| 一种改进含噪多聚焦图像融合方法 |
| |
| 引用本文： | 冯鑫,张建华,胡开群,翟志芬.一种改进含噪多聚焦图像融合方法[J].光电子．激光,2017,28(11):1260-1266. |
| |
| 作者姓名： | 冯鑫 张建华 胡开群 翟志芬 |
| |
| 作者单位： | 重庆工商大学 机械工程学院,制造装备机构设计与控制重庆市重点 实验室,重庆 400067,中国农业科学院 农业信息研究所,北京 100081,重庆工商大学 机械工程学院,制造装备机构设计与控制重庆市重点 实验室,重庆 400067,农业部 规 划设计研究院,北京 100125 |
| |
| 基金项目： | 国家自然科学基金(31501229)、重庆市基础科学与前沿技术研究(一般)项目(csct2015jcyjA 40014)和重庆市教委基础与前沿研究计划(KJ1400628)资助项目 (1．重庆工商大学 机械工程学院,制造装备机构设计与控制重庆市重点 实验室,重庆 400067； 2．中国农业科学院农业信息研究所,北京 100081; 3．农业部规 划设计研究院,北京 100125) |
| |
| 摘 要： | 针对目前多聚焦图像融合方法处理含噪图像缺乏有 效性而导致融合效果较差的问题,提出一种引导滤波结合脉冲耦合神经网络(PCNN)的非下采 样Shearlet变换(NSST)域内多聚焦图像融合方法。 首先,分别对待融合多聚焦图像进行NSST获取其相应高频子带和低频子带系数；对高 频子带系数,通过引导滤波结合改进简化PCNN模型设置融合规则；提取相位一致性、清晰 度和亮度等底层视觉特性,指导低频子带系数融合权重；最后反NSST获取最终融合结 果。实验结果表明,本文方法能够在噪声干扰情况下有效完成多聚焦融合,并且边缘和纹理 信息保持较好,当20标准差噪声时互信息提升了近0.15具有有效性。
|
| 关 键 词： | 多聚焦图像 非下采样Shearlet变换(NSST) 脉冲耦合神经网络(PCNN) 引导滤波 相 位一致性 |
| 收稿时间： | 2017/2/15 0:00:00 |
An improved method for noisy focus images fusion |
| |
| FENG Xin,ZHANG Jian-hu,HU Kai-qun and ZHAI Zhi-f en.An improved method for noisy focus images fusion[J].Journal of Optoelectronics·laser,2017,28(11):1260-1266. |
| |
| Authors: | FENG Xin ZHANG Jian-hu HU Kai-qun and ZHAI Zhi-f en |
| |
| Affiliation: | Key Laboratory of Manufacturing Equipment Mechanism Design and Control of Cho ngqing,College of Mechanical Engineering, Chongqing Technology and Business University,Chongqing 400067,China,Agricultu ral Information Institute of Chinese Academy of Agricultural Sciences,Beijing 100081,China,Key Laboratory of Manufacturing Equipment Mechanism Design and Control of Cho ngqing,College of Mechanical Engineering, Chongqing Technology and Business University,Chongqing 400067,China and Chinese Academy of Agricultural Engineering,Beijing 100125,China |
| |
| Abstract: | As the multi-focus image fusion method can not deal with the noisy image effectively,this paper pr oposes a multi-focus image fusion method in the non-subsampled shearlet transform (NSST) domain with pulse-coupled neural network (PCNN) and g uide filtering. Firstly,high frequency sub-band coefficients and low frequency sub-band coeff icients are obtained by performing NSST respectively.The fusion rules are improved by comb ining guide filtering with improved PCNN model for high-frequency sub-band coefficients.Th e low level visual characteristics of phase consistency,sharpness and brightness are extract ed to guide the low-frequency sub-band coefficient fusion.Finally,the fusion result is obtaine d from the inverse NSST.The experimental results show that the proposed method c an effectively accomplish multi-focus fusion under the condition of noisy interference,and im prove mutual information by nearly 0.15under the condition of standard deviation of noise of 20,and the edge and texture information is kept good and effective. |
| |
| Keywords: | multi-focus image non-subsampled shearlet transform (NSST) pulse-coupled ne ural network (PCNN) guide filtering phase coherence |
|
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
