同向平均梯度的各向异性扩散模型  

Anisotropic diffusion model based on average gradient of identical direction

作　　者：王相海[1,2] 李放[1] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,大连116029 [2]辽宁师范大学自然地理与空间信息科学辽宁省重点实验室,大连116029

出　　处：《中国图象图形学报》2011年第12期2105-2111,共7页Journal of Image and Graphics

基　　金：辽宁省自然基金项目(20102123);辽宁"百千万人才工程"项目(2008921036);计算机软件新技术国家重点实验室(南京大学)开放基金项目(KFKT2011B11);南京邮电大学图像处理与图像通信江苏省重点实验室开放基金项目(LBEK20100003)

摘　　要：遥感图像成像过程中经常会产生包括高斯噪声和椒盐噪声的图像噪声,这些噪声在很大程度上降低了图像的清晰度,影响了图像的实际应用。如何在有效的去除图像噪声的同时又能够很好的保留图像的纹理信息,成为遥感图像去噪追求的目标。针对林石算子和基于非线性小波阈值的各向异性扩散方程存在的不足,提出一种基于同向平均梯度值的各向异性扩散去噪模型,该模型克服了林石算子和基于非线性小波阈值的各向异性扩散方程无法去除强高斯噪声和椒盐噪声的不足,在有效去除遥感图像噪声的同时,很好的保持了图像的边缘和纹理信息。实验结果表明,提出模型的稳定性和有效性,并且去噪后的图像信噪比较林石算子和基于非线性小波阈值的各向异性扩散方程分别提高了24dB。During the imaging process of remote sensing images, it will cause the image noise, including Gaussian noise and salt-and-pepper noise ,which reduce the definition of the images and impact their practical application to a large extent. The goal of noise elimination of remote sensing images is to properly protect texture information of the image while efficiently eliminating noise. Based on the disadvantage of the Lin Shi algorithm and the anisotropic diffusion equation of nonlinear wavelet threshold value, the thesis puts forward the anisotropic diffused noise-eliminating model of average gradient of identical direction. This model effectively eliminates noise, at the same time, also properly protects edge features and texture information of remote sensing images,without the disadvantage the Gaussian noise and the salt-and-pepper noise cannot be eliminated by the Lin Shi algorithm and anisotropic diffusion equation of nonlinear wavelet threshold value. Our experiment show the stability and feasibility of our model, and the PSNR of image after using this model respectively increases 2-4 dB compared to the Lin＆Shi algorithm or the anisotropic diffusion equation of nonlinear wavelet threshold value.

关 键 词：同向梯度 林石算子 各向异性扩散方程 遥感图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]