基于小波-Contourlet变换的区域能量加权图像融合算法

为了消除Contourlet变换中拉普拉斯金字塔分解存在的信息冗余,提出了一种基于小波-Contourlet变换的图像融合算法.该算法采用了不同的窗口函数计算图像高频分量和低频分量的区域能量;以区域能量计算的归一化权值对各小波-Contourlet系数进行加权,得到融合小波-Contourlet系数.实验结果和均值、方差、熵与交叉熵等客观评价数据表明,在相同融合规则下,小波-Contourlet变换能够取得比Contourlet变换更好的结果;在相同变换条件下,基于不同窗口函数的区域能量融合规则的融合效果好于基于均值窗口函数的区域能量融合规则和低频采用均值与高频取最大值的融合规则.

Regional Energy Weighting Image Fusion Algorithm by Wavelet Based Contourlet Transform

In order to reduce the redundancy of Laplacian pyramids decomposing in contourlet transform(CT).An image fusion algorithm is proposed with the wavelet based contourlet transform(WBCT).By employing different masks,the algorithm integrates the approximation coefficients and the detail coefficients differently according to the weights,which are calculated with the energy of the corresponding neighbor region of the WBCT coefficients.Evaluation of the experimental results according to both the subjective and objective criteria,including the average,mean square error,entropy and cross entropy,it is demonstrated that algorithms based on WBCT are more effective than the ones based on CT with the same fusion rules,and that the fusion rule based on different masks can attain better results than the ones of average mask and traditional method.