobjective data clustering. in Proc.IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog.,2004,2:424-430.
[39]. S. Dudoit, J. Fridlyand. Bagging to improve the accuracy of a clusteringprocedure. Bioinformatics,2003,19(9):1090-1099.
[40]. A. Topchy, B. Minaei-Bidgoli, A. K. Jain, W. Punch. Adaptive clusteringensembles. in Proc. Int. Conf. Pattern Recog., Cambridge, U.K.,2004:272-275.
[41]. A. L. N. Fred. Finding consistent clusters in data partitions. in Proc.3rd Int.Workshop Multiple Classifier Syst., F. Roli and J. Kittler, Eds.,2001,2364:309-318.
[42]. A. L. N. Fred, A. K. Jain. Combining multiple clusterings using evidenceaccumulation. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(6):835-850.
[43]. Y. Jiang, Z.-H. Zhou. SOM ensemble-based image segmentation. NeuralProcess. Lett.,2004,20(3):171-178.
[44]. V. Vapnik. The Nature of Statistical Learning Theory. Berlin, Germany:Springer-Verlag,1999.
[45]. C. Blake, E. Keogh, C. J. Merz. UCI Repository of Machine LearningDatabases. Irvine, CA: Dept. Inf. Comput. Sci., Univ. California,1998.[Online].Available: http://www.ics.uci.edu/~mlearn/MLRepository.html
[46]. C. Carincotte, S. Derrode, S. Bourennance. Unsupervised change detection on
SAR images using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens.,
2006,44(2):432-441.
[1]. L. M. Novak. Coherent change detection for Multi-polarization SAR, Proceedings39thAsilomar Conference on Signals, Systems and Computers,2005:568-573.
[2]. L. Novak, C. Frost. Effects of SAR image compression on coherent changedetection. SPIE conference on Algorithms for SAR. Orlando, FL., April2009.
[3]. F. F. Xin, L. C. Jiao, G. T. Wang. SAR image change detection based on Memeticalgorithm. J.Infrared Millim.Waves,2012,31(1):61-66.
[4]. H. L. Wan, L. C. Jiao. Change detection in SAR images by means of groupingconnected regions using the clone selection algorithm. Electronics letters,2011,46(5):338-339.
[5]. Y. Bazi, F. Melgani, L. Bruzzone, et al. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imagery. InternationalJournal of Remote Sensing,2009,30(24):6591-6610.
[6]. T. Celik. Bayesian change detection based on spatial sampling and Gaussianmixture model. Pattern Recognition Letter,2011,32(12):1635-1642.
[7]. G. Moser, S. Serpico. Unsupervised change detection from multichannel SAR databy Markovian data fusion. IEEE Trans. Geoscience and Remote Sensing,2009,47(7):2114-2128.
[8]. F. Bovolo, L. Bruzzone. A Detail-Preserving Scalse-Driven Approach to ChangeDetection in Multitemporal SAR Images. IEEE Trans. Geosci. Remote Sens.2005,43(12),2963–2972.
[9]. J. Inglada, G. Mercier. A new statistical similarity measure for change detection inmultitemporal SAR images and its extension to multiscale change analysis. IEEE Trans.Geosci Remote Sens2007;45(5):1432-1445.
[10]. G. Meyer, R. coifman. Brushlet: a tool for directional image analysis andimage compression. Applied and Computional Harmonic Analysis,1997,4(2):147-187.
[11]. J. M. Li, H. Zhong, L. C. Jiao. SAR image segmentation based onmultiresolution GLCP in overcomplete brushlet domain. IEEE proceeding of2006International Conference on Radar, Oct,2006.
[12]. T. Blu, F. Luisier. The SURE-LET Approach to Image Denoising. IEEE Trans.on Image Processing,2007,16(11),2778-2786.
[13]. W. Zeng, L. Zhou, X. B. Jiang, et al. Clustering Based Image Denoising UsingSURE-LET.2011Seventh International Conference on Computational Intelligence andSecurity,2011:1303-1307.
[14]. F. Luisier, T. Blu, M. Unser. SURE-LET for Orthonormal Wavelet-DomainVideo Denoising. IEEE Trans. on Circuits and Systems for Video Technology,2010,20(6),913-919
[15]. D. A. Clausi, B. Yue. Comparing cooccurrence probabilities and Markovrandom fields for texture analysis of SAR sea ice imagery. IEEE Trans. on Geoscienceand Remote Sensing,2004,42(1):215-228.
[16]. R. Jobanputra, D. A. Clausi. Texture analysis using Gaussian weighted greylevel co-occurrence probabilities. IEEE Proceedings of the First Canadian Conferenceon Computer and Robot Vision,2004.
[17]. X. Y. Xu, S. Z. Xu, L. H. Jin, et al. Characteristic analysis of Otsu thresholdand its applications. Pattern Recognition Letters,2011,32(7):956-961.
[18]. Otsu N. A threshold selection method from gray-level histogram. IEEE Trans.On System, Man and Cybernetics,1979,9(1):62-66.
[2].焦李成，张向荣，侯彪.智能SAR图像处理与解译.北京：科学出版社,2009.
[3]. C. J. Oliver. Review article: Information from SAR images. J. Phys. D: Appli.Phys.,1991,24:1493-1514.
[4]. D. R. Wehner. High-Resolution Radar,2nded., Boston, MA: Artech House,1995.
[5].陈国忠. SAR图像纹斑噪声抑制算法研究.博士研究生学位论文.上海交通大学.2008.
[6].崔一.基于SAR图像的目标检测研究.博士研究生学位论文.清华大学.2011.
[7].陈少波. SAR图像相干斑抑制算法研究.博士研究生学位论文.华中科技大学.2010.
[8]. X. R. Zhang, L. C. Jiao, F. Liu, et al. Spectral Clustering Ensemble Applied to SARImage Segmentation. IEEE Trans. Geoscience and Remote Sensing,2008,46(7):2126-2136.
