一种基于形态分量的多聚焦图像融合算法
|
摘要
提出一种基于形态分量思想的多聚焦图像融合算法。该方法首先对源图像迭代分解,将其分解为低频和高频两个分量,并用curvelet变换表示低频分量,然后,对低频分量采用高斯差分算子定义图像点的特征活跃度和融合规则,对高频分量的细节特征度量采用加权梯度差的方法来衡量和融合。仿真实验在四组多聚焦图像中进行,除了与传统的图像融合算法做比较外,还与系数绝对值最大法的融合算法进行比较。实验结果表明:该方法在平均梯度、空间频率、信息熵等指标上优于传统的图像融合方法,同时也优于基于系数绝对值最大法的融合规则。
This paper presents a multi-focus image fusion algorithm based on morphological component.Firstly,source images are decomposed into low-frequent components and high-frequent components by iteration,and curvelet transformation is used for low-frequent components. Secondly,the low-frequent components are fused by applying a rule of feature activity which is defined by using the operator of difference of Gaussian,and the high frequent components are fused by means of a rule of details information which is defined by using weighted gradient. Finally,simulation experiments are conducted through four groups of multi-focus images. The experimental results compared with ones by traditional image fusion algorithm and the algorithm of the max absolute value of component coefficients. The experimental results show that the proposed algorithm outperforms other approaches in terms of average gradient,space frequence and entroy.
This paper presents a multi-focus image fusion algorithm based on morphological component.Firstly,source images are decomposed into low-frequent components and high-frequent components by iteration,and curvelet transformation is used for low-frequent components. Secondly,the low-frequent components are fused by applying a rule of feature activity which is defined by using the operator of difference of Gaussian,and the high frequent components are fused by means of a rule of details information which is defined by using weighted gradient. Finally,simulation experiments are conducted through four groups of multi-focus images. The experimental results compared with ones by traditional image fusion algorithm and the algorithm of the max absolute value of component coefficients. The experimental results show that the proposed algorithm outperforms other approaches in terms of average gradient,space frequence and entroy.
引文
[1]才溪.多尺度图像融合理论与方法[M].北京:电子工业出版社,2014.
[2] JAMES ALEX PAPPACHEN,DASARATHY BELUR V. Medical image fusion:a survey of the state of the art[J]. Information Fusion,2017,19:4-19.
[3] LI SHUTAO,KANG XUDONG,FANG LEYUAN. Pixel-level image fusion:a survey of the state of the art[J]. Information Fusion,2017,33:100-112.
[4] TANG J S. A contrast based image fusion technique in the DCT domain[J]. Digital Signal Processing,2004,14(3):218-226.
[5] 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. DOI:10. 1016/J. compeleceng. 2011.04. 016.
[6]晁锐,张科,李言俊.一种基于小波变换的图像融合算法[J].电子学报,2004,32(5):750-753.
[7] HILL PAUL,AL-MUALLA MOHAMMED EBRAHIM,BULL DAVID. Perceptual image fusion using wavelets[J].IEEE Transactions on Image Processing,2017,26(3):1076-1088.
[8] YU BITING,JIA BO,DING LU. Hybrid dual-tree complex wavelet transform and support vector machine for digitalmultifocus image fusion[J]. Neurocomputing,2016,182(19):1-9.
[9] ABDIPOUR MOHAMMAD,NOOSHYAR MEHDI. Multi-focus image fusion using sharpness criteria for visual sensor networks in wavelet domain[J]. COMPUTERS&ELECTRICAL ENGINEERING,2016,51(4):74-88.
[10] YANG YONG,TONG SONG,HUANG SHUYING. A hybrid method for multi-focus image fusion based on fast discrete curvelet transform[J]. IEEE Access,2017,5:14898-14913.
[11] GATTIM N K,RAJESH V,PARTHEEPAN R. Multimodal image fusion using curvelet and genetic algorithm[J].Joural of Scientific&Industrial Research[J]. 2017,76(11):694-699.
