一种基于小波系数区域特征的图像融合算法

Image Fusion Algorithm Based on the Neighboring Relation of Wavelet Coefficients

分析并统计了图像经小波变换后低频子带系数的区域特性和各高频子带系数的方向区域特性,并据此提出了一种新的基于小波系数区域特征的图像融合方法。对于低频子带的每个系数,根据其区域相关性,采用区域方差的融合规则,确定低频融合系数;对于各高频子带的每个系数,根据其所在子带的方向特征,采用方向区域能量的融合规则,进而确定高频融合系数。对多聚焦图像和医学图像进行了融合仿真实验,并用信息熵和平均梯度对融合结果进行了客观的评价。实验结果表明,基于小波系数方向特征的图像融合算法要优于传统的融合算法,具有一定的实用性。

The neighboring relation of low-frequency wavelet coefficients and the directional characteristic of the highfrequency coefficients was discussed and analyzed, then, a novel algorithm of image fusion based on the directional correlation of wavelet coefficients was proposed. At first, for every coefficient of the low-frequency, the algorithm of this paper made out the fusing coefficient by using the variance. Then, for every coefficient of the high-frequency, the algorithm of this paper made out the fusing coefficient by using the directional energy in the different directional high-frequency region. At last, the fused image was obtained through the reversely lifting wavelet transformation. Entropy and Average grads were used to judge the results of the proposed algorithms. Experimental results show that the proposed method is more outstanding than the conventional methods, and it has some application value.