基于非下采样Shearlet变换与模糊对比度的合成孔径雷达图像增强  

Synthetic aperture radar image enhancement method based on combination of non-subsampled shearlet transform and fuzzy contrast

作　　者：郭庆荣 贾振红[1] 杨杰[2] Nikola KASABOV GUO Qingrong;JIA Zhenhong;YANG Jie;Nikola KASABOV(College of Information Science and Engineering,Xinjiang University,Urumqi Xinjiang 830046,China;Institute of Image Processing and Patter Recognition,Shanghai Jiao Tong University,Shanghai 200240,China;Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand)

机构地区：[1]新疆大学信息科学与工程学院,乌鲁木齐830046 [2]上海交通大学图像处理与模式识别研究所,上海200240 [3]奥克兰理工大学知识工程与发现研究所

出　　处：《计算机应用》2018年第9期2701-2705,共5页journal of Computer Applications

基　　金：基于数字图像的信息检测技术研究(2014-2029;2016-2196)~~

摘　　要：针对合成孔径雷达(SAR)图像在成像和传输过程中引入噪声和干扰从而导致图像清晰度下降、细节丢失等问题,提出了一种非下采样Shearlet变换(NSST)与模糊对比度的SAR图像增强算法。首先,原始图像经NSST分解成一个低频分量和若干个高频分量;然后对低频分量进行线性增强以提高整体对比度,对高频分量采用阈值法进行增强以去除图像中的噪声;接着对处理后的两部分分量进行NSST反变换得到重构图像;最后采用模糊对比度算法对重构图像进行增强,提高图像细节信息和层次感,得到增强后的图像。对40幅图像的实验结果表明,与直方图均衡化、多尺度Retinex增强算法、基于Shearlet变换和多尺度Retinex的遥感图像增强算法、基于剪切波域改进Gamma校正的医学图像增强算法相比,该算法的图像峰值信噪比至少提升了22.9%,均方根误差至少降低了36.2%,能明显提升图像的清晰度,使图像的纹理信息更加清晰。Aiming at the noises and artifacts were introduced to Synthetic Aperture Radar(SAR)image in the process of imaging and transmission,which cause many problems such as reduction of definition and lack of details,an SAR image enhancement method based on the combination of Non-Subsampled Shearlet Transform(NSST)and fuzzy contrast was proposed.Firstly,the original image was decomposed into a low-frequency component and several high-frequency components by NSST.Then,the low-frequency component was linearly stretched to improve the overall contrast,and the threshold method was adopted for high-frequency components to remove noise.And then the reconstruction image was obtained by applying the inverse NSST to the processed low-frequency and high-frequency components.Finally,fuzzy contrast method was used to improve detail information and layering of reconstruction image and obtain the final image.The experimental results on 40 images show that,compared with Histogram Equalization(HE),Multi-Scale Retinex(MSR)enhancement algorithm,Remote sensing image enhancement algorithm based on shearlet transform and multi-scale Retinex,and medical image enhancement method based on improved Gamma correction in Shearlet domain,the Peak Signal-to-Noise Ratio(PSNR)of this proposed method promotes at least 22.9%,and the Root Mean Square Error(RMSE)optimizes at least 36.2%.And finally this proposed method can obviously improve image definition and obtains clearer texture information.

关 键 词：合成孔径雷达图像 非下采样Shearlet变换 阈值去噪 模糊对比度 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]