基于àtrous-NSCT变换和区域特性的图像融合方法
|
摘要
针对àtrous小波变换与NSCT这两种多尺度变换的优缺点,通过引入àtrous-NSCT变换工具,提出了一种基于àtrous-NSCT变换和区域特性的图像融合方法。此方法将区域平均梯度作为活性测度,以系数取大的融合方法完成低频子带图像的融合;选用基于区域方差加权自适应模型的融合方法完成高频子带图像的融合,通过àtrous逆变换处理获得融合后的最终结果。在实验中将新提出的方法与其他5种多尺度融合方法进行比较,结果表明,当新型多尺度变换的分解层数为4时,所获得的融合结果在主观视觉与客观评价两方面的性能都得到了明显的提升。
Aiming at the advantages and disadvantages of two kinds of multi-scale transforms of àtrous wavelet transform and NSCT,through introducing àtrous-NSCT transform tool,this paper proposed an image fusion method based on àtrous-NSCT transform and region characteristics.This method regards the regional average gradient as the activity measure,and makes use of the fusion method with large coefficient to complete the low-frequency sub-band image fusion.Then,it utilizes the fusion method based on adaptive model with regional variance weighting for high-frequency sub-band images to complete the fusion,thus obtaining the final fusion results through àtrous inverse transform process.In the experiment,the proposed method was compared with other five multi-scale fusion methods.The experimental results show that the fusion results obtained by the proposed method are significantly improved in both subjective vision and objective evaluation as the number of decomposition layers of the new multi-scale transformation is 4.
Aiming at the advantages and disadvantages of two kinds of multi-scale transforms of àtrous wavelet transform and NSCT,through introducing àtrous-NSCT transform tool,this paper proposed an image fusion method based on àtrous-NSCT transform and region characteristics.This method regards the regional average gradient as the activity measure,and makes use of the fusion method with large coefficient to complete the low-frequency sub-band image fusion.Then,it utilizes the fusion method based on adaptive model with regional variance weighting for high-frequency sub-band images to complete the fusion,thus obtaining the final fusion results through àtrous inverse transform process.In the experiment,the proposed method was compared with other five multi-scale fusion methods.The experimental results show that the fusion results obtained by the proposed method are significantly improved in both subjective vision and objective evaluation as the number of decomposition layers of the new multi-scale transformation is 4.
引文
[1] WANG J,PENG J,JIANG X,et al.Remote-Sensing Image Fusion Using Sparse Representation with Sub-Dictionaries[J].International Journal of Remote Sensing,2017,38(12):3564-3585.
[2] TAN R L.An Image Fusion Algorithm Using Wavelet Transform[J].Bulletin of Surveying and Mapping,2017(9):42-45.(in Chinese)谭仁龙.一种基于小波变换的图像融合方法[J].测绘通报,2017(9):42-45.
[3] WANG L J,HAN J,ZHANG Y,et al.Image Fusion Via Feature Residual and Statistical Matching[J].Iet Computer Vision,2016,10(6):551-558.
[4] ZHANGJ Y,KUN Z.A Wavelet Image Fusion Algorithm Based on Multi-Resolution and Multi-Scale Transform[J].BoletinTecnico/technical Bulletin,2017,55(7):35-41.
[5] SEAL A,BHATTACHARJEE D,NASIPURI M.Human Face Recognition Using Random Forest Based Fusion of àtrous Wavelet Transform Coefficients from Thermal and Visible Images[J].AEU-International Journal of Electronics and Communications,2016,70(8):1041-1049.
[6] DING L,YANG Z R,WEN R C,et al.Application of Shearlet and Wavelets in Signal and Image Denoising[J].Journal of Na-tural Science of Heilongjiang University,2016,33(2):272-280.(in Chinese)丁亮,杨卓然,闻瑞琛,等.剪切波与小波在信号及图像去噪中的应用[J].黑龙江大学自然科学学报,2016,33(2):272-280.
[7] DO M N,VETTERLI M.The Contourlet Transform:an Effi- cient Directional Multi-Resolution Image Representation[J].IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[8] LABATE D,LIM W Q,KUTYNIOK G,et al.Sparse Multi-Dimensional Representation Using Shearlets[J].Proceedings of the SPIE,2005,39(1):298-318.
[9] YANG D S.Image Fusion Algorithm Based on Shearlet Transform and Block Matching [D].Beijing:Beijing Jiaotong University,2017.(in Chinese)杨东盛.基于剪切波变换和图像块匹配的图像融合算法研究[D].北京:北京交通大学,2017.
