基于遗传算法优化的稀疏表示图像融合算法  

An Image Fusion Method with Sparse Representation Based on Genetic Algorithm Optimization

作　　者：赵学军[1] 李育珍[1] 雷书彧 

机构地区：[1]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《北京邮电大学学报》2016年第2期73-76,87,共5页Journal of Beijing University of Posts and Telecommunications

基　　金：国家高技术研究发展计划(863计划)项目(2012AA12A308;1212011120222)

摘　　要：关于稀疏表示理论的图像融合主要是利用加权系数方法来确定稀疏系数的融合规则,通过遗传算法求解最优加权系数,实现全色图像和多光谱图像的融合.所提算法与Contourlet变换、主成分分析算法和高通滤波等遥感图像融合算法相比,在提高图像清晰度的同时,光谱保真度相对较高.Due to sparse nature of the nature of image,the sparse signal representation theory can be well used in image processing,and with sparse representation theory of continuous improvement,it is also widely used in image de-noising rehabilitation and integration process. The sparse representation of image fusion theory was used to determine the weighting factor fusion rules sparse coefficients,and to solve the optimal weighting coefficients of genetic algorithm to achieve image fusion panchromatic,multispectral images,contourlet transform,principal component analysis（ PCA） algorithm and the high-pass filter image fusion algorithm. Also it improves the image clarity spectral fidelity compared to other algorithms.

关 键 词：遗传算法 稀疏表示 图像融合 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]