针对高光谱遥感图像易受噪声干扰,本文提出了一种基于非下采样Contourlet变换NSCT(Nonsubsampled ContourletTransform)和核主成分分析KPCA(Kernel Principal Component Analysis)的去噪方法。首先对高光谱各波段图像进行NSCT分解;然后利用KPCA对NSCT系数进行处理,并在KPCA重构时依据各类噪声的特性选取合适的主成分;最后用处理过的系数进行逆变换得到去噪图像。实验结果表明,本文方法抑制了高光谱遥感图像中的噪声干扰,较完整地保留了原始数据的有效信息。

As hyperspectral remote sensing image is easily interfered by noises, a denoising method of hyperspectral remote sensing image based on Nonsubsampled Contourlet Transform (NSCT) and Kernel Principal Component Analysis (KPCA) is proposed. First, hyperspectral image of each band is decomposed by NSCT to acquire the coefficients which are processed by KPCA. The proper principal components are selected for KPCA reconstruction according to noise features. Finally, the denoised image is obtained by performing inverse NSCT. Experimental results show that the proposed method can suppress noise interference in hyperspectral remote sensing images, and preserve the useful information of original data more completely.