曲波变换域的SAR图像相干斑去噪

Speckle reduction of SAR image in the curvelet domain

合成孔径雷达(SAR)图像固有的相干斑噪声降低了图像的质量,使得图像的可视化和解译变得困难,影响了后续的目标检测、分类和识别等应用。为此提出了一种在快速曲波变换域的SAR图像去噪算法。先将SAR图像分成均质区域、非均质区域和边缘区域。使用均值滤波器对均质区域的像素滤波,对于非均质区域的像素使用曲波硬阈值滤波算法处理,边缘区域的像素直接保留。实验结果表明,此算法能有效的去除SAR图像的噪声并保持图像细节。

Synthetic Aperture Radar（SAR） images are corrupted by speckle noise which severely decreases the qual-ity of images,it makes images visualization and interpretation difficult,and influences the follow-up target detection,classification and recognition.A filtering method of SAR image in the Curvelet domain is proposed in this paper.First,di-vided image into homogeneous area,non-homogeneous area and edge area.Then,average filtering method is applied to the homogeneous area,curvelet hard thresholding de-noising method applied to the non-homogeneous area and edge area retained directly.Experiments show that this algorithm can effectively eliminate noise and maintain edge details.