摘要
为弥补传统图像融合方法融合质量不高的缺点,提出了基于非下采样剪切波变换(Nonsubsampled Shearlet Transform,NSST)与自适应脉冲耦合神经网络(Pulse Coupled Neural Network,PCNN)的图像融合方法。首先,利用非下采样剪切波变换对源图像进行剪切波分解;然后,采用基于图像引导滤波器的融合规则对得到的低频分量进行低频融合;其次,对于高频分量,采用改进的空间频率作为PCNN的输入,利用改进的拉普拉斯能量和作为PCNN的链接强度;最后,通过NSST逆变换得到融合后的图像。实验结果表明,相比于传统的融合规则,文中提出的算法在主观效果上能很好地保留细节信息,并抑制伪影和失真的产生;在客观评价上,其在标准差、边缘信息传递量、信息熵和互信息等常用指标上的表现更为优越。
In order to overcome the disadvantages of low fusion quality in traditional image fusion methods,this paper proposed an image fusion method based on the nonsubsampled shearlet transform(NSST)and adaptive pulse coupled neural network(PCNN).Firstly,the source image is decomposed by nonsubsampled shearlet transform.Then,the low frequency fusion of the obtained low frequency components is performed by using the fusion rule based on the guided image filter.After that,the improved spatial frequency is used as the PCNN input for the high frequency component,and the improved Laplace energy summation is used as the PCNN link strength of PCNN.Finally,the fused image is obtained by inversion of NSST.The experimental results show that this algorithm can preserve the details well and prevent product artifacts and distortions from the perspective of subjective effects,and it possesses more superior perfor-mance in terms of objective indicator,such as standard deviation,Q AB/F,entropy and mutual information.
作者
杨利素
王雷
郭全
YANG Li-su;WANG Lei;GUO Quan(College of Computer Science and Technology,Shandong University of Technology,Zibo,Shandong 255000,China)
出处
《计算机科学》
CSCD
北大核心
2018年第12期217-222,250,共7页
Computer Science
基金
国家自然科学基金青年科学基金项目(61502282)
山东省自然科学基金青年科学基金项目(ZR2015FQ005)
山东理工大学博士科研启动经费资助项目
山东理工大学青年教师发展支持计划
