一种基于NSST和字典学习的红外和可见光图像融合算法 -- 西北工业大学学报,2017,35(3):408-413
论文:2017,Vol:35,Issue(3):408-413
引用本文:
刘战文, 冯燕, 李旭, 丁鹏飞, 徐继明. 一种基于NSST和字典学习的红外和可见光图像融合算法[J]. 西北工业大学学报
Liu Zhanwen, Feng Yan, Li Xu, Ding Pengfei, Xu Jiming. A Fusion Algorithm for Infrared and Visible Images Based on Dictionary Learning and NSST[J]. Northwestern polytechnical university

一种基于NSST和字典学习的红外和可见光图像融合算法
刘战文1,2, 冯燕1, 李旭1, 丁鹏飞1, 徐继明3
1. 西北工业大学 电子信息学院, 陕西 西安 710072;
2. 西北工业大学 保密处, 陕西 西安 710072;
3. 西北工业大学 计算机学院, 陕西 西安 710072
摘要:
近年来随着多尺度分析和压缩感知成为研究的热点,字典学习算法在图像融合领域得到了广泛应用,但是其算法应用于可见光和红外图像的融合,容易出现块状噪声,边缘有振铃现象。基于此,本文提出了一种基于非下采样剪切波变换(NSST)和字典学习的红外和见光图像融合算法研究,对NSST分解的低频分量利用滑动窗口得到图像块序列,并对其进行零均值化后再稀疏分解,选择区域能量的融合规则,高频子带选择拉普拉斯能量和的融合规则。仿真结果表明,本文的算法在视觉和客观评价指标上优于现有几种融合算法。
关键词:    图像融合    NSST    稀疏表示    字典学习    拉普拉斯能量和   
A Fusion Algorithm for Infrared and Visible Images Based on Dictionary Learning and NSST
Liu Zhanwen1,2, Feng Yan1, Li Xu1, Ding Pengfei1, Xu Jiming3
1. School of Electronic and Information, Northwestern Polytechnical University Xi'an 710072, China;
2. Divison for the Protection of State Secrets, Northwestern Polytechnical University Xi'an 710072, China;
3. School of computer, Northwestern Polytechnical University Xi'an 710072, China
Abstract:
Multi-scale analysis and compression sensing have become hot spots in recent years. and dictionary learning algorithm has been widely used in the field of image fusion. But when it is applied to the fusion of visible and infrared images, there often appear a lot of noise and edge ringing artifacts in their fusion results. Based on this, a fusion algorithm of infrared and visible light based on the Nonsubsampled Shearlet Transform (NSST) and dictionary learning is proposed in this paper. Firstly, the source images are decomposed with NSST; secondly, a rule based on regional energy is used in the low frequency sub-band coefficients after they block vectorization, zero-averaging and sparse decomposition; and a rule, based on laplacian energy sum, high-frequency coefficients was fused; finally, the inverse NSST is used to get the final fused image. The simulation results show that the proposed algorithm is superior to other fusion algorithms in visual and objective evaluation.
Key words:    image fusion    NSST    sparse representation    dictionary learning    Laplacian energy sum   
收稿日期: 2017-03-02     修回日期:
DOI:
基金项目: 国家自然科学基金(61071171)资助
通讯作者:     Email:
作者简介: 刘战文(1975-),西北工业大学博士研究生,主要从事图像融合研究。
相关功能
PDF(2907KB) Free
打印本文
把本文推荐给朋友
作者相关文章
刘战文  在本刊中的所有文章
冯燕  在本刊中的所有文章
李旭  在本刊中的所有文章
丁鹏飞  在本刊中的所有文章
徐继明  在本刊中的所有文章

参考文献:
[1] Zhang X Q, Chen Q L, Men T. Comparison of Fusion Methods for the Infrared and Color Visible Images[C]//Second IEEE International Conference on Computer Science and Information Technology, Beijing, 2009:421-424
[2] Gan Wei, Wu Xiaohong. Infrared and Visible Image Fusion with the Use of Multi-Scale Edge-Preserving Decomposition and Guided Image Filter[J]. Infrared Physics & Technology, 2015, 72:37-51
[3] Li Xu, He Mingyi, Michel ROUX. Multifocus Image Fusion Based on Redundant Wavelet Transform[J]. IET Image Processing, 2010,4(4):283-293