[9]. H. X. Feng, L. C. Jiao, B. Hou. SAR image despeckling based on adaptive windowand shape adaptive discrete wavelet transform. J. Infrared Millim. Waves，2009,28(3):212-217.
[10]. M. Walessa, M. Datcu. Model-based despeckling and information extractionfrom SAR images. IEEE Trans. Geoscience and Remote Sensing,1992,30(5):568-577.
[11]. F. T. Ulaby, F. Kouyate and B. Brisco. Texture information in SAR images.IEEE Trans. Geoscience and Remote Sensing,1986,24:235-245.
[12]. R. K. Raney. SAR response to partially coherent phenomena. IEEE Trans.Antennas Propagat.,1980,26(6):777-787.
[13]. S. N. Madsen. Spectral Properties of Homogeneous and NonhomogeneousRadar Images. IEEE Trans. Aerospace Electronic system,1987,23(4):583-588.
[14]. R. Touzi. Extration of point target response characteristics from complex SARdata. IEEE Trans. Geoscience and Remote Sensing,1992,30(11):1158-1161.
[15]. E. Jakeman. On the statistics of K-distribution noise. J. Phys. C,1980,13:31-48.
[16]. D. J. Lewinski. Nonstationary probabilistic target and clutter scattering models.IEEE Trans. Antennas Propagat.,1983,31:490-498.
[17]. R. S. Saunders, et al. The Magellan Venus Radar Mapping Mission. J. Geophys.Res.,1990,95:8339-8355.
[18]. W. T. K. Johnson. Magellan Imaging Radar Mission to Venus. Proc. of IEEE,1991,79(6):777-790.
[19]. JoBea Way, et al. The Evolution of Synthetic Aperture Radar Systems andTheir Progression to the EOS SAR. IEEE Trans. Geoscience and Remote Sensing,1991,29(6):962-985.
[20]. R. K. Raney. Transfer Functions for Partially Coherent SAR Systems. IEEEIEEE Trans. Aerospace and Electronic system,1983,19(5):740-749.
[21].合成孔径雷达图像处理.孙洪译.电子工业出版社，2005.
[22]. H. Derin, P. A. Kelly, G. Vezina, et al. Modeling and segmentation of speckledimages using complex data. IEEE Trans. Geoscience and Remote Sensing,1990,28(1):76-87.
[23]. H. Hctzhein. Using Martingale represeniation to adapt models for non-linearfiltering. In: Proceeding of International conference on Signal Proeessing. Beijing，China，1993:32-35.
[24]. E. Rignot, R. Chellappa. Segmentation of synthetic-aperture-radar complexdata. Jounal of the optical Society of Amric，1991，A8(9):1499-1509
[25]. B. R. Frieden, A. T. Bajkova. Bayesian cross-entroy reconstruction of compleximages. Applied Optics，1994，33(2):219-226.
[26]. S. Quegan. Parameter estimation for Polarimetric measurements fromvegetated areas. Proc. Third Intemational Workshop on Radar Polarimetry. Nantes，1995:626-635.
[27]. J.W. Goodman. Statistical properties of Laser speckle patterns, Laseer Speckleand Related phenomena. J. C. Daintry (ed), New York: Weley,1972.
[28]. S. J. Lee. Digital image enhaneement and noise filtering by use of localstatisties. IEEE Trans. Pattern analysis and machine Intelligence，1980，2(2):165-168.
[29]. S. V. Frost. A model for radar images and its application to adaptive digitalfiltering of multiplicative noise. IEEE Trans. Pattern analysis and machine Intelligence，1982，4(2):157-166.
[30]. D.T. Kuan， A. A. Sawchuk， T. C. Strand，et al. Adaptive noise smoothingfilter for images with signal-dependent noise. IEEE Trans. Pattern analysis and machineIntelligence，1985，2:165-177.
[31]. A. Lopes， R. Touzi， E. Nezry. Adaptive speckle filters and sceneheterogeneity. IEEE Trans. Geoscience and Remote Sensing，1990，28(6):992-1000.
[32]. S. J. Lee，J. H. Wen， T. L Anisworth， et al. Improved sigma Filter forspeckle filtering of SAR imagery. IEEE Trans. Geoscience and Remote Sensing，2009，47(1):202-213.
[33]. S. Foucher, G. B. Benie. MAP speckle filtering in SAR images. inProc.IGARASS，Washington，DC，1990:1683-1686.
[34]. C. J. Oliver. Review artiele: information from SAR images. J.Phys. D:Appli.Phys，1991，24:1493-1514.
[35]. B. D. Guether, N. George,C. R. Cchristensen, et al. Speckle noise and objectcontrast. Photo sci.and Eng.,1981,21:192-199.
[36]. Y. Hawwar, A. Reza. Spatially adaptive multiplicative noise image denoisingtechnique. IEEE Trans. Image Proeessing,2002,11(12):1397-1404.
[37]. D. L. Donoho. De-noising by soft thresholding. IEEE Trans. Inform. Theory,1995,41:613-627.
[38]. H. Chipman, E. Kolaczyk, R. Mc Culloch. Adaptive bayesian waveletsshringkage. Armer statust. Assoc.,1997,92:1413-1421.
[39]. Y. Dong, B. C. Froster, A. K. Milne, et al. Speckle suppression using recursivewave1ct transforms. International Joural of Remote Sensing,1998,19(2):317-330.
[40]. S. Fukuda, H. hirosawa. Suppression of speckle in synthetic aperature radarimages. International Joumal of Remote Sensing,1998,19(3):507-519.
[41]. S. G. Chang, B. Yu, M. Vetterli. Spatially adaptive wavelet thresholding withcontext modeling for imaging denoising. IEEE Trans. Image Proeessing,2000,9:1522-1523.
[42]. H. Xie, L. E. Pierce, F. T. Ulaby. SAR speckle reduction using waveletdenoising and Markov random field modeling. IEEE Trans. Geoscience and RemoteSensing,2002,40(10):2196-2212.
