基于非向下采样Contourlet变换的多聚焦图像融合  

MULTI-FOCUS IMAGE FUSION BASED ON NON-SUBSAMPLED CONTOURLET TRANSFORM

作　　者：王玲[1] 李红松[1] 周浩[1] 朱丽青[1] 杨永锋[1] 

机构地区：[1]云南大学信息科学与工程学院,云南昆明650091

出　　处：《计算机应用与软件》2011年第4期167-169,共3页Computer Applications and Software

基　　金：云南省教育厅基金项目(08T0044)

摘　　要：近年来图像融合已成为图像处理的一个热点,提出了一种基于非向下采样Contourlet变换NSCT(Nonsubsampled Contour-let transform)的多聚焦图像融合方法。首先对两幅源图像分别进行非向下采样轮廓波变换得到一个低频子带和多个高频方向子带,然后对高低频子带分别采取方向对比度的区域均值和局部熵的融合规则来选取相应的系数,最终通过反变换得到融合图像。实验中,与离散小波a、trous小波变换、NSCT的简单方法进行了比较,结果表明该方法的融合效果最好。In recent years,image fusion has become the focus of image processing.This paper presents a multi-focus image fusion method based on Non-subsampled Contourlet transform.Firstly,the Non-subsampled Contourlet transform is conducted on two pairs of source images respectively to get a low-frequency sub-band and a number of high-frequency directional sub-bands;and then the fusion rules of regional mean of directional contrast and of local entropy are adopted on high and low-frequency sub-bands respectively to select the corresponding coefficient;finally,the fused image is obtained through inverse transform.The proposed method,discrete wavelet transform,atrous wavelet transform and a simple method of NSCT are compared in experiment,the result show that the fusion effect of the proposed method is the best.

关 键 词：图像融合 NSCT atrous小波 局部熵 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]