[4] 李晖晖,郭雷,李国新. 基于脊波变换的SAR与可见光图像融合研究[J]. 西北工业大学学报, 2006, 24(4):418-420 Li Huihui, Guo Lei, Li Guoxin. Is Ridgelet Transform Better than Wavelet Transform in SAR and Optical Image Fusion[J]. Journal of Northwestern Polytechnical University, 2006, 24(4):418-420(in Chinese)
[5] Yang Shuyuan, Wang Min, Jiao Licheng, et al. Image Fusion Based on a New Contourlet Packet[J]. Information Fusion, 2010, 11(2):78-84
[6] Zhang Qiong, An X M. Adaptive Fusion Approach for Infrared and Visible Images Based on NSCT and Compressed Sensing[J]. Infrared Physics & Technology, 2016, 79:11-20
[7] Yin Ming, Duan Puhong, Liu Wei, et al. A Novel Infrared and Visible Image Fusion Algorithm Based on Shift-Invariant Dual-Tree Complex Shearlet Transform and Sparse Representation[J]. Neurocomputing, 2017, 226(22):182-191
[8] Liu Zhanwen, Feng Yan, Zhang Yifan, Li Xu. A Fusion Algorithm for Infrared and Visible Images Based on Rdu-Pcnn and Ica-Bases in Nsst Domain[J]. Infrared Physics & Technology, 2016, 79:183-190
[9] 王珺, 彭进业, 何贵青, 冯晓毅. 基于多尺度字典学习的图像融合方法[J]. 西北工业大学学报,2013,31(5),743-797 Wang Jun, Peng Jinye, He Guiqing, Feng Xiaoyi. An Image Fusion Algorithm Based on Multi-Scale Dictionary Learning[J]. Journal of Northwestern Polytechnical University, 2013,31(5):743-797(in Chinese)
[10] 王珺,彭进业,何贵青,等. 基于非下采样Contourlet变换和稀疏表示的红外与可见光图像融合方法[J]. 兵工学报, 2013, 34(7):815-820 Wang Jun, Peng Jinye, He Guiqing, et al. Fusion Method for Visible and Infrared Images Based on Non-Subsampled Contourlet Transform and Sparse Representation[J]. Acta Armamentarii, 2013,34(7):815-820(in Chinese)
[11] Kim Minjae, Han David K, Ko Hanseok. Joint Patch Clustering-Based Dictionary Learning for Multimodal Image Fusion[J]. Information Fusion 2016,27:198-214
[12] Mansour Nejati, Shadrokh Samavi, Shirani Shahram. Multi-Focus Image Fusion Using Dictionary-Based Sparse Representation[J]. Information Fusion, 2015, 25:72-84
[13] 李晖晖,曾艳,杨宁,等. 改进的压缩感知重构算法及其在图像融合中的应用[J]. 南京理工大学学报,2014,38(02):259-263 Li Huihui, Zeng Yan,Yang Ning, et al. Improved Compressed Sensing Reconstruction Algorithm and Its Application in Image fusion[J]. Journal of Nanjing University of Science and Technology, 2014, 38(02):259-263(in Chinese)
[14] 杨森林,万国宾. 基于分块压缩感知的遥感图像多尺度融合[J]. 西北大学学报, 2015,45(3):399-404 Yang Senlin, Wan Guobin. Multi-Scale Fusion for Remote-Sensing Images by Block-Based Compressed Sensing[J]. Journal of Northwest University, 2015,45(3):399-404(in Chinese)
[15] Yu Liu, Shuping Liu, Wang Zengfu. General Framework for Image Fusion Based on Multi-scale Transform and Sparse Representation[J]. Information Fusion 2015,24:147-164
[16] Aslantas V, Bendes E. A New Image Quality Metric for Image Fusion:the Sum of the Correlations of Differences[J]. Int J Electron Commun, 2015, 69:1890-1896
[17] Wang Zhou, Bovik Alanconrad, Hamid Rahimsheikh, et al. Image Quality Assessment:from Error Visibility to Structural Similarity[J]. IEEE Trans on Image Processing, 2004,13(4):600-612
相关文献:
1.段沛沛, 李辉, 李琦.基于结构划分字典学习的雷达目标识别[J]. 西北工业大学学报, 2015,33(4): 672-676
2.王珺, 彭进业, 何贵青, 冯晓毅.基于多尺度字典学习的图像融合方法[J]. 西北工业大学学报, 2013,31(5): 793-797