| 基于NSCT与PCNN的自适应图像融合 |
| |
| 引用本文： | 纪峰,吴仰玉,常霞,李翠. 基于NSCT与PCNN的自适应图像融合[J]. 宁夏大学学报(自然科学版), 2013, 0(2): 168-172 |
| |
| 作者姓名： | 纪峰 吴仰玉 常霞 李翠 |
| |
| 作者单位： | 北方民族大学信息与计算科学学院信息与系统科学研究所,宁夏银川750021 |
| |
| 基金项目： | 国家自然科学基金资助项目（61102008）;教育部重点实验室开放基金资助项目（OIPIU012011006）;北方民族大学科研项目（2011Y021）;北方民族大学研究生自主创新项目（2011ZYC036,2012XYC030,2012xjyk10） |
| |
| 摘 要： | 提出了一种新的基于非下采样轮廓波(NSCT)和脉冲耦合神经网络(PCNN)相结合的自适应图像融合方法.对已经配准的源图像进行NSCT分解,得到低频子带系数和不同方向的高频子带系数.对NSCT分解的低频部分采用简单的加权平均融合规则;而高通子带系数,采用改进的拉普拉斯能量作为PCNN链接强度的方法.最后,对融合的系数进行NSCT逆变换得到融合图像.实验结果表明,本文算法明显优于其他几种方法,具有更好的融合性能,清晰度更高,是一种可行、有效的图像融合方法.
|
| 关 键 词： | 图像融合 非下采样Contourlet变换 脉冲耦合神经网络 自适应 |
Adaptive Image Fusion Based on NSCT and PCNN |
| |
| Ji Feng,Wu Yangyu,Chang Xia,Li Cui. Adaptive Image Fusion Based on NSCT and PCNN[J]. Journal of Ningxia University(Natural Science Edition), 2013, 0(2): 168-172 |
| |
| Authors: | Ji Feng Wu Yangyu Chang Xia Li Cui |
| |
| Affiliation: | 1. School of Information and Computation Science, Beifang University of Nationalities, Yinchuan 750021, China) |
| |
| Abstract: | A novel image fusion scheme is proposed based on the nonsubsampled contourlet transform （NSCT） and pulse coupled neural networks （PCNN）. Firstly, two registered source image are decomposed by NSCT to obtain the low frequency subband coefficients and high frequency subband coefficients. Secondly, the fusion principle of traditional weighted average is used to the part of low frequency subband, and algorithm which employ the modified Laplace energy as the link intensity of PCNN is used to the part of high frequency. Finally, the fusion images are obtained by the nonsubsampled contourlet inverse transform. The experimental results show that the method is a feasible and effective, and has better fusion performance and higher definition than the other methods. |
| |
| Keywords: | image fusion nonsubsampled contourlet transform pulse coupled neural networks adaptive |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