[43]. Y. Dong, A. K. Milne, B. C. Froster. Toward edge sharpening: a SAR specklefiltering algorithm. IEEE Trans. Geoscience and Remote Sensing,2001,39(4):851-863.
[44]. F. Argenti, L. Alparone. Speckle removal from SAR images in theundecimated wavelet domain. IEEE Trans. Geoscience and Remote Sensing,2002,40(11):2363-2374.
[45]. H. Xie, L. E. Pieree, F. T. Ulaby. Spatially adaptive Radar speckle reductionusing wavelet denoising and Markov Random fields. In proc. IGARSs.2001.
[46].杨晓慧，焦李成，李登峰.基于复Bandelcts的自适应SAR图像相干斑抑制.电子学报，2009，9(37):2575-1555.
[47].励金祥，金炜，杨任尔等.合成孔径雷达图像的contourlet域空间滤波降斑噪声算法.光学技术，2009，2(35):310-314.
[48].王文波，张晓东，费浦生等.基于contourlet变换的自适应sAR图像相干斑噪声抑制算法.光学学报，2009，20(29):2726-2731.
[49]. Y. J. Yu， Action S T. Speckle reduction anisotropic diffusion. IEEETransactions on Image Processing，2002，11(11):1260-1270.
[50]. P. Perona， J. Malik. Scale-space and edge deteetion using anisotropicdiffusion. IEEE Trans. Pattern Analysis and Machine Intelligence，1990，2(7):629-639.
[51]. S. Aja-Femandez， C. Alberola-Lopez. On the estimation of the coefficient ofvariation for anisotropic diffusion speckle filtering. IEEE Trans. Image Processing，2006，15(9):2694-2701.
[52]. K. Karl，C. F. Westin，R. Kikinis，et al. Oriented Speckle Reducing AnisotropicDiffsion. IEEE Trans. Image Proeessing，2006，16(5):1412-1424.
[53]. L. I. Rudin， P. L. Lions， S. Ohser. Multiplicative denoising and deblurring:Theory and algorithims. In S.Osher and N. Paragios, editors， Geothetric Level Sets inImaging Vision， and GraPhics，2003:103-119.
[54]. L. I. Rudin， S. Osher， E. Fatemi. Nonlinear total variation based noiseremoval algorithms. Physica D.，1992，60:259-268.
[55]. G. Aubert, J. F. Aujol. A variational approach to remove multiplicative noise.CMLA，2006-11.
[56]. F. Li， C. M. Shen， L. Pi. A new diffusion-based variational model for imagedenoising and segmentation. Journal of mathematical Imaging and Vision，2006，26:115-125.
[57].黎芳.几何分析方法在图像处理中的应用.博士学位论文.上海:华东师范大学，2007.
[58].邹谋炎.反卷积和信号复原.国防科技图书出版社，2001
[59].孙即祥.数字图象处理.石家庄:河北教育出版社,1993.
[60].劳丽.聚类算法研究及在图像分割中的应用.博士学位论文.广州:华南理工大学,2006.
[61]. Z. Pan, J. Lu. A bayes-based region-growing algorithm for medical imagesegmentation. Comput Sci Eng,2007,9:32-38.
[62]. L. Band. Topographical partition of watersheds with digital elevation models.Water Resources Research,1986,22(1):15-24.
[63]. L. Vincent, P. Soille. Watersheds in digital spaces：an efficient algorithm basedon immersion simulations. IEEE Trans．Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[64]. L. Bertelli, B. Sumengen, B. S. Manjunath, et al. A variational framework formulti-region pairwise similarity-based image segmentation. IEEE Trans. PatternAnalysis and Machine Intelligence,2008,30(8):1400-1414.
[65]. N. Otsu. A threshold selection method from gray-level histogram. IEEE Trans.On System, Man and Cybernetics,1979,9(1):62-66.
[66]. L. G. Shapiro, G. C. Stockman. Computer vision. New Jersey: Prentice Hall,2001.
[67]. O. D. Trier, A. K. Jain. Goal-directed evaluation of binarization methods. IEEETrans. Pattern Anal. Mach. Intell.,1995, PAMI-17:1191-1201.
[68]. J. Bernsen. Dynamic thresholding of gray level images. ICPR'86: Proc. Intl.Conf. Patt. Recog. Paris, France,1986:1251-1255.
[69]. F. Chan, F. Lam, H. Zhu. Adaptive thresholding by variational method. IEEETrans. Image Processing,1991,7:469-473.
[70]. J. Dunn. A fuzzy relative of the ISODATA process and its use in detectingcompact well separated cluster. J Cybemet,1974,3:32-57.
[71]. J. Bezdek. Pattern recognition with fuzzy objective function algorithms. NewYork: Plenum,1981.
[72]. J. Ruspini. A new approach to clustering. Information control,1969,19:22-32.
[73]. J. Bezdek. A convergence theorem for the fuzzy ISODATA clusteringalgorithm. IEEE Trans. Pattern Analysis and Machine Intelligence,1980,1(2):1-8.
[74]. D. Pham. Spatial models for fuzzy clustering. Computer Vision and ImageUnderstanding,2001,84(2):285-297.
[75]. M. Kass, A. Witkin, D. Terzopoulos. Snakes: active contour models.International Journal of Computer Vision,1987,1(4):321-331.
[76].李培华,张田文.主动轮廓线模型(蛇模型)综述.软件学报,2000,11(6):751-757.
[77].陈波,赖剑煌.用于图像分割的活动轮廓模型综述.中国图象图形学报,2007,12(1):11-20.
[78]. L. H. Staib, J. S. Duncan. Boundary fitting with parametrically deformablemodels. IEEE Trans. Pattern Analysis and Machine Intelligence,1992,14(11):1061-1075.
[79]. C. Xu, J. L. Prince. Snakes, shapes and gradient vector flow. IEEE Trans onImaging Processing,1998,7(3):359-369.
