计算机应用 ›› 2018, Vol. 38 ›› Issue (9): 2701-2705.DOI: 10.11772/j.issn.1001-9081.2018030527

• 虚拟现实与多媒体计算 • 上一篇    下一篇

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

郭庆荣1, 贾振红1, 杨杰2, Nikola KASABOV3   

  1. 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, 新西兰 奥克兰 1020
  • 收稿日期:2018-03-14 修回日期:2018-04-27 出版日期:2018-09-10 发布日期:2018-09-06
  • 通讯作者: 贾振红
  • 作者简介:郭庆荣(1993—),男,甘肃定西人,硕士研究生,主要研究方向:图像增强;贾振红(1964—),男,河南洛阳人,教授,博士,主要研究方向:光通信、信号与信息处理;杨杰(1964—),男,上海人,教授,博士,主要研究方向:图像处理、模式识别;Nikola KASABOV(1948—),男,保加利亚索菲亚人,教授,博士,主要研究方向:数字图像处理、模式识别。
  • 基金资助:
    基于数字图像的信息检测技术研究(2014-2029,2016-2196)。

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

GUO Qingrong1, JIA Zhenhong1, YANG Jie2, Nikola KASABOV3   

  1. 1. College of Information Science and Engineering, Xinjiang University, Urumqi Xinjiang 830046, China;
    2. Institute of Image Processing and Patter Recognition, Shanghai Jiao Tong University, Shanghai 200240, China;
    3. Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1020, New Zealand
  • Received:2018-03-14 Revised:2018-04-27 Online:2018-09-10 Published:2018-09-06
  • Contact: 贾振红
  • Supported by:
    This work is partially supported by the Research of Information Detection Technology based on Digital Image (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。

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

Abstract: 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.

Key words: Synthetic Aperture Radar (SAR) image, Non-Subsampled Shearlet Transform (NSST), threshold denoising, fuzzy contrast

中图分类号: