基于非抽样剪切波的加权区域图像融合

李隆, 傅依柳, 柴昱洲, 陈霄鹏, 高当丽, 屈子杰

李隆, 傅依柳, 柴昱洲, 陈霄鹏, 高当丽, 屈子杰. 基于非抽样剪切波的加权区域图像融合[J]. 应用光学, 2015, 36(5): 735-741. DOI: 10.5768/JAO201536.0502002
引用本文: 李隆, 傅依柳, 柴昱洲, 陈霄鹏, 高当丽, 屈子杰. 基于非抽样剪切波的加权区域图像融合[J]. 应用光学, 2015, 36(5): 735-741. DOI: 10.5768/JAO201536.0502002
shu
Li Long, Fu Yi-liu, Chai Yu-zhou, Chen Xiao-peng, Gao Dang-li, Qu Zi-jie. Image fusion based on non-sampling shearlets and weighted area feature[J]. Journal of Applied Optics, 2015, 36(5): 735-741. DOI: 10.5768/JAO201536.0502002
Citation: Li Long, Fu Yi-liu, Chai Yu-zhou, Chen Xiao-peng, Gao Dang-li, Qu Zi-jie. Image fusion based on non-sampling shearlets and weighted area feature[J]. Journal of Applied Optics, 2015, 36(5): 735-741. DOI: 10.5768/JAO201536.0502002
shu

基于非抽样剪切波的加权区域图像融合

  • 1.

    西安建筑科技大学 理学院,陕西 西安 710055;

  • 2.

    贵州大学 大数据与信息工程学院,贵州 贵阳 550025

基金项目: 

陕西省自然科学基金（2014JQ1008）

详细信息
    通讯作者:

    李隆（1972-），男，河南正阳人，博士，教授，主要从事激光技术及光电技术方面的研究。 Email：lilong@xauat.edu.cn

  • 中图分类号: TN911.73

Image fusion based on non-sampling shearlets and weighted area feature

  • 1.

    Faculty of Science,Xi’an University of Architecture &Technology,Xi’an 710055,China;

  • 2.

