基于区域分维和非采样Contourlet变换的图像融合算法
|
摘要
针对源图像有用信息的提取,提出了基于区域分维和非下采样Contourlet变换相结合的红外与可见光图像融合算法.将图像的区域属性、区域大小、边缘强度以及纹理显著程度等特点用图像不同尺度上的区域分维进行描述,对于非下采样Contourlet变换低频系数,根据源图像不同尺度上的区域分维进行基于系数选择的融合.针对带通子带系数设计了系数局部匹配度算子,依据匹配度不同采用加权和系数选取相结合的融合规则.与其他常规融合方法进行比较,该算法可有效实现红外与可见光图像的融合.
As an important problem in the course of image fusion,the extraction of useful information from source images affects the fusion result directly,and it is all along one of the research focuses and difficult ponits of image fusion.A novel image fusion method for infrared and visible images based on nonsubsampled contourlet transform and fractal dimension is proposed.The regional properties,size of regions,intensity of edges and the strength of texture are all described by the regional fractal dimensions in different scales.Through selecting coefficients from two source images based on regional fractal dimension,the low frequency subband coefficients of the source images are fused.The bandpass directional coefficients are fused using different strategies based on the matching operator proposed.Compared with other methods,experimental results show that the proposed algorithm is effective and feasible.
As an important problem in the course of image fusion,the extraction of useful information from source images affects the fusion result directly,and it is all along one of the research focuses and difficult ponits of image fusion.A novel image fusion method for infrared and visible images based on nonsubsampled contourlet transform and fractal dimension is proposed.The regional properties,size of regions,intensity of edges and the strength of texture are all described by the regional fractal dimensions in different scales.Through selecting coefficients from two source images based on regional fractal dimension,the low frequency subband coefficients of the source images are fused.The bandpass directional coefficients are fused using different strategies based on the matching operator proposed.Compared with other methods,experimental results show that the proposed algorithm is effective and feasible.
引文
[1]PIELLA G.A general framework for multiresolution i mage fusion:frompixels to regions[J].Information Fusion,2003,4(4):259-280.
[2]PIELLA G.A region-based multiresolution i mage fusion algorithm[C].Proceedings of the Fifth International Conference on Information Fusion.Sunnyvale:Int Soc Inf Fusion,2002,168-173.
[3]LEWIS J J,O′CALLAGHAN RJ,NIKOLOVS G,et al.Pixel-and region-based i mage fusion with complex wavelets[J].Information Fusion,2007,8(2):119-130.
[4]YU Tian-he,LI Qiu-ming,DAI Jing-min.Newenhancement of infrared i mage based on human visual system[J].Chinese Optics Letters,2009,7(3):206-209.
[5]ZHAO Yong-qiang,PAN Quan,ZHANG Hong-cai.Study of adaptive multi-band polarization i mage fusion[J].Acta Photonica Sinica,2007,36(7):1356-1359.赵永强,潘泉,张洪才.自适应多波段偏振图像融合研究[J].光子学报,2007,36(7):1356-1359.
[6]YAN Wen-hao,MA Cai-wen,ZHANG Ming,et al.A New Way for I mage Fusion Based on Wavelet Transform[J].Acta Photonica Sinica,2006,35(4):638-640.燕文浩,马彩文,张鸣,等.基于小波变换的图像融合新算法[J].光子学报,2006,35(4):638-640.
[7]ZHANG Qiang,GUO Bao-long.Fusion of multifocus i mages based on the nonsubsampled contourlet transform[J].Acta Photonica Sinica,2008,37(4):476-480.
[8]YE Chuan-qi,WANG Bao-shu,MI AO Qi-guang.Fusion algorithmof infrared and visiblei mages based on regionfeature[J].Acta Photonica Sinica,2009,38(6):1498-1503.叶传奇,王宝树,苗启广.一种基于区域特性的红外与可见光图像融合算法[J].光子学报,2009,38(6):1498-1503.
[9]DO M N,VETTERLI M.Contourlets:a directional multiresolutioni mage representation[C].Proceedings of2002International Conference on Image Processing.Piscataway:IEEE,2002:357-360.
[10]DO M N,VETTERLI M.The contourlet transform:an efficient directional multiresolution i mage representation[J].IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[11]da CUNHA A L,ZHOU Jian-ping,DO M N.The Nonsubsampled Contourlet Transform:Theory,Design,and Applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101.
[12]CHEN Yong,CHEN Ling.Fractal Geometry[M].Beijing:Earthquake Publishing House,2005:59-61.陈颙,陈凌.分形几何学[M].北京:地震出版社,2005:59-61.
[13]QI N Qi-ming,LU Rong-jian.Satellite i mage classification based on fractal di mension and neural networks[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2000,36(6):858-864.秦其明,陆荣建.分形与神经网络方法在卫星数字图像分类中的应用[J].北京大学学报(自然科学版),2000,36(6):858-864.
[2]PIELLA G.A region-based multiresolution i mage fusion algorithm[C].Proceedings of the Fifth International Conference on Information Fusion.Sunnyvale:Int Soc Inf Fusion,2002,168-173.
[3]LEWIS J J,O′CALLAGHAN RJ,NIKOLOVS G,et al.Pixel-and region-based i mage fusion with complex wavelets[J].Information Fusion,2007,8(2):119-130.
[4]YU Tian-he,LI Qiu-ming,DAI Jing-min.Newenhancement of infrared i mage based on human visual system[J].Chinese Optics Letters,2009,7(3):206-209.
[5]ZHAO Yong-qiang,PAN Quan,ZHANG Hong-cai.Study of adaptive multi-band polarization i mage fusion[J].Acta Photonica Sinica,2007,36(7):1356-1359.赵永强,潘泉,张洪才.自适应多波段偏振图像融合研究[J].光子学报,2007,36(7):1356-1359.
[6]YAN Wen-hao,MA Cai-wen,ZHANG Ming,et al.A New Way for I mage Fusion Based on Wavelet Transform[J].Acta Photonica Sinica,2006,35(4):638-640.燕文浩,马彩文,张鸣,等.基于小波变换的图像融合新算法[J].光子学报,2006,35(4):638-640.
[7]ZHANG Qiang,GUO Bao-long.Fusion of multifocus i mages based on the nonsubsampled contourlet transform[J].Acta Photonica Sinica,2008,37(4):476-480.
[8]YE Chuan-qi,WANG Bao-shu,MI AO Qi-guang.Fusion algorithmof infrared and visiblei mages based on regionfeature[J].Acta Photonica Sinica,2009,38(6):1498-1503.叶传奇,王宝树,苗启广.一种基于区域特性的红外与可见光图像融合算法[J].光子学报,2009,38(6):1498-1503.
[9]DO M N,VETTERLI M.Contourlets:a directional multiresolutioni mage representation[C].Proceedings of2002International Conference on Image Processing.Piscataway:IEEE,2002:357-360.
[10]DO M N,VETTERLI M.The contourlet transform:an efficient directional multiresolution i mage representation[J].IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[11]da CUNHA A L,ZHOU Jian-ping,DO M N.The Nonsubsampled Contourlet Transform:Theory,Design,and Applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101.
[12]CHEN Yong,CHEN Ling.Fractal Geometry[M].Beijing:Earthquake Publishing House,2005:59-61.陈颙,陈凌.分形几何学[M].北京:地震出版社,2005:59-61.
[13]QI N Qi-ming,LU Rong-jian.Satellite i mage classification based on fractal di mension and neural networks[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2000,36(6):858-864.秦其明,陆荣建.分形与神经网络方法在卫星数字图像分类中的应用[J].北京大学学报(自然科学版),2000,36(6):858-864.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心