正在加载图片...
第11卷第2期 智能系统学报 Vol.11No.2 2016年4月 CAAI Transactions on Intelligent Systems Apr.2016 D0I:10.11992/is.201509017 网络出版地址:http://www.cnki.net/kcms/detail/23.1538.TP.20160314.1431.004.html 多小波和NSDFB组合域递归滤波多聚焦图像融合 任晓霞,孙秀明,耿鹏2,苏醒2 (1.张家口学院理学系,河北张家口075000:2.石家庄铁道大学信息科学与技术学院,河北石家庄050043) 摘要:多小波能同时满足正交、紧支、对称等对信号处理十分重要的特性,结合多小波变换的多尺度特点和非子采 样方向滤波器组变换的多方向性,提出了一种新的基于多小波和非子采样方向滤波器组的多尺度多方向变换。对 于高频系数首先计算其修改空间频率,然后利用域变换递归滤波进行滤波的融合规则:低频系数采用了修改拉普拉 斯能量和的(SML)融合规则。通过与其他融合方法进行实验对比,实验结果表明:本文提出的融合方法能够更加有 效地选择源图像中的聚焦良好区域,并且引入的伪影信息较少:此外,与其他融合方法相比本文方法的客观评价结 果也是最好的。 关键词:图像处理;图像融合:递归滤波;改进空间频率:多小波 中图分类号:TP391文献标志码:A文章编号:1673-4785(2016)02-0241-08 中文引用格式:任晓霞,孙秀明,耿鹏,等.多小波和NSDFB组合域递归滤波多聚焦图像融合[J].智能系统学报,2016,11(2): 241-248. 英文引用格式:REN Xiaoxia,SUN Xiuming,GENG Peng,etal.Multifocus image fusion using a recursive filter in the combined domain of multiwavelets and NSDFB[].CAAI transactions on intelligent systems,2016,11(2):241-248. Multifocus image fusion using a recursive filter in the combined domain of multiwavelets and NSDFB REN Xiaoxia',SUN Xiuming',GENG Peng2,SU Xing? (1.Science department,Zhangjiakou University,Zhangjiakou 075000,China;2.School of Information Science and Technology,Shi- jiazhuang Tiedao University,Shijiazhuang 050043,China) Abstract:The multiwavelet transform has properties of orthogonality,tight frame,and symmetry,which are vital to signal processing.In this study,a new transform,called as MNSDFB,is proposed by combining the multi-wavelet and nonsubsampled directional filter banks.The domain transform recursive filter is adopted to fuse the filters after the spatial frequency of the high frequency coefficient is calculated.The modified sum-modified-Laplacian (SML) is employed in the low pass subbands as a focus measurement to select fused coefficients.The presented fusion rule in the high pass subband can distinguish the focused regions from the blurred regions.The proposed fusion method was compared with three other fusion methods.The experimental results demonstrate that the proposed fusion meth- od can select the focused regions while introducing few artifacts into the final merged image.Furthermore,its objec- tive criteria,such as MI and QAB/F,are better than those of the other three methods. Keywords:image processing;image fusion;recursive filter;modified spatial frequency;multiwavelett 图像融合是信息融合的一个重要分支,其目的 一幅新的具有更高可信度清晰度以及可理解性的图 是将不同传感器获取的同一目标的互补信息合并为 像[山。因此,经过图像融合技术得到的合成图像可 以更全面、更精确地描述所研究的对象,为进一步图 收稿日期:2015-09-09.网络出版日期:2016-03-14. 像处理和分析提供高质量数据。因此,图像融合技 基金项目:河北省自然科学基金项目(F2013210094,F2013210109). 通信作者:耿鹏.E-mail:Gengpeng(@stdu.cdu.cn. 