联合均匀离散曲波变换及非局部张量稀疏正则化的SAR图像相干斑抑制

SAR Image Despeckling Based on Joint of Discrete Curvelet Transform and Nonlocal Tensor Sparse Regularization

正则化技术是合成孔径雷达(Synthetic Aperture Radar,SAR)图像相干斑抑制的一种有效工具。在正则化相干斑抑制中,设计有效的正则化项来反映图像的先验信息起着至关重要的作用。本文通过同时刻画SAR图像的局部稀疏性和非局部自相似性,提出了一种新的基于联合稀疏正则化的SAR图像相干斑抑制模型。该模型包含一个数据保真项和两个正则化项,其中一个正则化项采用离散曲波变换来描述SAR图像的局部平滑性,另一个正则化项采用张量稀疏模型刻画SAR图像的非局部自相似性,图像张量是由具有相似结构的图像块组合,从而在对图像张量进行稀疏表示的过程中能够刻画图像中固有的局部稀疏性和非局部自相似性。进一步,为了求解该模型,提出了一种分离Bregman迭代技术的高效求解算法。实验结果表明,该模型在图像质量的主观视觉评价和客观评价方面均明显优于传统和最新的技术。

Regularization-based approaches have recently been considered as effective tools for synthetic aperture radar(SAR)image despeckling,where designing effective regularization terms to reflect the image priors plays a critical role.In this paper,by characterizing local sparsity and nonlocal self-similarity of SAR images simultaneously,a new joint sparsity regularization model for SAR image despeckling is proposed.The proposed model contains a data fidelity term and two regularization terms.One of the two regularization terms employs the discrete curvelet transform to depict the local smoothness of the SAR image,and the other employs a tensor sparse transform of the three-dimensional(3 D)tensor generated by stacking similar SAR image patches.The joint employment of these two regularization terms,which has not been utilized in existing methods of SAR image despeckling yet,aims to produce better despeckling performance and preserve more geometrical features of SAR images.Furthermore,to address the optimization problem in the proposed model,a new efficient algorithm is derived based on the split Bregman iterations framework.Experimental results show that the proposed model considerably outperforms some conventional and state-of-the-art techniques in terms of both subjective visual assessment of image quality and objective evaluation.