[10] DA C A,ZHOU J,DO M N.The Non-Subsampled ContourletTransform:Theory,Design,and Applications[J].IEEE Transa-ctions on Image Processing,2006,15(10):3089-3101.
[11] QIN X,ZHENG J,HU G.Image Fusion Method Based on The Local Neighborhood Feature and Non-Subsampled ContourletTransform[C]//International Conference on Image,Vision and Computing.IEEE,2017:396-400.
[12] LI H,QIU H,YU Z,et al.Infrared and Visible Image Fusion Scheme Based on NSCT and Low-Level Visual Features[J].Infrared Physics & Technology,2016,76(5):174-184.
[13] CAO Y Q,CAO T,HUANG X S.Image Fusion Method Combined CS and Regional Characteristics Based on NSST[J].Computer Engineering and Appications,2018,54(20):190-196.(in Chinese)曹义亲,曹婷,黄晓生.基于NSST的CS与区域特性相结合的图像融合方法[J/OL].计算机工程与应用,2018,54(20):190-196.
[14] FENG Y,HE X S,YANG X S.Infrared and Visual Image Fusion Based on NSCT and Hybrid Particle Swarm Optimization[J].Electronics Optics & Control,2018,25(1):23-27.(in Chinese)冯颖,贺兴时,杨新社.基于NSCT和混合粒子群算法的红外与可见光图像融合[J].电光与控制,2018,25(1):23-27.
[15] ZHANG L,LI Z,LIU J,et al.Improved Algorithm of Adaptive DR Image Denoising Based on Fast Curvelet Transform and Ani-sotropic Median-diffusion Filtering[C]//The 15th International Conference on Biomedical Engineering.Cham:Springer,2014:581-584.
[16] MICHAEL D,MC N,HOLLY S.et al.A Framework for Cognitive Field Studies[J].International Journal of Cognitive Ergonomics,1999,3(4):307-331.
[17] ZHANG K.Research on a Rapid Fusion Method for Remote Sensing Images Based on an Improve Atrous Wavelet Decomposition[D].Kaifeng:Henan University,2016.(in Chinese)张凯.基于改进atrous小波分解的遥感影像快速融合方法的研究[D].开封:河南大学,2016.
[18] HUA K L,DAI B R,SRINIVASAN K,et al.A Hybrid NSCT Domain Image Watermarking Scheme[J].Eurasip Journal on Image & Video Processing,2017,2017(1):1-17.
[19] LI L,SI Y,JIA Z.Remote Sensing Image Enhancement Based on Non-Local Means Filter in NSCT Domain[J].Algorithms,2017,10(4):1-13.
[20] CAO Y Q,HE Y E,HUANG X S.Multi-focus Image Fusion Algorithm Based on Compressed Sensing and Regional Characteristics[J].Computre Science,2017,44(1):295-299.(in Chinese)曹义亲,贺亚飞,黄晓生.基于区域特性的压缩感知多聚焦融合算法[J].计算机科学,2017,44(1):295-299.
[21] GONG J M,YANG X,YANG M,et al.An Image Fusion Algorithm Based on Region Average Gradient and Region Energy[J].Journal of Xi’an University of Posts and Telecommunications,2016,21(3):54-58.(in Chinese)巩稼民,杨潇,杨萌,等.基于区域平均梯度与区域能量的图像融合[J].西安邮电大学学报,2016,21(3):54-58.
[2] TAN R L.An Image Fusion Algorithm Using Wavelet Transform[J].Bulletin of Surveying and Mapping,2017(9):42-45.(in Chinese)谭仁龙.一种基于小波变换的图像融合方法[J].测绘通报,2017(9):42-45.
[3] WANG L J,HAN J,ZHANG Y,et al.Image Fusion Via Feature Residual and Statistical Matching[J].Iet Computer Vision,2016,10(6):551-558.
[4] ZHANGJ Y,KUN Z.A Wavelet Image Fusion Algorithm Based on Multi-Resolution and Multi-Scale Transform[J].BoletinTecnico/technical Bulletin,2017,55(7):35-41.
[5] SEAL A,BHATTACHARJEE D,NASIPURI M.Human Face Recognition Using Random Forest Based Fusion of àtrous Wavelet Transform Coefficients from Thermal and Visible Images[J].AEU-International Journal of Electronics and Communications,2016,70(8):1041-1049.