[12] DONG LIMIN,YANG QINGXIANG,WU HAIYONG. High quality multi-spectral and panchromatic image fusion technologies based on curvelet transform[J]. Neurocomputing,2015,159(7):268-274.
[13]时丕丽,郭雷,李晖晖.基于NSCT的SAR与可见光图像融合方法[J].计算机应用研究,2013,30(5):1568-1570.
[14] SRIVASTAVA R,KHARE A. Multifocus noisy image fusion using contourlet transform[J]. Imaging Science Journal,2015,63(7):408-422.
[15] XU HUA,WANG YAN,WU YUJING. Infrared and multi-type images fusion algorithm based on contrast pyramid transform[J]. Infrared Physics&Technology,2016,78(9):133-146.
[16] ZHANG QIANG,WANG LONG,LI HUIJUAN. Similarity-based multimodality image fusion with shiftable complex directional pyramid[J]. Pattern Recognition Letters,2011,32(13):1544-1553.
[17]焦李成,尚荣华,刘芳,等.稀疏学习、分类与识别[M].北京:科学出版社,2017.
[18] MA JIANWEI,PLONKA GERLIND. The curvelet transform[J]. IEEE Signal Processing Magazine,2010,27(2):118-133.
[19] CANDES E J,DONOHO D L. Recovering edges in ill-posed inverse problems:optimality of curvelet frames[J]. Annals of Statistics,2002,30(3):784-842.
[20] CANDES EMMANUEL,DEMANET LAURENT,DONOHO DAVID. Fast discrete curvelet transforms[J]. Multiscale Modeling&Simulation,2006,5(3):861-899.
[21] STARCK J L,CANDES E J,DONOHO D L. The curvelet transform for image denoising[J]. IEEE Transactions on Image Processing,2002,11(6):670-684.
[22] STARCK J L,MURTAGH F,CANDES E J. Gray and color image contrast enhancement by the curvelet transform[J].IEEE Transactions on Image Processing,2003,12(6):706-717.
[23] HERRMANN FELIX J,HENNENFENT GILLES. Non-parametric seismic data recovery with curvelet frames[J]. Geophysical Journal International,2008,173(1):233-248.
[24] STARCK J L,ELAD M,DONOHO D. Redundant multiscale transforms and their application for morphological component analysis[J]. Advances in Imaging and Electron Physics,2004,132(82):287-348.
[25] STARCK J L,ELAD M,DONOHO D. Image decomposition via the combination of sparse representation and a variational approach[J]. IEEE Trans Image Processing,2005,14(10):1570-1582.
[26]章毓晋.图像工程:上册.图像处理[M]. 2版.北京:清华大学出版社,2006.
[27] JIANG Y,WANG M H. Image fusion with morphological component analysis[J]. Information Fusion,2014(18):107-118.
[28]左飞.图像处理的数学修炼[M].北京:清华大学出版社,2017.
[29]高健,黄心汉,彭刚,等.基于Harris角点和高斯差分的特征点提取算法[J].模式识别与人工智能,2008,21(2):171-176.
[30]王兆仲,周付根.基于高斯差分滤波器的图像光场矫正[J].红外与激光工程,2000,29(6):64-67.
[2] JAMES ALEX PAPPACHEN,DASARATHY BELUR V. Medical image fusion:a survey of the state of the art[J]. Information Fusion,2017,19:4-19.
[3] LI SHUTAO,KANG XUDONG,FANG LEYUAN. Pixel-level image fusion:a survey of the state of the art[J]. Information Fusion,2017,33:100-112.
[4] TANG J S. A contrast based image fusion technique in the DCT domain[J]. Digital Signal Processing,2004,14(3):218-226.
[5] 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. DOI:10. 1016/J. compeleceng. 2011.04. 016.
[6]晁锐,张科,李言俊.一种基于小波变换的图像融合算法[J].电子学报,2004,32(5):750-753.
[7] HILL PAUL,AL-MUALLA MOHAMMED EBRAHIM,BULL DAVID. Perceptual image fusion using wavelets[J].IEEE Transactions on Image Processing,2017,26(3):1076-1088.
