基于各向异性热扩散方程的多聚焦图像融合算法

doi:10.3969/j.issn.0372-2112.2015.06.023

电子学报 ›› 2015, Vol. 43 ›› Issue (6): 1192-1199.DOI: 10.3969/j.issn.0372-2112.2015.06.023

基于各向异性热扩散方程的多聚焦图像融合算法

涂超平¹, 肖进胜^1,2, 杜康华¹, 易本顺¹

1. 武汉大学电子信息学院, 湖北武汉 430072;
2. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079

收稿日期:2013-09-22 修回日期:2014-01-15 出版日期:2015-06-25
- 通讯作者:
- 肖进胜
- 作者简介:
- 涂超平 男,1990年2月出生于湖北孝感.2012年于武汉大学获工学学士学位.武汉大学电子信息学院硕士生.主要研究方向:计算机视觉. E-mail:781512827@qq.com杜康华男,1991年生,硕士研究生在读,主要研究领域为数字图像处理.易本顺男,1965年生,博士,教授,博士生导师,主要研究领域为多媒体通信、无线网络通信.
- 基金资助:
- 国家自然科学基金重大研究计划项目 (No.91120002)

Multi-focus Image Fusion Algorithm Based on the Anisotropic Thermal Diffusion Equation

TU Chao-ping¹, XIAO Jin-sheng^1,2, DU Kang-hua¹, YI Ben-shun¹

1. School of Electronic Information, Wuhan University, Wuhan, Hubei 430072, China;
2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, Hubei 430079, China

Received:2013-09-22 Revised:2014-01-15 Online:2015-06-25 Published:2015-06-25
- Supported by:
- Major Research Project of National Natural Science Foundation of China (No.91120002)

摘要/Abstract

摘要：

本文根据多聚焦图像的光学成像原理,利用各向异性热扩散方程来估计图像深度信息,并讨论一种基于深度信息提取的多聚焦图像的融合算法.算法首先对两幅多聚焦图像进行光学成像过程的模拟,分别建立正向区域的热扩散方程,通过对热扩散方程的迭代求解估计出图像场景的深度信息.然后对深度信息进行自适应的区域划分,分别得到每幅图像的清晰区域,模糊区域和中间过渡区域.最后通过提取清晰区域的像素点,融合过渡区域的像素点实现多聚焦图像的融合.理论推导和实验验证表明,本方法能够克服常用算法中出现的块效应和人工痕迹,是一种有效的图像融合算法.

关键词: 多聚焦, 深度提取, 热扩散, 图像融合, 分层模型

Abstract:

A method for multi-focus image fusion based on depth information extraction is discussed.Under the optical imaging principle of multi-focus image, the anisotropic thermal diffusion equation is used to estimate the image depth information.Firstly, the optical imaging of two multi-focus images is simulated and the positive thermal diffusion equation is respectively established.After iteration of thermal diffusion equation, the image scene depth information is estimated.Depth information is adaptively divided, and images are divided into three regions:clear region, fuzzy region and intermediate transition region.Finally, the result of the proposed algorithm is achieved as soon as the pixels of clear region are extracted and pixels of transition region are fused.Theoretical analysis and experiment results show that the proposed algorithm is an effective method of image fusion that can overcome the block effect and artifacts in general algorithms.

Key words: multi-focus, depth extraction, diffusion, image fusion, layered model

中图分类号:

TP391Z.41

涂超平, 肖进胜, 杜康华, 等. 基于各向异性热扩散方程的多聚焦图像融合算法[J]. 电子学报, 2015, 43(6): 1192-1199.

TU Chao-ping, XIAO Jin-sheng, DU Kang-hua, et al. Multi-focus Image Fusion Algorithm Based on the Anisotropic Thermal Diffusion Equation[J]. Acta Electronica Sinica, 2015, 43(6): 1192-1199.