[80].闫成新,桑农,张天序.基于图论的图像分割研究进展.计算机工程与应用,2006,42(5):11-14.
[81]. L. A. Zadeh. Fuzzy sets. Information and Control,1965,8(3):338-353.
[82].刘尚旺.基于改进选择性视觉注意模型的语义图像分割研究.博士学位论文.西北农林科技大学.2012.
[83].黄勇. SAR图像变化检测及相关技术研究.博士学位论文.电子科技大学.2006.
[84]. A. Singh. Digital Change Deteetion Technique Using Remotely-Sensed Data，Int. J. of Remote Sensing，10:989-1003.
[85].范海生,马蔼乃,李京.采用图象差值法提取土地利用变化信息方法，遥感学报，2001,5(l):63-67.
[1].刘永坦.雷达成像技术.哈尔滨：哈尔滨工业大学出版社,1999-10：3-4.
[2]. J. C. Curlander, R. H. McDonough. Synthetic Aperture Radar: Systems and SignalProcessing. John Wiley&Sons, Inc. New York.1991.
[3].陈国忠.SAR图像纹斑噪声抑制算法研究.博士学位论文，上海交通大学.2008
[4].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[5].陈少波. SAR图像相干斑抑制算法研究.博士学位论文，华中科技大学.2010.
[6]. K. Tomiyasu. Preliminary Results of a Spectral Analysis of Simulated ComplexPulse Response History of a Synthetic Aperture Radar Pixel. IEEE Trans. Geosci.Remote Sensing.,1984,22(6):577-581.
[7]. C. Elachi. Spaceborne Radar Remote Sensing: Applications and Techniques. IEEEPress,1988.
[8]. R. K. Raney. SAR response to partially coherent phenomena. IEEE Trans. AntennasPropagat.,1980,26(6):777-787.
[9]. R. Touzi. A review of speckle filtering in the context of estimation theory, IEEETrans. Geosci. Remote Sens.2002,40(11):2392-2404.
[10]. B. E. A. Saleh and M. Rabbani. Linear filtering of speckled images. Opt.Commun.,1980,35:327-331.
[11]. A. D. Goldfinger. Estimation of spectra from speckle images. IEEE Trans.Aerospace Elect. Syst.,1982,18:675-681.
[12]. D. T. Kuan, A. A. Sawchuk, T.C. Strand, and P. Chavel. Adaptive noisesmoothing filter for images with signal-depedent noise. IEEE Trans. Pattern Anal.Machine Intell.,1985,2:165-177.
[13]. F. T. Ulaby, F. Kouyate, and B. Brisco. Texture information in SAR images.IEEE Trans. Geosci. Remote Sensing,1986,24:235-245.
[14]. V. S. Frost, J. A. Stiles, et al. A model for radar images and its application toadaptive digital filtering of multiplicative noise. IEEE Trans. Pattern Anal. MachineIntell.,1982,4:157-166.
[15]. J. S. Lee. Digital image enhancement and noise filtering by use of localstatistics. IEEE Trans. Pattern Anal. Machine Intell.,1980,2:165-168.
[16]. E. Jakeman. On the statistics of K-distribution noise. J. Phys. C,1980,13:31-48.
[17]. D. J. Lewinski. Nonstationary probabilistic target and clutter scattering models.IEEE Trans. Antennas Propagat.,1983,31:490-498.
[18]. H. Zhang， Z. T. Jiao， J. Qin， et al. Study on scale scope and regionalconsistency of earth scene heterogeneity. Proc IGARSS’04. Anehorge，AK:IEEE，2004:2643-2646.
[19]. J. Zhu， J. Chen. Information-theoretic heterogeneity analysis for evaluatingthe performances of image fusion techniques. IEEE Tencon’06Proeeedings. Hongkong:IEEE,2006.
[20]. B. Aiazzi， L. Alparone， S. Baronti. Information-therotic heterogeneitymeasurement for SAR imagery. IEEE Trans. Geosci. Remote Sens.,2004,43(3):619-624.
[21]. A. Lopes, R. Touzi, E. Nezry. Adaptive speckle filters and scene heterogeneity.IEEE Trans. Geosci. Remote Sens.,1990,28(6):992-1000.
[22]. M. Beauchemin, K. Thomson，G. Edwards. The ratio of the arithmetic to thegeometric mean: A first-order statistical test for multilook SAR image homogeneity.IEEE Trans. Geosci. Remote Sens.,1996,34(2):604-666.
[23].陈杰，朱晶，周荫清等.复杂目标场景合成孔径雷达图像异质性分析与测
量方法研究.电子学报,2008,36(9):1687-1692.
[1].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[2].焦李成，张向荣，侯彪.智能SAR图像处理与解译.北京：科学出版社,2009.
[3]. C. J. Oliver. Review article: Information from SAR images. J. Phys. D: Appli.Phys.,1991,24:1493-1514.
[4].陈少波. SAR图像相干斑抑制算法研究.博士研究生学位论文.华中科技大学.2010.
[5]. M. Walessa, M. Datcu. Model-based despeckling and information extraction fromSAR images. IEEE Trans. Geosci. Remote Sensing,1992,30(5):568-577.
[6]. Y. Hawwar, A. Reza. Spatially adaptive multiplicative noise image denoisingtechnique. IEEE Trans. Image Proeessing,2002,11(12):1397-1404.
[7]. D. L. Donoho. De-noising by soft thresholding. IEEE Trans. Inform. Theory,1995,41:613-627.
[8]. S. J. Lee. Digital image enhaneement and noise filtering by use of local statisties.IEEE Trans. Pattern analysis and machine Intelligence，1980，2(2):165-168.
[9]. D. T. Kuan， A. A. Sawchuk， T. C. Strand，et al. Adaptive noise smoothing filterfor images with signal-dependent noise. IEEE Trans. Pattem Anal. Machine Intell.，1985，2:165-177.
