计算机科学 ›› 2013, Vol. 40 ›› Issue (9): 270-274.

• 图形图像与模式识别 • 上一篇    下一篇

一种基于变分方法的多分辨率域融合策略

马宁,周则明,罗立民   

  1. 解放军理工大学气象海洋学院 南京210007;解放军理工大学气象海洋学院 南京210007;东南大学影像科学与技术实验室 南京210096
  • 出版日期:2018-11-16 发布日期:2018-11-16
  • 基金资助:
    本文受国家自然科学基金(41174164),解放军理工大学预研基金(KYQYZLXY1207)资助

Variational Fusion Strategy for Multiscale Analysis Domain

MA Ning,ZHOU Ze-ming and LUO Li-min   

  • Online:2018-11-16 Published:2018-11-16

摘要: 针对常规多分辨率域融合策略的处理过于直接可能会降低融合图像质量的现象,提出了一种多分辨率域变分融合策略。该策略根据源图像分解系数的梯度信息构造目标系数梯度场,寻找梯度最接近目标梯度场的系数作为融合图像的分解系数。为了保持与源图像的相似性,对高、低频系数分别加入了约束条件。针对高频系数对噪声敏感的特点,还引入了全变分项来保证解的平滑性。在多聚焦图像、红外图像与可见光图像上的融合实验结果表明:与常规融合策略相比,提出的融合策略能够注入更多的空间细节信息,同时能更有效地保留源图像的结构信息。

关键词: 多分辨率分析,变分,图像融合,融合策略 中图法分类号TP391.4文献标识码A

Abstract: Conventional fusion strategies typically manipulate the fused coefficiented too directly,which may introduce artifacts and decrease the fused image quality.This paper presented a variational fusion strategy for multiscale analysis domain.An energy minimization problem was proposed to find the solution whose gradient is closest to that of the target gradient field,which is built from the gradient information of the source images’ decomposition coefficients.To keep the similarity with source images,the constraint condition was imposed into the highpass and lowpass coefficients separately.Since the highpass coefficients are sensitive to the noise,the total variation term is also introduced to assure the smoothness of the solution.The performance of the proposed fusion strategy was evaluated on multifocus images,infrared and visible images.Experimental results show that the strategy can inject more spatial detail information and meanwhile preserve more structural information of the original image than conventional fusion strategies.

Key words: Multiscale analysis,Variation,Image fusion,Fusion strategy

[1] Pajares G,de la Cruz J M.A wavelet-based image fusion tutorial[J].Pattern Recognition,2004,37(9):1855-1872
[2] 陈焕平,何明一,李旭.基于SWT区域对比度像素提取的多聚焦图像融合[J].中国图象图形学报,2011,16(5):865-870
[3] 杨艳春,党建武,王阳萍,等.基于提升小波变换的医学图像融合方法[J].计算机科学,2011,38(12):266-268
[4] 杨晓慧,贾建,焦李成.基于活性测度和闭环反馈的非下采样Contourlet域图像融合[J].电子与信息学报,2010,32(2):422-426
[5] Piella G.Image fusion for enhanced visualization:A variational approach[J].International journal of computer vision,2009,83(1):1-11
[6] Sapiro G.On the level lines and geometry of vector-valued images[J].IEEE Signal Processing Letters,2000,7(9):241-243
[7] Socolinsky D A.A variational approach to image fusion[D].The Johns Hopkins University,2000
[8] Socolinsky D A,Wolff L B.Multispectral image visualizationthrough first-order fusion[J].IEEE Transactions on Image Processing,2002,11(8):923-931
[9] Bertalmío M,Caselles V,Provenzi E,et al.Perceptual color correction through variational techniques[J].IEEE Transactions on Image Processing,2007,16(4):1058-1072
[10] Rudin L I,Osher S,Fatemi E.Nonlinear total variation basednoise removal algorithms[J].Physica D:Nonlinear Phenomena,1992,60(1):259-268
[11] Jiang Xiao-yu,Zhou Li-wei,Gao Zhi-yun.Multispectral imagefusion using wavelet transform[C]∥Electronic Imaging and Multimedia Systems.Beijing,China,1996,2898:35-42
[12] Zheng Yong-an,Zhu Chang-sheng,Song Jian-she,et al.Fusion of multi-band SAR images based on Contourlet transform[C]∥International Conference on Information Acquisition.Shandong,China,2006:420-424
[13] Qu Gui-hong,Zhang Da-li,Yan Ping-fan.Medical image fusionby wavelet transform modulus maxima[J].Optics Express,2001,9(4):184-190
[14] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612
[15] Piella G,Heijmans H.A new quality metric for image fusion[C]∥International Conference on Image Processing.Barcelona,Spain,2003:173-176

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!