首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221007--1)

基于扩展相位拉伸变换的多聚焦图像融合算法

Multi-focus Image Fusion Algorithm Based on Extended Phase Stretch Transform

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对目前传统多聚焦图像融合中图像局部模糊不易度量, 融合策略难以设计等问题,提出一种新的相位拉伸核函数, 形成基于扩展相位拉伸变换的多聚焦图像融合算法。该算法将传统的线性或次线性群延迟相位滤波器推广到非线性群延迟相位滤波器,并从理论上证明,这种扩展相位拉伸变换的逆变换相位近似于原始图像的归一化二阶梯度, 将图像高频特征传统的梯度极值表达转换为角度或相位表达,利用角度/相位图像局部方差对清晰与模糊图像良好的区别特性设计出基于扩展相位拉伸变换局部相位方差度量的融合策略,克服了目前融合方法存在的不足。利用MATLAB软件平台对Lytro数据集中的相当数量多聚焦图像数据进行融合实验, 与传统基于离散小波变换、拉普拉斯、超分辨率、引导滤波和联合卷积自编码网络算法等融合算法结果进行对照分析。 结果表明, 本文算法的融合图像明显优于传统最好的融合算法, 融合图像的互信息、信息熵、空间频率、平均梯度及结构相似性等指标比现有的其他方法提高5%以上,证明了所提算法的优越性与实用性。

Abstract

Aiming at the problem that the local blur of the image is not easy to measure and the fusion strategy is difficult to designed in traditional multi-focus image fusion, a new phase stretching kernel function is developed, which results in a multi-focus image fusion algorithm based on extended phase stretch transformation. The method promotes the traditional linear or sublinear group delay phase filter to the nonlinear group delay phase filter. It is proved theoretically that the phase of the inverse transformation of the extended phase stretch transformation is approximate to the normalized two-step degree of the original image. The traditional gradient extremum expression of image high-frequency features is transformed into angle or phase expression, and a fusion strategy based on local phase variance measurement of extended phase stretching transform is designed to overcome the shortcomings of current fusion methods by using the good difference between clear and fuzzy images. Many multi focus image data in Lytro dataset are fused using MATLAB software platform. The results are compared with those of traditional fusion algorithms based on discrete wavelet transformation, Laplace Laplacian, super-resolution, guided filtering, and joint convolution self-coding network algorithm. The results show that the fusion image of this algorithm is obviously better than the traditional best fusion algorithm, and the mutual information, information entropy, spatial frequency, average gradient and structural similarity of the fused image are improved by more than 5% compared with other existing methods, which proves the superiority and practicability of the proposed algorithm.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.9

DOI:10.3788/LOP57.221007

所属栏目:图像处理

基金项目:河南省科技厅科技攻关项目、平顶山学院博士科研启动基金项目、平顶山学院青年基金;

收稿日期:2020-02-10

修改稿日期:2020-04-10

网络出版日期:2020-11-01

作者单位    点击查看

张亚峰:平顶山学院信息工程学院, 河南 平顶山 467000
耿则勋:平顶山学院信息工程学院, 河南 平顶山 467000信息工程大学地理空间信息学院, 河南 郑州 450001
王军敏:平顶山学院信息工程学院, 河南 平顶山 467000

联系人作者:张亚峰(zhangyafeng@pdsu.edu.cn)

备注:河南省科技厅科技攻关项目、平顶山学院博士科研启动基金项目、平顶山学院青年基金;

【1】Wang J, Wu X S. Medical image fusion based on improved guided filtering and dual-channel pulse coupled neural networks [J]. Laser & Optoelectronics Progress. 2019, 56(15): 151004.
王建, 吴锡生. 基于改进的引导滤波和双通道脉冲耦合神经网络的医学图像融合 [J]. 激光与光电子学进展. 2019, 56(15): 151004.

【2】Cao J, Chen H, Zhang J W. Research on multi-focus image fusion algorithm based on super resolution [J]. Computer Engineering and Applications. 2020, 56(3): 180-186.
曹军, 陈鹤, 张佳薇. 基于超分辨率的多聚焦图像融合算法研究 [J]. 计算机工程与应用. 2020, 56(3): 180-186.
Cao J, Chen H, Zhang J W. Research on multi-focus image fusion algorithm based on super resolution [J]. Computer Engineering and Applications. 2020, 56(3): 180-186.
曹军, 陈鹤, 张佳薇. 基于超分辨率的多聚焦图像融合算法研究 [J]. 计算机工程与应用. 2020, 56(3): 180-186.

【3】Ouyang N, Li Z, Yuan H, et al. Multi-focus image fusion based on adaptive sparse representation [J]. Microelectronics & Computer. 2015, 32(6): 22-26, 31.
欧阳宁, 李子, 袁华, 等. 基于自适应稀疏表示的多聚焦图像融合 [J]. 微电子学与计算机. 2015, 32(6): 22-26, 31.
Ouyang N, Li Z, Yuan H, et al. Multi-focus image fusion based on adaptive sparse representation [J]. Microelectronics & Computer. 2015, 32(6): 22-26, 31.
欧阳宁, 李子, 袁华, 等. 基于自适应稀疏表示的多聚焦图像融合 [J]. 微电子学与计算机. 2015, 32(6): 22-26, 31.

