基于非抽样Contourlet变换的多聚焦图像融合算法

文中研究了非抽样Contourlet变换（NSCT）的原理,以及其多尺度、局部化、方向性和各向异性等优点。提出了一种基于NSCT的多聚焦图像融合新算法。本算法将多聚焦图像进行NSCT分解,不同子带采用不同的融合规则,低频子带采用新的基于灰度形态学梯度算子的融合算法,并做一致性检测,带通子带采用基于区域能量的融合算法。最后将融合得到的系数进行NSCT反变换得到融合图像。实验结果表明,与其他融合算法相比较,该算法可以更有效地保留源图像信息和细节特征。

Multi-Focus Image Fusion Algorithm Based on Nonsubsampled Contourlet Transform

The principle of nonsubsampled Contourlet transform and the advantage of multi-scale,localization directionality and anisotropy are studied in the paper.A new multi-focus image fusion algorithm based on NSCT is developed.Firstly,two different multi-focus source images are decomposed by NSCT.Secondly,different fusion rules are applied in the low and banpass subband coefficients.A new fusion algorithm based on the gray morphology grad operator is applied in lowpass subbands and the consistency check is proposed.The regional energy fusion rule is applied in highpass subbands.Finally,the fused image is reconstructed by the inverse NSCT.The experimental results show that,compared with other algorithms,this fusion method can retain the information and features of source more effectively.