一种改进的基于区域梯度——能量的图像融合方法

Improved image fusion algorithm based on regional gradient and regional energy

针对区域梯度法、区域能量法重构图像峰值信噪比较低、均方根误差较高的现象,提出了一种改进的基于区域梯度-能量的压缩感知图像融合方法。该方法首先构造正交小波变换矩阵,并使用小波变换使图像稀疏化,然后采用哈达玛矩阵作为测量矩阵对稀疏信号进行测量得到测量值,分别计算测量值对应的梯度值及能量值,依据绝对值取大法及加权平均法对测量值进行融合,最后对融合后的测量值进行图像重构。实验结果表明,该方法比单独使用区域梯度法或区域能量法具有较好的图像融合效果。

According to the phenomenon that the peak signal to noise ratio is low and the root-meansquare error is high corresponding to the reconstructed fusion image based on the regional gradient method and the regional energy method,this paper proposes an improved compressive sensing image fusion algorithm based on both gradient method and regional energy method.Firstly,a orthogonal wavelet transform matrix should be constructed,and we should use wavelet transform to make image sparse.Secondly,hadamard matrix is used as the measurement matrix to get measurement value of sparse signal,and then gradient values and energy values are calculated corresponding to the measured values.Thirdly,we fuse the measurement values according to absolute value method and weighted average method.Finally,image is constructed according to the measured value of fused.The experiments results show that this algorithm can obtain better effect of image fusion compared to single regional gradient method or regional energy method.