【4】Qu X B, Yan J W, Xiao H Z, et al. Image fusion algorithm based on spatial frequency-motivated pulse coupled neural networks in nonsubsampled contourlet transform domain [J]. Acta Automatica Sinica. 2008, 34(12): 1508-1514.
屈小波, 闫敬文, 肖弘智, 等. 非降采样Contourlet域内空间频率激励的PCNN图像融合算法 [J]. 自动化学报. 2008, 34(12): 1508-1514.
Qu X B, Yan J W, Xiao H Z, et al. Image fusion algorithm based on spatial frequency-motivated pulse coupled neural networks in nonsubsampled contourlet transform domain [J]. Acta Automatica Sinica. 2008, 34(12): 1508-1514.
屈小波, 闫敬文, 肖弘智, 等. 非降采样Contourlet域内空间频率激励的PCNN图像融合算法 [J]. 自动化学报. 2008, 34(12): 1508-1514.

【5】Asghari M H, Jalali B. Anamorphic transformation and its application to time-bandwidth compression [J]. Applied Optics. 2013, 52(27): 6735-6743.Asghari M H, Jalali B. Anamorphic transformation and its application to time-bandwidth compression [J]. Applied Optics. 2013, 52(27): 6735-6743.

【6】Suthar M, Asghari H, Jalali B. Feature enhancement in visually impaired images [J]. IEEE Access. 2018, 6: 1407-1415.Suthar M, Asghari H, Jalali B. Feature enhancement in visually impaired images [J]. IEEE Access. 2018, 6: 1407-1415.

【7】Asghari M H, Jalali B. Discrete anamorphic transform for image compression [J]. IEEE Signal Processing Letters. 2014, 21(7): 829-833.Asghari M H, Jalali B. Discrete anamorphic transform for image compression [J]. IEEE Signal Processing Letters. 2014, 21(7): 829-833.

【8】Ilovitsh T, Jalali B, Asghari M H, et al. Phase stretch transform for super-resolution localization microscopy [J]. Biomedical Optics Express. 2016, 7(10): 4198-4209.

【9】Asghari M H, Jalali B. Edge detection in digital images using dispersive phase stretch transform [J]. International Journal of Biomedical Imaging. 2015, 2015: 687819.Asghari M H, Jalali B. Edge detection in digital images using dispersive phase stretch transform [J]. International Journal of Biomedical Imaging. 2015, 2015: 687819.

【10】Qian W, Chang X, Hu L. Infrared and visible image pseudo color fusion algorithm based on improved color transfer strategy and NSCT [J]. Infrared Technology. 2019, 41(6): 555-560.
钱伟, 常霞, 虎玲. 基于改进颜色传递策略与NSCT的红外与可见光图像伪彩色融合 [J]. 红外技术. 2019, 41(6): 555-560.

【11】Jin X, Nie R C, Zhou D M, et al. Multifocus color image fusion based on NSST and PCNN [J]. Journal of Sensors. 2016, 2016(2): 1-12.Jin X, Nie R C, Zhou D M, et al. Multifocus color image fusion based on NSST and PCNN [J]. Journal of Sensors. 2016, 2016(2): 1-12.

【12】Li X L, Nie X F, Huang H B, et al. Remote sensing image fusion method based on guided filter and histogram matching [J]. Video Engineering. 2018, 42(10): 17-20, 76.
李晓玲, 聂祥飞, 黄海波, 等. 基于引导滤波和直方图匹配的遥感图像融合 [J]. 电视技术. 2018, 42(10): 17-20, 76.
Li X L, Nie X F, Huang H B, et al. Remote sensing image fusion method based on guided filter and histogram matching [J]. Video Engineering. 2018, 42(10): 17-20, 76.
李晓玲, 聂祥飞, 黄海波, 等. 基于引导滤波和直方图匹配的遥感图像融合 [J]. 电视技术. 2018, 42(10): 17-20, 76.

【13】Luo X Q, Xiong M Y, Zhang Z C. Multi-focus image fusion method based on the joint convolution auto-encoder network [J]. Control and Decision. 2020, 35(7): 1651-1658.
罗晓清, 熊梦渔, 张战成. 基于联合卷积自编码网络的多聚焦图像融合方法 [J]. 控制与决策. 2020, 35(7): 1651-1658.
Luo X Q, Xiong M Y, Zhang Z C. Multi-focus image fusion method based on the joint convolution auto-encoder network [J]. Control and Decision. 2020, 35(7): 1651-1658.
罗晓清, 熊梦渔, 张战成. 基于联合卷积自编码网络的多聚焦图像融合方法 [J]. 控制与决策. 2020, 35(7): 1651-1658.

【14】Zhou X L, Jiang Z T. Infrared and visible image fusion combining pulse-coupled neural network and guided filtering [J]. Acta Optica Sinica. 2019, 39(11): 1110003.
周哓玲, 江泽涛. 结合脉冲耦合神经网络与引导滤波的红外与可见光图像融合 [J]. 光学学报. 2019, 39(11): 1110003.

【15】Zhu D R, Xu L, Wang F B, et al. Multi-focus image fusion algorithm based on fast finite shearlet transform and guided filter [J]. Laser & Optoelectronics Progress. 2018, 55(1): 011001.
朱达荣, 许露, 汪方斌, 等. 基于快速有限剪切波变换与引导滤波的多聚焦图像融合算法 [J]. 激光与光电子学进展. 2018, 55(1): 011001.

【16】Yi W, Zeng Y, Yuan Z. Fusion of GF-3 SAR and optical images based on the nonsubsampled contourlet transform [J]. Acta Optica Sinica. 2018, 38(11): 1110002.
易维, 曾湧, 原征. 基于NSCT变换的高分三号SAR与光学图像融合 [J]. 光学学报. 2018, 38(11): 1110002.

引用该论文

Zhang Yafeng,Geng Zexun,Wang Junmin. Multi-focus Image Fusion Algorithm Based on Extended Phase Stretch Transform[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221007

张亚峰,耿则勋,王军敏. 基于扩展相位拉伸变换的多聚焦图像融合算法[J]. 激光与光电子学进展, 2020, 57(22): 221007

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF