一种改进的基于小波变换的相干斑去噪方法

An Improved Speckle Denoising Method Based on Wavelet Transform

对于合成孔径雷达(SAR)图像中含有的相干斑噪声的抑制一直是SAR图像处理的热点和难点。相干斑噪声的存在对SAR图像的后续相关的图像处理,例如图像的分割、图像的特征提取以及目标的分类与识别有很大影响。提出了一种基于平稳小波变换的相干斑去噪方法,通过平稳小波变换对图像进行小波分解,对于子图像的高频区域进行阈值分割和双边滤波,利用平稳小波更好的冗余性和平稳不变性更好地去除了SAR图像的相干斑噪声。实验结果表明,这种改进的去噪方法对SAR图像的相干斑噪声抑制有很好的效果,并且尽可能地保留了图像的边缘和纹理细节。

The suppression of speckle noise in SAR image is a difficult problem for SAR image processing. The presence of speckle noise has a great influence on the subsequent image processing of SAR images, such as image segmentation, feature extraetion of images, and classifieation and recognition of targets. In this paper, a coherent speckle denoising method based on stationary wavelet transform is proposed. The wavelet decomposition of the image is carried out by stationary wavelet transform, the threshold segmentation and bilateral filtering are performed on the high frequency region of sub-image, and the better redundancy and smooth invariance can better remove speekle noise from SAR images. The experimental results show that the improved denoising method has a good effeet on the speckle noise suppression of SAR images, and reserves the edges and texture details of the image as much as possible.