计算机科学 ›› 2015, Vol. 42 ›› Issue (Z6): 158-162.

• 模式识别与图像处理 • 上一篇    下一篇

ND-GSM模型的采样矩阵方向优化及SAR图像去噪

陈双叶,周耳江,吴强   

  1. 北京工业大学电控学院 北京100124,北京工业大学电控学院 北京100124,北京工业大学电控学院 北京100124
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金资助

Direction Optimization of Sampling Matrix and SAR Image Denoising in ND-GSM Model

CHEN Shuang-ye, ZHOU Er-jiang and WU Qiang   

  • Online:2018-11-14 Published:2018-11-14

摘要: 将非下采样Directionlet变换(Nonsubsampled Directionlet,ND)和高斯混合尺度(GSM)模型相结合,提出了基于ND-GSM模型的采样矩阵方向优化算法并将其应用于SAR图像去噪。首先,将SAR图像的分割子图进行二进小波变换,从而确定SAR图像的方向优化采样矩阵,然后在各个子图中将GSM模型引入采样矩阵方向优化的非下采样Directionlet变换域中,构造了采样矩阵方向优化的非下采样Directionlet域分解系数的邻域模型(ND-GSM),最后利用 Bayes最小均方估计进行子图变换域的局部去噪,并合成去噪后的分割子图,得到去噪后的SAR图像。该方法解决了当非下采样Directionlet基函数的方向与图像中各向异性目标不一致时图像的逼近效果差的问题。仿真实验结果表明,该方法能充分体现邻域间系数的相关性,同时在图像边缘等细节特征保持方面具有明显优势,明显改善了图像视觉效果,取得了比空域滤波及小波方法更优的去噪性能。

Abstract: A new improved algorithm of the sampling matrix direction based on the model of ND-GSM combining with the nonsubsampled Direction lettransform and the model of Gaussian scale mixtures was presented.First,binary wavelet transform is applied to segment subgraphs of SAR image to determine thesampling matrix of optimizing direction of SAR image.Then,by combining nonsubsampled Directionlet transform which optimizes the direction of the sampling matrix with Gaussian scale mixtures in the segmentation subgraphs,the marginal distributions of neighbor coefficients in the nonsubsampled Directionlet domain with the sampling matrix of direction optimization are modeled.Finally,for removing the speckle noise,the Bayes least square estimation is adopted to evaluate each coefficient.The denoised segmentation subgraphs is composed to obtain the SAR image after denoising.The method solves the phenomenon that image approximation effect is bad when the direction of nonsubsampled Directionlet basis function and the direction of the image anisotropic target is inconsistent.Simulation results show that theme thod can fully reflect strong correlation among the amplitudes of neighbor coefficients,have obvious advantage in image detail preservation,improve the image visual effect and achieve a better denoising performance than the spatial filtering and wavelet method.

Key words: Nonsubsampled directionlet transform,Gaussian scale mixtures,Direction optimization of sampling matrix,SAR image

[1] Portilla J,Strela V,Wainwright M J,et al.Imagedenoising using scale mixtures of Gaussians in the waveletdomain[J].IEEE Transactions on Image Processing,2003,2(11):1338-1351
[2] Zhang Lei,Shi Han-qing,Du Hua-dong,et al.Estimation of seasur facewind direction using Space borne SAR images and wavele tanalysis[J].Journal of remote Sensing,2014,1:215-216
[3] Velisavljevic V,Beferull-Lozano B,Vetterli M,et al.Directionlets:anisotropic multi-directional representation with separable filtering[J].IEEE Trans.on Image Proc.,2006,5(7):1916-1933
[4] 胡贺军,高清维,卢一相,等.基于方向波域混合高斯模型的SAR图像去噪[J].计算机应用与软件,2013,0(7):283-286
[5] Do M N,Vetterli M.The Contourlet Transform:An Efficient Directional Multiresolution Image Representation[J].IEEE proc.,2005,14(12):2091-2106
[6] 刘帅奇,胡绍海,肖扬.基于小波Contourlet变换与Cycle Spinning相结合的SAR图像去噪[J].信号处理,2011,7(6):837-842
[7] 张弛.Directionlet变换在图像去噪中的应用研究[D].合肥:安徽大学,2010
[8] 关辉.基于Directionlet变换的SAR图像噪声抑制及边缘检测[D].西安:西安电子科技大学,2010
[9] 岳春宇,江万寿.基于最大后验和非局域约束的非下采样轮廓波变换域SAR图像去噪方法[J].测绘学报,2012,2(1):59-64
[10] 张弛.基于平稳小波域GSM模型的SAR图像去噪[J].黑龙江科技学院学报,2010,0(3):222-226
[11] 侯青松,郭英,王布宏.基于格理论的非均匀稀疏线阵旁瓣结构的分析方法[J].电子学报,2010,8(6):1459-1463
[12] 刘杰,朱启兵,李允公.基于新阈值函数的二进小波变换信号去噪研究[J].东北大学学报,2006,7(5):536-539
[13] 张冬翠.基于Directionlet变换的图像去噪和融合[D].西安:西安电子科技大学,2010
[14] 武晓弱,郭宝龙,李雷达.一种新的结合非下采样Contourlet与自适应全变差的图像去噪方法[J].电子与信息学报,2010,2(2):360-365
[15] 侯建华,田金文,柳健.小波域局部维纳滤波器估计误差分析及图像去噪[J].光子学报,2007,6(1):189-191
[16] 张明,李开成,胡益胜.基于Bayes估计的双小波维纳滤波电能质量信号去噪算法[J].电力系统保护与制,2011,39(4):52-57

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!