一种基于小波阈值的SAR图像降噪方法  

A New Method of Reducing Speckle Noises of SAR Images Based on the Wavelet Threshold Analysis

作　　者：陈鲁宁[1] 唐政[1] 高正[1] 吴宝勤[2] 

机构地区：[1]海军潜艇学院,山东青岛266071 [2]海军海洋测绘研究所,天津300061

出　　处：《海洋测绘》2009年第5期48-50,共3页Hydrographic Surveying and Charting

摘　　要：由于SAR特殊的相干成像机理导致图像有斑点噪声,使得目标识别和特征提取造成困难。在小波变换阈值降噪法的基础上,提出一种改进的SAR图像降噪方法。先用新的阈值公式对图像进行小波分解,再对小波系数进行更为细致的处理,最后通过逆变换实现图像去噪和重建。实验结果表明,与传统方法相比,本方法更为有效地去除了SAR图像的噪声,并能保持图像的细节特征,有着良好的图像视觉解译效果。The speckle noises caused by the special coherently image-generated mechanism of SAR make it difficult to identify target and get feature in SRA image. The paper puts forward the new threshold value formula, and carrys on the more careful processing to the wavelet coefficiet and passes through contrary altermation to realize de-noising and rebuilding of an image. The test result shows that, compared with the traditional method, this new method can reduce the noises from the SAR images more effectively and keep the detailed features of the images, which gives clearer visual effect.

关 键 词：合成孔径雷达图像 小波变换 阈值 降噪 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]