基于Contourlet变换和交替方向法的压缩感知图像重构算法  

Compressed Sensing Image Reconstruction Algorithm Based on Contourlet Transform and Alternating Direction Method

作　　者：邹健[1] 

机构地区：[1]长江大学信息与数学学院,湖北荆州434023

出　　处：《长江大学学报（自然科学版）》2017年第5期1-5,共5页Journal of Yangtze University(Natural Science Edition)

基　　金：国家自然科学基金项目(61503047)

摘　　要：在传统的基于压缩感知的图像重构中,小波变换往往用来将图像稀疏表示,但小波变换并不能很好的表现图像的轮廓和纹理等细节信息。提出了一种基于Contourlet变换和交替方向法的压缩感知图像重构算法:首先利用Contourlet变换将图像稀疏表示,然后利用交替方向法重构原始图像。与基于小波变换的方法相比,该方法不仅可以显示更多的图像的边缘和轮廓信息,在重构精度上也占优。数值试验也验证了新算法的有效性。In traditional compressed sensing(CS)image reconstruction,wavelet transform is usually used to express the sparse images,but can hardly capture the information of image curves and edges.In this paper,a new CS reconstruction algorithm based on and alternating direction method is presented.The Contourlet transform is first used to express the sparse images and the alternating direction method is used reconstruct the original image.Contrast with wavelet based method,the proposed method not only can enforce the curve sparsity of images with fast computation,but also outperform on reconstruction accuracy.Numerical results show the effectiveness of the proposed algorithm.

关 键 词：压缩感知 图像重构 CONTOURLET变换 交替方向法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]