基于小波方向相关性的图像融合方法

Image Fusion Algorithm Based on the Directional Co-relation of Wavelet Coefficient

通过分析图像经小波变换后低频系数的邻域相关性和各高频子带的区域方向性,本文提出一种基于小波方向相关性的图像融合方法。对低频子带的每个系数,以多向梯度模作为其自相关性的衡量标准,确定融合后低频系数;对于各个高频子带的系数,根据其不同的方向特性,采用基于方向相关系数的融合规则。最后通过对比仿真实验,验证本文方法的有效性。

We discussed the neighboring relation of low - frequency wavelet coefficients and the directional characteristic of the high - frequency coefficients, and then proposed a novel algorithm of image fusion based on the directional co - relation of wavelet coefficients. Firstly, the algorithm of this paper made out the fusing coeffi- cient by multi - orientation gradient mode for every coefficient of the low - frequency. Then, for every coefficient of the high - frequency in different directions, we calculated directional co - relation which determined the fusing coefficient. The fused image was obtained tal results show that the proposed method through is more the reversely lifting wavelet transformation at last. Experimen- outstanding than the conventional method.