[10]. S. V. Frost. A model for radar images and its application to adaptive digitalfiltering of multiplicative noise. IEEE Trans. Pattern Analysis and MachineIntelligence，1982，4(2):157-166.
[11]. S. Foucher, G. B. Benie. MAP speckle filtering in SAR images. inProc.IGARASS，Washington，DC，1990:1683-1686.
[12]. Y. Dong, A. K. Milne, B. C. Froster. Toward edge sharpening: a SAR specklefiltering algorithm. IEEE Trans. Geosei. Remote Sensing,2001,39(4):851-863.
[13]. F. Argenti, L. Alparone. Speckle removal from SAR images in theundecimated wavelet domain. IEEE Trans. Geosci. Remote Sensing,2002,40(11):2363-2374.
[14]. H. Xie, L. E. Pieree, F. T. Ulaby. Spatially adaptive Radar speckle reductionusing wavelet denoising and Markov Random fields. In proc. IGARSs.2001.
[15]. J. Zhang, Z. H. Wei. Fractional-order multi-scale variation PDE model andadaptive algorithm for SAR Image Denoising. Journal of Electronics&InformationTechnology，2010，32(7):1654-1659.
[16]. O. V. Lepski, E. Mammen, V. G. spokoiny. Optimal spatial adaptation toinhomogeneous smoothness: an approach based on kernel estimates with variablebandwidth selectors. Ann. Statist,1997,25(3):929-947.
[17]. X. H. Zhang, J. W. Chen, H. Y. Meng, et al. SAR image despeckling: based onnon-local means with non-subsample Shearlet and directional windows. J. InfraredMillim. Waves，2012，31(2):159-165.
[18]. A. Buades, B. Coll, J. Morel. A non local algorithm for image denoising.Computer Vision and Pattern Recognition,2005,2:60-65.
[19]. A. D. Charles, D. Vincent, S. Joseph. Anisotropic non-local means withspatially adaptive patch shapes. Lecture Notes in Computer Science,2012,6667:231-242.
[20]. H. X. Feng, B. Hou, M. G. Gong. SAR image despeckling based on localhomogeneous-region segmentation by using pixel-relativity measurement. IEEE Trans.Geosci. Remote Sensing,2011,49(7):2724-2736.
[21]. D. Gleigh, M. Datcu. Gauss-Markov model for wavelet-based SAR imagedespeckling. IEEE Signal Processing Letters,2006,13(6):365-368.
[22]. C. Kervrann, J. Boulanger. Optimal spatial adaptation for patch-based imagedenoising. IEEE Trans. Image Processing,2006,15(10):2866-2878.
[23]. K. Dabov, A. Foi, V. Katkovnik, et al. Image denoising by sparse3-Dtransform-domain collaborative filtering. IEEE Trans. Image Processing,2007,16(8):2080-2095.
[24]. M. Hebar, et al. Autobinomial model for SAR image despecking andinformation extraction. IEEE Trans. Geosci. Remote Sensing,2009,47(8):2818-2835.
[1].焦李成，张向荣，侯彪.智能SAR图像处理与解译[M].北京：科学出版社,2009
[2].张澄波.综合孔径雷达.科学出版社，1989:3-8.
[3]. H. Derin, P. A. Kelly, G. Vezina, et al. Modeling and segmentation of speckledimages using complex data. IEEE Trans. Geoscience and Remote sensing,1990,28(1):76-87.
[4]. X. R. Zhang, L. C. Jiao, F. Liu, et al. Spectral Clustering Ensemble Applied to SARImage Segmentation. IEEE Trans. Geoscience and Remote Sensing,2008,46(7):2126-2136.
[5]. E. Rignot, R. Chellappa. Segmentation of synthetic-aperture-radar complex data.Jounal of the optical Society of Amric，1991，A8(9):1499-1509
[6]. X. Y. Xu, S. Z. Xu, L. H. Jin. Characteristic analysis of Otsu threshold and itsapplications. Pattern recognition letters,2011,32(7):956-961.
[7]. J. Gong, L. Y. Li, W. N. Chen. Fast recursive algorithm for two-dimensionalthresholding. Pattern recognition,1998,31(3):295-300.
[8].景晓军，李剑峰，刘郁林.一种基于三维最大类间方差的图像分割算法.电子学报,2003,31(9):1281-1285.
[9]. Buades A, Coll B, Morel J. A non local algorithm for image denoising. ComputerVision and Pattern Recognition,2005,2:60-65.
[10].颜学颖，焦李成，王凌霞，万红林.一种提高SAR图像分割性能的新方法.电子与信息学报，2011,33(7):1700-1705.
[11]. W. Wang, J. H. Gao, K. Li. Structure-Adaptive Anisotropic Filter with LocalStructure Tensors. IEEE Computer Society Second International Symposium onIntelligent Technology Application, Shanghai,2008,2:1005-1010
[12]. G. Deng, L.W. Gahill. An adaptive Gaussian filter for noise reduction and edgedetection. Proc. IEEE Nuclear Science Symposium and Medical Imaging conference,San Francisco CA,1993,3:1615-1619.
[13]. W. F. Sun, Y. H. Peng, W. L. Hwang. Modified similarity metric for non-localmeans algorithm. Electronics letters,2009,45(25),1307-1309.
[14]. S. J. Ko, Y. H. Lee. Center weighted median filters and their application toimage enhancement. IEEE Transactions on Circuits and Systems,1991,38(9):984-993.
[15]. N. Wang, X. Li, X. H. Chen. Fast three-dimensional Otsu thresholding withshuffled frog-leaping algorithm. Pattern Recognition Letters,2010,31(1):1809-1815.
[16]. Q. W. Li, S. Y. Yang, S. X. Zhu. Image segmentation based on the2-Dmaximum entropy value and improved genetic algorithm.2011InternationalConference on Computer Science and Network Technology (ICCSNT),2011:1403-1406.
[17].安成锦,牛照东,李志军,陈曾平.典型Otsu算法阈值比较及其SAR图像水域分割性能分析.电子与信息学报,2010,32(9):2215-2219.
