非下采样轮廓波的多源图像融合

Multi-source Image Fusion Based on NSCT

利用非下采样轮廓波(NSCT)对源图像进行多尺度、多方向分解,对分解后的低频子带系数采用区域能量的融合规则,对高频子带系数采用基于领域方差加权平均的融合规则,对融合后的系数经过NSCT逆变换得到融合图像。实验结果表明,在主观视觉和客观评价指标上均优于其他对比方法。

This paper is mainly to discuss multi- source image fusion technology. The NSCT has many fea- tures which is the shift- invariant, multi- resolution, muhidirectional and avoids Gibbs phenomenon. Two primitive matched images are decomposed in NSCT domain. The low frequency used the weighted aver- age, while the high frequency coefficients was fused by weighted average of the variance of the neighbor- hood. Finally,the fused result is obtained through inverse NSCT. Experimental results show that the pro- posed fusion algorithm which has a better visuals and better evaluation are significantly better than the comparative experiment.