基于三通道不可分对称小波的多聚焦图像融合  

Multi-focus image fusion based on three channel nonseparable symmetrical wavelets

作　　者：刘斌[1] 刘维杰[2] 马嘉利[1] 

机构地区：[1]湖北大学数学与计算机科学学院,武汉430062 [2]武汉大学计算机学院,武汉430079

出　　处：《仪器仪表学报》2012年第5期1110-1116,共7页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金(61072126);湖北省自然科学重点基金(2009CDA133)资助项目

摘　　要：针对Daubechies系列小波不具有对称性、张量积小波变换只强调水平和垂直方向的不足,提出了一种基于三通道不可分对称小波的多聚焦图像融合方法。利用矩阵扩充的方法,给出了一种三通道不可分对称小波滤波器组的构造方法,用所构造的不可分小波滤波器组分别对多聚焦图像作非下采样多尺度分解,采用低频分量系数值取小、高频分量系数绝对值取大的融合规则对分解后的子图像进行融合。实验结果表明,该方法有较好的融合效果,其融合结果图像有较丰富的边缘信息、较高的清晰度和空间分辨力,其融合性能比基于不作采样的张量积离散小波帧变换的融合方法的融合性能好。In order to solve the problems that the Daubechies series of wavelets do not have symmetry and the separable discrete wavelet transforms only emphasize horizontal and vertical directions of the decomposed images,a novel fusion method of multi-focus images based on three channel nonseparable symmetrical wavelets is proposed.A construction method of the symmetrical filter banks relating to this kind of wavelet is presented.The multi-resolution decompositions of multi-focus images are performed in nonsubsampled mode using the constructed filter banks.The fusion rule is that the smaller value is selected for low frequency subband coefficients;while for high frequency subband coefficients,the coefficients with larger absolute value are employed.The fused image is achieved through inverse nonseparable wavelet transform.Experiment results show that the proposed method has good fusion results and the fused images have rich edge information,high definition and spatial resolution.The fusion performance outperforms the performance of the fusion method based on discrete wavelet frame transform（DWFT）.

关 键 词：图像融合 不可分小波 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]