[1]. L. Bertelli, B. Sumengen, B. S. Manjunath, et al. A variational framework formulti-region pairwise similarity-based image segmentation. IEEE Trans. PatternAnalysis and Machine Intelligence,2008,30(8):1400-1414.
[2]. N.Otsu. A threshold selection method from gray-level histogram. IEEE Trans. OnSystem, Man and Cybernetics,1979,9(1):62-66.
[3]. H. X. Feng, B. Hou, M. G. Gong. SAR image despeckling based on localhomogeneous-region segmentation by using pixel-relativity measurement. IEEE Trans.Geoscience and Remote Sensing,2011,49(7):2724-2736.
[4]. E. Rignot, R. Chellappa. Segmentation of synthetic-aperture-radar complex data.Jounal of the optical Society of Amric，1991，8(9):1499-1509
[5].安成锦,牛照东,李志军,陈曾平.典型Otsu算法阈值比较及其SAR图像水域分割性能分析.电子与信息学报,2010,32(9):2215-2219.
[6].尹奎英,胡利平,刘宏伟,金林.一种复合的SAR图像去噪算法.西安电子科技大学学报,2010,37(2):224-230.
[7]. X. R. Zhang, L. C. Jiao, F. Liu, et al. Spectral Clustering Ensemble Applied to SARImage Segmentation. IEEE Trans. Geoscience and Remote Sensing,2008,46(7):2126-2136.
[8]. Y. M. Shuai, H. Sun, G. Xu. SAR Image Segmentation Based on Level Set WithStationary Global Minimum. IEEE Geoscience and Remote Sensing Letters,2008,5(4):644-648.
[9]. F. G. Meyer, R. Coifman. Brushlet: a tool for directional image analysis and imagecompression. Applied and Computional Harmonic Analysis,1997,4(2):147-187.
[10]. E. J. Candes. Ridgelet: theory and applications. Ph.D. Thesis, Department ofStatistics, Stanford University,1998.
[11]. E. J. Candes, D. L. Donoho. Curvelets-a surprisingly effective nonadaptiverepresentation for objects with edges. Technical report, Stanford Univ,1999.
[12]. S. Tan, X. R. Zhang, L. C. Jiao. A brushlet–based feature set applied to textureclassification. Int. Conf. on Computational and Information Sciences,2004,1175-1180.
[13]. E. Angelini, A. Laine, S. Takuma, S. Homma. LV volume quantification viaspatiotemporal analysis of real-time3-D echocardiography. IEEE Trans. MedicalImaging,2001,20(6):457-469.
[14].侯彪,刘芳,焦李成.基于脊波变换的直线特征检测,中国科学(E)，2003,33(1):65-73.
[15]. I. Daubechies. Ten lectures on wavelet. SIAM,1992
[16]. M. V. Wickerhauser, Smooth localized orthomormal bases, C.R.Acad.Sci.ParisI,1993:423-427.
[17]. P. Auscher, G. Weiss, M. V. Wickerhauser. Local sine and cosine bases ofcoifman and meyer and the construction of smooth wavelet. In wavelets-a tutorial intheory and applications,1992:237-256.
[18]. M. V. Wickerhauser: Adapted wavelet analysis from theory to software, A. K.Perrers,1995.
[19]. J. M. Li, H. Zhong, L. C. Jiao. SAR image segmentation based onmultiresolution GLCP in overcomplete brushlet domain. IEEE proceeding of2006International Conference on Radar, Oct,2006.
[20]. R. Jobanputra, D. A. Clausi. Texture analysis using Gaussian weighted greylevel co-occurrence probabilities. IEEE Proceedings of the First Canadian Conferenceon Computer and Robot Vision,2004.
[21]. D. A. Clausi, B. Yue. Comparing cooccurrence probabilities and Markovrandom fields for texture analysis of SAR sea ice imagery. IEEE Trans. Geoscience andRemote Sensing,2004,42(1):215-228.
[22]. V. Katkovnik, K. Egiazarian, J. Astola. Adaptive window size imagede-noising based on intersection of confidence intervals (ICI) rule. Journal ofMathematical Imaging and Vision,2002,16(3):223-235.
[23]. J. M. Park, W. J. Song, W. A. Pearlman. Speckle filtering of SAR imagesbased on adaptive windowing. IEE Proceedings of Vision, Image and Signal Process,1999:191-197.
[24]. D. L. Donoho. Compressed Sensing. IEEE Trans. Information Theory,2006,52(4):1289-1306.
[25]. E. Candès, J. Romberg, T. Tao,“Robust uncertainty principles: Exact signalreconstruction from highly incomplete frequency information,” IEEE Trans. Inform.Theory,2006,52(2):489-509.
[26]. David Donoho, Compressed sensing.(IEEE Trans. on Information Theory,52(4), pp.1289-1306, April2006)
[27]. R.G. Baraniuk, M. Davenport, R. DeVore, and M.B. Wakin,“A simple proofof the restricted isometry principle for random matrices (aka the Johnson-Lindenstrausslemma meets compressed sensing),” Constructive Approximation,2007[Online].Available: http://dsp.rice.edu/s/jlcs-v03.pdf
[28]. D. H. Liu, G. M. Shi, J. S. Zhou, et al. New method of multiple descriptioncoding for image based on compressed sensing. J.Infrared Millim. Waves,2009,28(4):298-302.
[29]. J. D. Coker, A. H. Tewfik. Compressed sensing and multistatic SAR. IEEEproceeding of2009International Conference on Acoustics, Speech and SignalProcessing,2009,19(24):1097-1100.
[1]. R. J. Dekker. Texture analysis and classification of ERS SAR images for mapupdating of urban areas in The Netherlands. IEEE Trans. Geosci. Remote Sens.,2003,41(9):1950-1958.
[2]. Q. Zhao, J. C. Principe. Support vector machines for SAR automatic targetrecognition. IEEE Trans. Aerosp. Electron. Syst.,2001,37(2):643-654.