术在军事、医学、遥感、计算机视觉等领域得到了广第 11 卷第 2 期 智 能 系 统 学 报 Vol.11№.2 2016 年 4 月 CAAI Transactions on Intelligent Systems Apr. 2016 DOI:10.11992 / tis.201509017 网络出版地址:http: / / www.cnki.net / kcms/ detail / 23.1538.TP.20160314.1431.004.html 多小波和 NSDFB 组合域递归滤波多聚焦图像融合 任晓霞1 ,孙秀明1 ,耿鹏2 ,苏醒2 (1.张家口学院 理学系, 河北 张家口 075000; 2.石家庄铁道大学 信息科学与技术学院, 河北 石家庄 050043) 摘 要:多小波能同时满足正交、紧支、对称等对信号处理十分重要的特性,结合多小波变换的多尺度特点和非子采 样方向滤波器组变换的多方向性,提出了一种新的基于多小波和非子采样方向滤波器组的多尺度多方向变换。 对 于高频系数首先计算其修改空间频率,然后利用域变换递归滤波进行滤波的融合规则;低频系数采用了修改拉普拉 斯能量和的(SML)融合规则。 通过与其他融合方法进行实验对比,实验结果表明:本文提出的融合方法能够更加有 效地选择源图像中的聚焦良好区域,并且引入的伪影信息较少;此外,与其他融合方法相比本文方法的客观评价结 果也是最好的。 关键词:图像处理;图像融合;递归滤波;改进空间频率;多小波 中图分类号: TP391 文献标志码:A 文章编号:1673⁃4785(2016)02⁃0241⁃08 中文引用格式:任晓霞,孙秀明,耿鹏,等. 多小波和 NSDFB 组合域递归滤波多聚焦图像融合[ J]. 智能系统学报, 2016, 11( 2): 241⁃248. 英文引用格式:REN Xiaoxia, SUN Xiuming, GENG Peng, et al. Multifocus image fusion using a recursive filter in the combined domain of multiwavelets and NSDFB[J]. CAAI transactions on intelligent systems, 2016, 11(2): 241⁃248. Multifocus image fusion using a recursive filter in the combined domain of multiwavelets and NSDFB REN Xiaoxia 1 , SUN Xiuming 1 , GENG Peng 2 , SU Xing 2 (1. Science department , Zhangjiakou University, Zhangjiakou 075000, China; 2. School of Information Science and Technology, Shi⁃ jiazhuang Tiedao University, Shijiazhuang 050043, China) Abstract:The multiwavelet transform has properties of orthogonality, tight frame, and symmetry, which are vital to signal processing. In this study, a new transform, called as MNSDFB, is proposed by combining the multi⁃wavelet and nonsubsampled directional filter banks. The domain transform recursive filter is adopted to fuse the filters after the spatial frequency of the high frequency coefficient is calculated. The modified sum⁃modified⁃Laplacian (SML) is employed in the low pass subbands as a focus measurement to select fused coefficients. The presented fusion rule in the high pass subband can distinguish the focused regions from the blurred regions. The proposed fusion method was compared with three other fusion methods. The experimental results demonstrate that the proposed fusion meth⁃ od can select the focused regions while introducing few artifacts into the final merged image. Furthermore, its objec⁃ tive criteria, such as MI and QAB / F, are better than those of the other three methods. Keywords: image processing; image fusion; recursive filter; modified spatial frequency; multiwavelett 收稿日期:2015⁃09⁃09. 网络出版日期:2016⁃03⁃14. 基金项目:河北省自然科学基金项目(F2013210094, F2013210109). 通信作者:耿鹏.E⁃mail:Gengpeng@ stdu.edu.cn. 图像融合是信息融合的一个重要分支,其目的 是将不同传感器获取的同一目标的互补信息合并为 一幅新的具有更高可信度清晰度以及可理解性的图 像[1] 。 因此,经过图像融合技术得到的合成图像可 以更全面、更精确地描述所研究的对象,为进一步图 像处理和分析提供高质量数据。 因此,图像融合技 术在军事、医学、遥感、计算机视觉等领域得到了广
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有