基于双树复数小波的快速二步迭代混合范数算法  

A Fast Two-step Iterative Hybrid Norm Algorithm Based on Double-tree Complex Wavelet

作　　者：叶润武 陈晨[2] 刘委[1] 孙旭[1] 高亚红[1] 孔尧[1] 张鑫晟[1] 孙海威[1] YE Run-wu CHEN Chen LIU Wei SUN Xu GAO Ya-hong KONG Yao ZHANG Xin-sheng SUN Hai-wei(School of Computer Science and Communication Engineering, Jiangsu University Communication Engineering , Jingjiang College of Jiangsu University, Zhenjiang 212000, China)

机构地区：[1]江苏大学计算机科学与通信工程学院 [2]江苏大学京江学院通信工程系,江苏镇江212200

出　　处：《软件导刊》2017年第10期54-56,60,共4页Software Guide

基　　金：江苏省高校研究生科研创新计划项目(KYLX15_1072)

摘　　要：以双树复数小波基为稀疏基,局部哈达玛矩阵为观测矩阵,在IST算法的基础上提出一种改进的快度二步迭代混合范数算法,目标函数采用混合范数模型,二步迭代加速了目标函数的优化,二步迭代混合范数算法收敛于混合目标函数的最小值。改进的算法重构速度高于IST算法的2.5倍,图像的均方误差减小50%以上。与以DCT为稀疏基、高斯矩阵为观测矩阵、快速二步迭代混合范数算法为重构算法的压缩感知重构系统相比,改进算法的峰值信噪比提高了约1dB,表明改进算法具有更好的图像重构质量和重构速度。Based on the IST algorithm, an improved fast two-step iterative mixed norm algorithm is proposed. The objective function is based on the mixed norm model, and the two- The iterative method accelerates the optimization of the objective function, and the two-step iterative mixed norm algorithm converges to the minimum value of the mixed objective function. The improved algorithm is 2.5 times faster than the IST algorithm, and the mean square error of the image is reduced by more than 50%. Compared with the compression-aware reconstruction system with DCT as sparse base and Gaussian matrix as observation matrix and fast two-step iterative mixed norm algorithm, the improved signal has a peak signal-to-noise ratio of about ldB, which shows that the improved algorithm has Better image reconstruction quality and reconstruction speed.

关 键 词：压缩感知 图像重构 稀疏变换 混合范数 二步迭代 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]