[3]. J. S. Lee, I. Jurkevich. Segmentation of SAR images. IEEE Trans. Geosci. RemoteSens.,1989,27(6):674-680.
[4]. A. E. Zaart, D. Ziou, S. Wang, Q. Jiang. Segmentation of SAR images usingmixture of gamma distribution. Pattern Recognit.,2002,35(3):713-724.
[5]. P. R. Kersten, J.-S. Lee, T. L. Ainsworth. Unsupervised classification ofpolarimetric synthetic aperture radar images using fuzzy clustering and EM clustering,”IEEE Trans. Geosci. Remote Sens.,2005,43(3):519-527.
[6]. W. Chumsamrong, P. Thitimajshima, Y. Rangsanseri. Synthetic aperture radar(SAR) image segmentation using a new modified fuzzy c-means algorithm. in Proc.IEEE Symp. Geosci. Remote Sens., Honolulu, HI,2000:624-626.
[7]. R. Samadani. A finite mixtures algorithm for finding proportions in SAR images.IEEE Trans. Image Process.,1995,4(8):1182-1185.
[8]. Y. Dong, B. C. Forster, A. K. Milne. Comparison of radar image segmentation byGaussian and Gamma-Markov random field models. Int. J. Remote Sens.,2003,24(4):711-722.
[9]. H. Deng, D. A. Clausi. Unsupervised segmentation of synthetic aperture radar seaice imagery using a novel Markov random field model. IEEE Trans. Geosci. RemoteSens.,2005,43(3):528-538.
[10]. C. Lemaréchal, R. Fj rtoft, P. Marthon. SAR image segmentation bymorphological methods. Proc. SPIE,1998,3497:111-121.
[11]. B. Ogor, V. Haese-coat, J. Ronsin. SAR image segmentation by mathematicalmorphology and texture analysis. in Proc. IGARSS,1996:717-719.
[12]. C. Fowlkes, S. Belongie, F. Chung, J.Malik. Spectral grouping using theNystr m method. IEEE Trans. Pattern Anal. Mach. Intell.,2004,26(2):214-225.
[13]. J. Shi, J. Malik. Normalized cuts and image segmentation. IEEE Trans. PatternAnal. Mach. Intell.,2000,22(8):888-905.
[14]. M. Fiedler. Algebraic connectivity of graphs. Czechoslovak Math. J.,1973,23:298-305.
[15]. A. Y. Ng, M. I. Jordan, Y. Weiss. On spectral clustering: Analysis and analgorithm. in Advances in Neural Information Processing Systems (NIPS), vol.14, T.Dietterich, S. Becker, and Z. Ghahramani, Eds. Cambridge, MA: MIT Press,2002.
[16]. C. Ding, X. He, H. Zha, M. Gu, H. Simon. A min-max cut algorithm for graphpartitioning and data clustering. in Proc. IEEE Int. Conf. Data Mining,2001:107-114.
[17]. S. X. Yu, J. Shi. Multiclass spectral clustering. in Proc. Int. Conf. Comput. Vis.,2003,1:313-319.
[18]. F. R. Bach, M. I. Jordan. Blind one-microphone speech separation: A spectrallearning approach. in Advances in Neural Information Processing Systems,2005, vol.17. Cambridge, MA: MIT Press.
[19]. P. K. Chan, M. D. F. Schlag, J. Y. Zien. Spectral k-way ratio-cut partitioningand clustering. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst.,1994,13(9):1088-1096.
[20]. L. Zelnik-Manor, P. Perona. Self-tuning spectral clustering. in Advances inNeural Information Processing Systems, vol.17, L. K. Saul, Y. Weiss, and L. Bottou,Eds. Cambridge, MA: MIT Press,2005.
[21]. M. Breitenbach, G. Z. Grudic. Clustering through ranking on manifolds. inProc.22nd Int. Conf. Mach. Learn., Bonn, Germany,2005:73-80.
[22]. A. Krogh, J. Vedelsby. Neural network ensembles, cross validation, and activelearning. in Advances in Neural Information Processing Systems. Cambridge, MA: MITPress,1995:231–238.
[23]. L. Hansen, P. Salamon.Neural network ensembles. IEEE Trans. Pattern Anal.Mach. Intell.,1990,12(10):993-1001.
[24]. A. Strehl, J. Ghosh. Cluster ensembles—A knowledge reuse framework forcombining multiple partitions, J. Mach. Learn. Res.,2002,3(3):583-617.
[25]. X. Z. Fern, C. E. Brodley. Random projection for high dimensional dataclustering: A cluster ensemble approach. in Proc.20th Int. Conf. Mach. Learn.,2003:186-193.
[26]. T. K. Ho. The random subspace method for constructing decision forests. IEEETrans. Pattern Anal. Mach. Intell.,1998,20(8):832-844.
[27]. A. H. S. Solberg, A. K. Jain. Texture fusion and feature selection applied toSAR imagery. IEEE Trans. Geosci. Remote Sens.,1997,35(2):475-479.
[28]. R. M. Haralick, K. Shanmugam, I. Dinstein. Textural features for imageclassification. IEEE Trans. Syst., Man, Cybern.,1973,3(6):610-621.
[29]. F. G. Meyer, R. Coifman. Brushlet: a tool for directional image analysis andimage compression. Applied and Computional Harmonic Analysis,1997,4(2):147-187.
[30]. D. A. Clausi, B. Yue. Comparing cooccurrence probabilities and Markovrandom fields for texture analysis of SAR sea ice imagery. IEEE Trans. Geosci. RemoteSens.,2004,42(1):215-228.
[31]. D. A. Clausi, Y. Zhao. Rapid extraction of image texture by cooccurrenceusing a hybrid data structure. Comput. Geosci.,2002,28(6):763-774.
[32]. D. G. Barber, E. F. LeDrew. SAR sea ice discrimination using texture statistics:A multivariate approach. Photogramm. Eng. Remote Sens.,1991,57(4):385-395.