    College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China

摘要

    摘要
  • 摘要: 以提升遥感图像和多聚焦图像的融合精度为目的，结合非下采样剪切波变换（NSST）可以捕捉图像的细节特征，提出了一种NSST和加权区域特性的图像融合方法。利用非下采样剪切波变换对源图像进行多尺度、多方向分解，得到低频子带和高频子带，低频子带系数采用改进梯度投影的非负矩阵分解（NMF），高频子带系数采用加权区域能量和区域方差相结合的融合策略，然后应用非下采样剪切波的逆变换得到融合的图像。实验结果表明：该方法从主观视觉方面很好地保留了多幅图像的有用信息，给出该方法与其他融合算法在客观评价指标应用信息熵EN、互信息MI和加权边缘信息量QAB/F的比较结果 。
    Abstract: To improve the remote sensing image and multi-focus image fusion accuracy, combined with the non-sampling shearlets transform (NSST) which can capture the details of the image features, we proposed a image fusion method based on NSST and weighted area feature. Firstly this method uses nonsampling shearlets transform for source image to carry on multi-scale multi-direction decomposition to get low-frequency and high-frequency subbands.Then the improved gradient projection of non-negative matrix factorization(NMF) is used for the low-frequency sub-band coefficient,while the high frequency sub-band coefficient uses the fusion strategy combining the regional energy and variance of the weighted area. Finally, the non-sampling shearlets inverse transformation is used to get image fusion. The experimental results show that this method can well retain the useful information of multiple images from the aspect of subjective vision,and the comparison results are given with other fusion methods from the aspect of objective evaluation indexes such as entropy, mutual information and weighted edge information preservation values.
    • HTML全文
    • 参考文献(1)
  • [1]Do M N, Vetter M. The contourlet transform: an efficient directional multiresolution image repreisentation[J]. IEEE Trans. on Image Processing, 2005,14(12):2091-2106.
    [2]Cunha A L, Zhou J P, Dom N. The non-subsampled  contourlet transform: theory, design, and application[J].  IEEE Trans. on Image Processing, 2006, 15(10): 3089-3101.
    [3]Guo K，Labate  D.Characterization and analysis of edges using the continuous shearlet transform[J]. SIAM Journal on Imaging Sciences, 2009, 2(3):959-986.
    [4]Cao Yuan,Li Shutao, Hu Jianwen. Multi-focus image fusion by nonsub sampled shear-let transform[C]. US: IEEE,2011:17-21.
    [5]Yang Yuetao, Zhu Ming, He Baigen,et.al., Fusion algorithm based on improved projected gradient NMF and NSCT[J].Optics  and Precision Engineering. 2011, 19 (5): 1143-1145.
    杨粤涛,朱明,贺柏根,等.采用改进投影梯度非负矩阵分解和非采样Contourlet变换的图像融合方法[J]. 光学精密工程, 2011, 19(5): 1143-1150.
    [6]Li Le, Zhang Yujin. A survey algorithms of nonnegative matrix factorization[J]. Acta Electronica Sinica,2008, 36(4): 737-743.
    李乐,章毓晋. 非负矩阵算法综述[J]. 电子学报, 2008, 36(4): 737-743.
    [7]Zheng Wei, Sun Xueqing, Li Zhe,et al. Image fusion based on shearlet transform and region characteristics[J]. Laser Technology, 2015, 39(1):50-56.
    郑伟,孙雪青,李哲,等.Shearlet变换和区域特性相结合的图像融合[J].激光技术,2015,39(1):50-56.
    [8]Zhang Qiang, Guo Baolong. Fusion of infrared and visible light images based on nonsubsampled contourlet transform[J]. Journal of Infrared and Millimeter Waves, 2007, 26 (6): 476-480.
    张强,郭宝龙.一种基于非采样Contourlet变换红外图像与可见光图像融合算法[J].红外与毫米波学报, 2007, 26 (6): 476-480.
    [9]Yue Zhen, Li Fanming. Polarization image fusion algorithm based on wavelet transform[J]. Journal of Applied Optics, 2014,35 (2):321-326.
    岳振,李范鸣.一种基于小波变换的红外偏振融合[J].应用光学, 2014,35 (2): 321-326.
    [10]Na Yan, Jiao Licheng. Image fusion method based multiresolution analysis theory[M]. Xi’an Press of Xidian University, 2007.
     那彦,焦李成. 基于多分辨分析理论的图像融合方法[M].西安:西安电子科技大学出版社,2007.
    [11]Alejaily A M,Rube I A E,Mangoud M A. Fusion of remote sensing images using contour let transform [M]. Berlin: Springer-Verlag, 2008:213-218.
    [12]Lu Yaning, Guo Lei, Li Huihui. Remote sensing image fusion using edge information and features of SAR image based on curve let transform[J]. Acta Photonic Sinica, 2012, 41(9): 1118-1123.
    [13]Gao Shaoshu, Jin Weiqi, Wang Lingxue, et al. Objective quality assement of image fusion[J]. Journal of Applied Optics, 2011, 32 (4): 671-677.
    高绍姝,金伟其,王岭雪,等.图像融合质量客观评价方法 [J].应用光学,2011,32(4):671-677.
    • 相关文章
    • 施引文献(4)

  • 期刊类型引用(3)

    1. 王芳, 陈燕. 基于信息量制约的遥感图像融合算法. 太赫兹科学与电子信息学报. 2020(03): 470-476 . 百度学术
    2. 朱达荣, 许露, 汪方斌, 刘涛, 储朱涛. 基于区域能量的NSST域偏振图像融合算法. 安徽建筑大学学报. 2017(04): 43-48 . 百度学术
    3. 李艳玮, 郑伟勇. 改进对比度和空间频率的图像融合算法. 计算机工程与设计. 2017(09): 2457-2463 . 百度学术

    其他类型引用(1)

    • 资源附件(0)
计量
  • 文章访问数:  1614
  • HTML全文浏览量:  120
  • PDF下载量:  95
  • 被引次数: 4
出版历程

目录

摘要
HTML全文
    参考文献(1)
    相关文章
    施引文献(4)
    资源附件(0)

    /

    返回文章
    返回

    相关数据库

    广告合作

    友情链接

    帮助中心

    扫描关注本刊微信平台

    您是第  2900149位访问者，欢迎！

    地址: 西安市电子三路西段9号 邮政编码: 710065 联系电话: 029-88288172

    版权所有 © 《应用光学》编辑部

    陕公网安备 61011302001501号       陕ICP备19002862号-1

    北京仁和汇智信息技术有限公司 开发  技术支持: info@rhhz.net   百度统计