[8] YU BITING,JIA BO,DING LU. Hybrid dual-tree complex wavelet transform and support vector machine for digitalmultifocus image fusion[J]. Neurocomputing,2016,182(19):1-9.
[9] ABDIPOUR MOHAMMAD,NOOSHYAR MEHDI. Multi-focus image fusion using sharpness criteria for visual sensor networks in wavelet domain[J]. COMPUTERS&ELECTRICAL ENGINEERING,2016,51(4):74-88.
[10] YANG YONG,TONG SONG,HUANG SHUYING. A hybrid method for multi-focus image fusion based on fast discrete curvelet transform[J]. IEEE Access,2017,5:14898-14913.
[11] GATTIM N K,RAJESH V,PARTHEEPAN R. Multimodal image fusion using curvelet and genetic algorithm[J].Joural of Scientific&Industrial Research[J]. 2017,76(11):694-699.
[12] DONG LIMIN,YANG QINGXIANG,WU HAIYONG. High quality multi-spectral and panchromatic image fusion technologies based on curvelet transform[J]. Neurocomputing,2015,159(7):268-274.
[13]时丕丽,郭雷,李晖晖.基于NSCT的SAR与可见光图像融合方法[J].计算机应用研究,2013,30(5):1568-1570.
[14] SRIVASTAVA R,KHARE A. Multifocus noisy image fusion using contourlet transform[J]. Imaging Science Journal,2015,63(7):408-422.
[15] XU HUA,WANG YAN,WU YUJING. Infrared and multi-type images fusion algorithm based on contrast pyramid transform[J]. Infrared Physics&Technology,2016,78(9):133-146.
[16] ZHANG QIANG,WANG LONG,LI HUIJUAN. Similarity-based multimodality image fusion with shiftable complex directional pyramid[J]. Pattern Recognition Letters,2011,32(13):1544-1553.
[17]焦李成,尚荣华,刘芳,等.稀疏学习、分类与识别[M].北京:科学出版社,2017.
[18] MA JIANWEI,PLONKA GERLIND. The curvelet transform[J]. IEEE Signal Processing Magazine,2010,27(2):118-133.
[19] CANDES E J,DONOHO D L. Recovering edges in ill-posed inverse problems:optimality of curvelet frames[J]. Annals of Statistics,2002,30(3):784-842.
[20] CANDES EMMANUEL,DEMANET LAURENT,DONOHO DAVID. Fast discrete curvelet transforms[J]. Multiscale Modeling&Simulation,2006,5(3):861-899.
[21] STARCK J L,CANDES E J,DONOHO D L. The curvelet transform for image denoising[J]. IEEE Transactions on Image Processing,2002,11(6):670-684.
[22] STARCK J L,MURTAGH F,CANDES E J. Gray and color image contrast enhancement by the curvelet transform[J].IEEE Transactions on Image Processing,2003,12(6):706-717.
[23] HERRMANN FELIX J,HENNENFENT GILLES. Non-parametric seismic data recovery with curvelet frames[J]. Geophysical Journal International,2008,173(1):233-248.
[24] STARCK J L,ELAD M,DONOHO D. Redundant multiscale transforms and their application for morphological component analysis[J]. Advances in Imaging and Electron Physics,2004,132(82):287-348.
[25] STARCK J L,ELAD M,DONOHO D. Image decomposition via the combination of sparse representation and a variational approach[J]. IEEE Trans Image Processing,2005,14(10):1570-1582.
[26]章毓晋.图像工程:上册.图像处理[M]. 2版.北京:清华大学出版社,2006.
[27] JIANG Y,WANG M H. Image fusion with morphological component analysis[J]. Information Fusion,2014(18):107-118.
[28]左飞.图像处理的数学修炼[M].北京:清华大学出版社,2017.
[29]高健,黄心汉,彭刚,等.基于Harris角点和高斯差分的特征点提取算法[J].模式识别与人工智能,2008,21(2):171-176.
[30]王兆仲,周付根.基于高斯差分滤波器的图像光场矫正[J].红外与激光工程,2000,29(6):64-67.