基于四通道不可分加性小波的多聚焦图像融合  

Multifocus Image Fusion Based on Four Channel Non-separable Additive Wavelet

作　　者：刘斌 谌文江 辛迦楠 LIU Bin;CHEN Wen-jiang;XIN Jia-nan(School of Computer and Information Engineering,Hubei University,Wuhan 430062,China)

机构地区：[1]湖北大学计算机与信息工程学院

出　　处：《计算机科学》2019年第7期268-273,共6页Computer Science

基　　金：国家自然科学基金面上项目(61471160);湖北省自然科学基金重点项目(2012FFA053)资助

摘　　要：针对张量积小波不具有对称性,在图像融合中难以获得高空间分辨率图像的问题,文中利用伸缩矩阵为[2,0;0,2]的不可分小波的构造方法构造四通道6×6对称的不可分小波滤波器组,并把它应用于多聚焦图像的融合中。利用此类滤波器组中的低通滤波器对多聚焦图像进行加性小波分解,得到小波平面组,然后利用融合规则对分解后的小波平面进行融合。实验结果表明,该方法有较好的融合效果,融合结果图像具有较高的清晰度和空间分辨率,其融合性能优于拉普拉斯金字塔融合方法(基于LP的融合方法)、基于小波分解的融合方法(基于DWT的融合方法)和基于三通道不可分对称小波的融合方法(基于3-NSDWT的融合方法)。In order to solve the problem that separable wavelets are not symmetry and cannot get high spatial resolution image,this paper constructed four channel 6×6 filter banks by using the method of non-separable wavelet transform which the dilation matrix is[2,0;0,2]and presented a multi-focus image fusion method based on this kind filter bank.The multifocus images are decomposed through additive wavelet mode by using the low-pass filter of the filter bank,and then the wavelet planes are obtained.Then the fusion rules are used to fuse the decomposed wavelet plane.The experiment results show that this method has better fusion effect in the high definition and spatial resolution.This fusion performance outperforms the Laplacian pyramid fusion method,the fusion method based on the wavelet decomposition and the fusion method based on three channel non-separable symmetric wavelet.

关 键 词：图像融合 不可分小波 加性小波 滤波器组 多聚焦图像 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]