[6] DING L,YANG Z R,WEN R C,et al.Application of Shearlet and Wavelets in Signal and Image Denoising[J].Journal of Na-tural Science of Heilongjiang University,2016,33(2):272-280.(in Chinese)丁亮,杨卓然,闻瑞琛,等.剪切波与小波在信号及图像去噪中的应用[J].黑龙江大学自然科学学报,2016,33(2):272-280.
[7] DO M N,VETTERLI M.The Contourlet Transform:an Effi- cient Directional Multi-Resolution Image Representation[J].IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[8] LABATE D,LIM W Q,KUTYNIOK G,et al.Sparse Multi-Dimensional Representation Using Shearlets[J].Proceedings of the SPIE,2005,39(1):298-318.
[9] YANG D S.Image Fusion Algorithm Based on Shearlet Transform and Block Matching [D].Beijing:Beijing Jiaotong University,2017.(in Chinese)杨东盛.基于剪切波变换和图像块匹配的图像融合算法研究[D].北京:北京交通大学,2017.
[10] DA C A,ZHOU J,DO M N.The Non-Subsampled ContourletTransform:Theory,Design,and Applications[J].IEEE Transa-ctions on Image Processing,2006,15(10):3089-3101.
[11] QIN X,ZHENG J,HU G.Image Fusion Method Based on The Local Neighborhood Feature and Non-Subsampled ContourletTransform[C]//International Conference on Image,Vision and Computing.IEEE,2017:396-400.
[12] LI H,QIU H,YU Z,et al.Infrared and Visible Image Fusion Scheme Based on NSCT and Low-Level Visual Features[J].Infrared Physics & Technology,2016,76(5):174-184.
[13] CAO Y Q,CAO T,HUANG X S.Image Fusion Method Combined CS and Regional Characteristics Based on NSST[J].Computer Engineering and Appications,2018,54(20):190-196.(in Chinese)曹义亲,曹婷,黄晓生.基于NSST的CS与区域特性相结合的图像融合方法[J/OL].计算机工程与应用,2018,54(20):190-196.
[14] FENG Y,HE X S,YANG X S.Infrared and Visual Image Fusion Based on NSCT and Hybrid Particle Swarm Optimization[J].Electronics Optics & Control,2018,25(1):23-27.(in Chinese)冯颖,贺兴时,杨新社.基于NSCT和混合粒子群算法的红外与可见光图像融合[J].电光与控制,2018,25(1):23-27.
[15] ZHANG L,LI Z,LIU J,et al.Improved Algorithm of Adaptive DR Image Denoising Based on Fast Curvelet Transform and Ani-sotropic Median-diffusion Filtering[C]//The 15th International Conference on Biomedical Engineering.Cham:Springer,2014:581-584.
[16] MICHAEL D,MC N,HOLLY S.et al.A Framework for Cognitive Field Studies[J].International Journal of Cognitive Ergonomics,1999,3(4):307-331.
[17] ZHANG K.Research on a Rapid Fusion Method for Remote Sensing Images Based on an Improve Atrous Wavelet Decomposition[D].Kaifeng:Henan University,2016.(in Chinese)张凯.基于改进atrous小波分解的遥感影像快速融合方法的研究[D].开封:河南大学,2016.
[18] HUA K L,DAI B R,SRINIVASAN K,et al.A Hybrid NSCT Domain Image Watermarking Scheme[J].Eurasip Journal on Image & Video Processing,2017,2017(1):1-17.
[19] LI L,SI Y,JIA Z.Remote Sensing Image Enhancement Based on Non-Local Means Filter in NSCT Domain[J].Algorithms,2017,10(4):1-13.
[20] CAO Y Q,HE Y E,HUANG X S.Multi-focus Image Fusion Algorithm Based on Compressed Sensing and Regional Characteristics[J].Computre Science,2017,44(1):295-299.(in Chinese)曹义亲,贺亚飞,黄晓生.基于区域特性的压缩感知多聚焦融合算法[J].计算机科学,2017,44(1):295-299.
[21] GONG J M,YANG X,YANG M,et al.An Image Fusion Algorithm Based on Region Average Gradient and Region Energy[J].Journal of Xi’an University of Posts and Telecommunications,2016,21(3):54-58.(in Chinese)巩稼民,杨潇,杨萌,等.基于区域平均梯度与区域能量的图像融合[J].西安邮电大学学报,2016,21(3):54-58.