参考文献

[1] Haghighat M B A, Aghagolzadeh A, Seyedarabi H.Multi-focus image fusion for visual sensor networks in DCT domain [J].Computers & Electrical Engineering, 2011, 37(5):789-797.
[2] 高雪妮, 玉振明, 张军, 李陶深.基于多级分块迭代法的不同聚焦图像融合[J].电子学报, 2011, 39(3):690-694. GAO Xue-ni, YU Zheng-ming, ZHANG Jun, LI Tao-shen.Multi-focus image fusion based on multi-level and iterative method [J].Acta Electronica Sinica, 2011, 39(3):690-694.(in Chinese)
[3] Toet A.Image fusion by a ratio of low-pass pyramid [J].Pattern Recognition Letters, 1989, 9(4):245-253.
[4] 李华锋, 柴毅, 张晓阳.提升静态小波域内多聚焦图像融合算法[J].光电工程, 2011, 38(3):131-144. LI Hua-feng, CHAI Yi, ZHANG Xiao-yang.Multi-focus image fusion algorithm in lifting stationary wavelet domain [J].Opto-Electronic Engineering, 2011, 38(3):131-144.(in Chinese)
[5] 焦李成, 谭山.图像的多尺度几何分析:回顾和展望[J].电子学报, 2003, 31(12A):1975-1981. JIAO Li-cheng, Tan Shan.Development and prospect of image multiscale geometric analysis [J], Acta Electronica Sinica, 2003, 31(12A):1975-1981.(in Chinese)
[6] 马苗, 万仁远, 尹义龙.基于相似性灰关联的 Curvelet 域多聚焦图像融合[J].电子学报, 2012, 40(10):1984-1988. MA Miao, WAN Ren-yuan, YIN Yi-long.Multi-focus image fusion based on grey relation of similarity in curvelet domain [J].Acta Electronica Sinica, 2012, 40(10):1984-1988.(in Chinese)
[7] Li H F, Chai Y, Li X F.Multi-focus image fusion based on nonsubsampled contourlet transform and focused regions detection[J].Optik-International Journal for Light and Electron Optics, 2013, 124(1):40-51.
[8] Zhang B H, Lu X Q, Jia W T.A multi-focus image fusion algorithm based on an improved dual-channel PCNN in NSCT domain [J].Optik-International Journal for Light and Electron Optics, 2013, 124(20):4104-4109.
[9] 石智, 张卓, 岳彦刚.基于Shearlet变换的自适应图像融合算法[J].光子学报, 2013, 42(1):115-120. SHI Zhi, ZHANG Zhuo, YUE Yan-gang.Adaptive image fusion algorithm based on shearlet transform [J].Acta Photonica Sinica, 2013, 42(1):115-120.(in Chinese)
[10] Pentland A P.A new sense for depth of field [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1987, 9(4):523-531.
[11] Chambolle A.Partial differential equations and image processing [A].IEEE International Conference of Image Processing[C].Austin, Texas:IEEE, 1994.16-20.
[12] Ziou D, Deschênes F.Depth from defocus estimation in spatial domain [J].Computer Vision and Image Understanding, 2001, 81(2):143-165.
[13] Favaro P, Mennucci A, Soatto S.Observing shape from defocused images [J].International Journal of Computer Vision, 2003, 52(1):25-43.
[14] Rajagopalan A N, Chaudhuri S, Mudenagudi U.Depth estimation and image restoration using defocused stereo pairs [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11):1521-1525.
[15] Favaro P, Soatto S.A geometric approach to shape from defocus [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3):406-417.
[16] Favaro P, Soatto S, Burger M, et al.Shape from defocus via diffusion [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(3):518-531.
[17] Zhang Y Q, Ding Y, Xiao J S, et al.Visibility enhancement using an image filtering approach[J].EURASIP Journal on Advances in Signal Processing, 2012, 2012(1):1-6.
[18] 肖进胜, 李佩, 易本顺, 等.一种基于图像色貌模型和分层模型的色调映射算法[J].光电子·激光, 2013, 24(4):812-819. XIAO Jin-sheng, LI Pei, YI Ben-shun, et al.A tone mapping algorithm based on image color appearance model and hierarchical model[J].Journal of Optoelectronics·Laser, 2013, 24(4):812-819.(in Chinese)
[19] Lewis J J, O' Callaghan R J, Nikolov S G, et al.Pixel-and region-based image fusion with complex wavelets [J].Information Fusion, 2007, 8(2):119-130.

基于各向异性热扩散方程的多聚焦图像融合算法

Multi-focus Image Fusion Algorithm Based on the Anisotropic Thermal Diffusion Equation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	徐少平, 林珍玉, 张贵珍, 陈孝国, 李芬. 采用深度学习与图像融合混合实现策略的低照度图像增强算法[J]. 电子学报, 2021, 49(1): 72-76.
[2]	秦福强, 王丽芳. 基于变分的多尺度遥感图像融合算法[J]. 电子学报, 2020, 48(6): 1084-1090.
[3]	张以文, 崔光明, 郭星, 张燕平. 一种基于任务粒化的服务组合优化方法[J]. 电子学报, 2018, 46(1): 245-251.
[4]	邓立暖, 尧新峰. 基于NSST的红外与可见光图像融合算法[J]. 电子学报, 2017, 45(12): 2965-2970.
[5]	戴文战, 姜晓丽, 李俊峰. 基于人眼视觉特性的NSCT医学图像自适应融合[J]. 电子学报, 2016, 44(8): 1932-1939.
[6]	刘斌, 刘维杰, 罗益辉, 郭琳. 八通道MSVD构造及其在多聚焦图像融合中的应用[J]. 电子学报, 2016, 44(7): 1694-1701.
[7]	闫利, 向天烛. NSCT域内结合边缘特征和自适应PCNN的红外与可见光图像融合[J]. 电子学报, 2016, 44(4): 761-766.
[8]	李奕, 吴小俊. 粒子群进化学习自适应双通道脉冲耦合神经网络图像融合方法研究[J]. 电子学报, 2014, 42(2): 217-222.
[9]	刘斌, 祝青, 胡福强, 刘维杰. 基于采样二通道不可分小波的多光谱图像融合[J]. 电子学报, 2013, 41(4): 710-716.
[10]	卢振坤, 玉振明. 基于自适应局部Log-Gabor能量的多聚焦图像融合[J]. 电子学报, 2013, 41(1): 199-204.
[11]	叶剑, 李锦涛, 朱珍民. 分布式情境感知分层模型设计与角色分析[J]. 电子学报, 2012, 40(8): 1572-1576.
[12]	郭珈, 王孝通, 徐晓刚, 张成堡. 基于均值滤波矩阵组的二维信号快速经验模式分解方法[J]. 电子学报, 2012, 40(10): 1980-1983.
[13]	马苗, 万仁远, 尹义龙. 基于相似性灰关联的Curvelet域多聚焦图像融合[J]. 电子学报, 2012, 40(10): 1984-1988.
[14]	刘斌;彭嘉雄. 基于非下采样三通道不可分对称小波的多光谱图像融合[J]. 电子学报, 2011, 39(5): 1094-1099.
[15]	高雪妮;玉振明;张军;李陶深. 基于多级分块迭代法的不同聚焦图像融合[J]. 电子学报, 2011, 39(3): 690-694.