[33]. D. A. Clausi. An analysis of co-occurrence texture statistics as a function ofgrey level quantization. Can. J. Remote Sens.,2002,28(1):45-62.
[34]. L. J. Du, J. S. Lee, K. Hoppel, S. A. Mango. Segmentation of SAR imagesusing the wavelet transform. Int. J. Imaging Syst. Technol.,1992,4(4):319-329.
[35]. L. Breiman. Bagging predictors. Mach. Learn.,1996,24(2):123-140.
[36]. Y. Freund. Boosting a weak learning algorithm by majority. Inf. Comput.,1995,121(2):256-285.
[37]. A. Topchy, A. K. Jain, W. Punch. A mixture model for clustering ensembles. inProc. SIAM Int. Conf. Data Mining,2004:379-390.
[38]. M. H. C. Law, A. P. Topchy, A. K. Jain. Multiobjective data clustering. in Proc.IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recog.,2004,2:424-430.
[39]. S. Dudoit, J. Fridlyand. Bagging to improve the accuracy of a clusteringprocedure. Bioinformatics,2003,19(9):1090-1099.
[40]. A. Topchy, B. Minaei-Bidgoli, A. K. Jain, W. Punch. Adaptive clusteringensembles. in Proc. Int. Conf. Pattern Recog., Cambridge, U.K.,2004:272-275.
[41]. A. L. N. Fred. Finding consistent clusters in data partitions. in Proc.3rd Int.Workshop Multiple Classifier Syst., F. Roli and J. Kittler, Eds.,2001,2364:309-318.
[42]. A. L. N. Fred, A. K. Jain. Combining multiple clusterings using evidenceaccumulation. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(6):835-850.
[43]. Y. Jiang, Z.-H. Zhou. SOM ensemble-based image segmentation. NeuralProcess. Lett.,2004,20(3):171-178.
[44]. V. Vapnik. The Nature of Statistical Learning Theory. Berlin, Germany:Springer-Verlag,1999.
[45]. C. Blake, E. Keogh, C. J. Merz. UCI Repository of Machine LearningDatabases. Irvine, CA: Dept. Inf. Comput. Sci., Univ. California,1998.[Online].Available: http://www.ics.uci.edu/~mlearn/MLRepository.html
[46]. C. Carincotte, S. Derrode, S. Bourennance. Unsupervised change detection on
SAR images using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens.,
2006,44(2):432-441.
[1]. L. M. Novak. Coherent change detection for Multi-polarization SAR, Proceedings39thAsilomar Conference on Signals, Systems and Computers,2005:568-573.
[2]. L. Novak, C. Frost. Effects of SAR image compression on coherent changedetection. SPIE conference on Algorithms for SAR. Orlando, FL., April2009.
[3]. F. F. Xin, L. C. Jiao, G. T. Wang. SAR image change detection based on Memeticalgorithm. J.Infrared Millim.Waves,2012,31(1):61-66.
[4]. H. L. Wan, L. C. Jiao. Change detection in SAR images by means of groupingconnected regions using the clone selection algorithm. Electronics letters,2011,46(5):338-339.
[5]. Y. Bazi, F. Melgani, L. Bruzzone, et al. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imagery. InternationalJournal of Remote Sensing,2009,30(24):6591-6610.
[6]. T. Celik. Bayesian change detection based on spatial sampling and Gaussianmixture model. Pattern Recognition Letter,2011,32(12):1635-1642.
[7]. G. Moser, S. Serpico. Unsupervised change detection from multichannel SAR databy Markovian data fusion. IEEE Trans. Geoscience and Remote Sensing,2009,47(7):2114-2128.
[8]. F. Bovolo, L. Bruzzone. A Detail-Preserving Scalse-Driven Approach to ChangeDetection in Multitemporal SAR Images. IEEE Trans. Geosci. Remote Sens.2005,43(12),2963–2972.
[9]. J. Inglada, G. Mercier. A new statistical similarity measure for change detection inmultitemporal SAR images and its extension to multiscale change analysis. IEEE Trans.Geosci Remote Sens2007;45(5):1432-1445.
[10]. G. Meyer, R. coifman. Brushlet: a tool for directional image analysis andimage compression. Applied and Computional Harmonic Analysis,1997,4(2):147-187.
[11]. J. M. Li, H. Zhong, L. C. Jiao. SAR image segmentation based onmultiresolution GLCP in overcomplete brushlet domain. IEEE proceeding of2006International Conference on Radar, Oct,2006.
[12]. T. Blu, F. Luisier. The SURE-LET Approach to Image Denoising. IEEE Trans.on Image Processing,2007,16(11),2778-2786.
[13]. W. Zeng, L. Zhou, X. B. Jiang, et al. Clustering Based Image Denoising UsingSURE-LET.2011Seventh International Conference on Computational Intelligence andSecurity,2011:1303-1307.
[14]. F. Luisier, T. Blu, M. Unser. SURE-LET for Orthonormal Wavelet-DomainVideo Denoising. IEEE Trans. on Circuits and Systems for Video Technology,2010,20(6),913-919
[15]. D. A. Clausi, B. Yue. Comparing cooccurrence probabilities and Markovrandom fields for texture analysis of SAR sea ice imagery. IEEE Trans. on Geoscienceand Remote Sensing,2004,42(1):215-228.
[16]. R. Jobanputra, D. A. Clausi. Texture analysis using Gaussian weighted greylevel co-occurrence probabilities. IEEE Proceedings of the First Canadian Conferenceon Computer and Robot Vision,2004.
[17]. X. Y. Xu, S. Z. Xu, L. H. Jin, et al. Characteristic analysis of Otsu thresholdand its applications. Pattern Recognition Letters,2011,32(7):956-961.
[18]. Otsu N. A threshold selection method from gray-level histogram. IEEE Trans.On System, Man and Cybernetics,1979,9(1):62-66.