基于增补小波变换和PCNN的NSCT域图像融合算法
|
摘要
针对传统NSCT图像融合算法存在的不足,提出一种基于增补小波变换和PCNN的NSCT域图像融合算法。首先对源图像进行NSCT分解,生成一系列低频和高频分量。对低频分量利用二维小波分解,生成一个低频和三个方向分量,对低频分量利用局部区域能量加权方法融合,三个方向分量利用改进的高斯加权SML方法融合;对NSCT分解的高频分量,分为对最高层和其它层的融合,最高层利用改进的高斯加权SML方法融合,其余层利用边缘梯度信息激励PCNN方法融合。最后对NSCT进行逆变换得到融合图像。实验结果证实了所提算法的有效性。
Aiming at the shortcomings of the traditional NSCT image fusion algorithm,we propose an image fusion algorithm based on complementary wavelet transform and PCNN in NSCT domain.Firstly,we use the NSCT to decompose the source image and generate a series of low frequency and high frequency sub-bands.Low frequency sub-bands are decomposed by two-dimensional wavelet into a low frequency sub-band and three directional sub-bands.Then the low frequency sub-band is fused by the local region energy weighting method.And the three directional sub-bands are fused by the improved Gaussian weighted SML method.The high frequency sub-bands decomposed by the NSCT are divided into the highest layers and other layers for fusion.The highest layers are fused by using the improved Gaussian weighted SML method,and the other layers are fused by the PCNN method enhanced by edge gradient information.Finally,the fused image is obtained through NSCT inverse transform.Experimental results demonstrate the effectiveness of the proposed algorithm.
Aiming at the shortcomings of the traditional NSCT image fusion algorithm,we propose an image fusion algorithm based on complementary wavelet transform and PCNN in NSCT domain.Firstly,we use the NSCT to decompose the source image and generate a series of low frequency and high frequency sub-bands.Low frequency sub-bands are decomposed by two-dimensional wavelet into a low frequency sub-band and three directional sub-bands.Then the low frequency sub-band is fused by the local region energy weighting method.And the three directional sub-bands are fused by the improved Gaussian weighted SML method.The high frequency sub-bands decomposed by the NSCT are divided into the highest layers and other layers for fusion.The highest layers are fused by using the improved Gaussian weighted SML method,and the other layers are fused by the PCNN method enhanced by edge gradient information.Finally,the fused image is obtained through NSCT inverse transform.Experimental results demonstrate the effectiveness of the proposed algorithm.
引文
[1] Minh N D,Martin V.The finite ridgelet transform for image representation[J].IEEE Transactions on Image Processing,2003,12(1):16-28.
[2] Fu Meng-yin,Zhao Cheng.Fusion of infrared and visible images based on the second generation curvelet transform[J].Journal of Infrared and Millimeter Waves,2009,28(4):255-258.(in Chinese)
[3] Chao Rui,Zhang Ke,Li Yan-jun.An image fusion algorithm using wavelet transforms[J].Acta Electronical Sinica,2004,32(5):750-753.(in Chinese)
[4] Yang S,Wang M,Jiao L,et al.Image fusion based on a new contourlet packet[J].Information Fusion,2010,11(2):78-84.
[5] Li S,Yang B,Hu J.Performance comparison of different multi-resolution transforms for image fusion[J].Information Fusion,2011,12(2):74-84.
[6] Fu Z Z,Wang X,Xu J,et al.Infrared and visible images fusion based on RPCA and NSCT[J].Infrared Physics&Technology,2016,77:114-123.
[7] Chen Z,Zhang C X,Wang P.High-quality fusion for visible and infrared images based on the double NSCT[C]∥Proc of IEEE the 7th International Congress on Image and Signal Processing,2014:223-227.
[8] Chen Zhen,Yang Xiao-ping,Zhang Cong-xuan,et al.Infrared and visible image fusion based on the compensation mechanism in NSCT domain[J].Chinese Journal of Scientific Instrument,2016,37(4):861-870.(in Chinese)
[9] da Cunha A L,Zhou J P,Do M N.The non-subsampled contourlet transform:Theory,design,and applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101.
[10] Wang N,Ma Y,Zhan K.Spiking cortical model for multifocus image fusion[J].Neurocomputing,2014,130:44-51.
[11] Kinser J M.Pulse-coupled image fusion[J].Optical Engineering,1997,36(3):737-741.
[12] Hang W,Jing Z.Evaluation of focus measures in multi-focus image fusion[J].Pattern Recognition Letters,2007,28(4):493-500.
[2]付梦印,赵诚.基于二代Curvelet变换的红外与可见光图像融合[J].红外与毫米波学报,2009,28(4):255-258.
[3]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.
[8]陈震,杨小平,张聪炫,等.基于补偿机制的NSCT域红外与可见光图像融合[J].仪器仪表学报,2016,37(4):861-870.
[2] Fu Meng-yin,Zhao Cheng.Fusion of infrared and visible images based on the second generation curvelet transform[J].Journal of Infrared and Millimeter Waves,2009,28(4):255-258.(in Chinese)
[3] Chao Rui,Zhang Ke,Li Yan-jun.An image fusion algorithm using wavelet transforms[J].Acta Electronical Sinica,2004,32(5):750-753.(in Chinese)
[4] Yang S,Wang M,Jiao L,et al.Image fusion based on a new contourlet packet[J].Information Fusion,2010,11(2):78-84.
[5] Li S,Yang B,Hu J.Performance comparison of different multi-resolution transforms for image fusion[J].Information Fusion,2011,12(2):74-84.
[6] Fu Z Z,Wang X,Xu J,et al.Infrared and visible images fusion based on RPCA and NSCT[J].Infrared Physics&Technology,2016,77:114-123.
[7] Chen Z,Zhang C X,Wang P.High-quality fusion for visible and infrared images based on the double NSCT[C]∥Proc of IEEE the 7th International Congress on Image and Signal Processing,2014:223-227.
[8] Chen Zhen,Yang Xiao-ping,Zhang Cong-xuan,et al.Infrared and visible image fusion based on the compensation mechanism in NSCT domain[J].Chinese Journal of Scientific Instrument,2016,37(4):861-870.(in Chinese)
[9] da Cunha A L,Zhou J P,Do M N.The non-subsampled contourlet transform:Theory,design,and applications[J].IEEE Transactions on Image Processing,2006,15(10):3089-3101.
[10] Wang N,Ma Y,Zhan K.Spiking cortical model for multifocus image fusion[J].Neurocomputing,2014,130:44-51.
[11] Kinser J M.Pulse-coupled image fusion[J].Optical Engineering,1997,36(3):737-741.
[12] Hang W,Jing Z.Evaluation of focus measures in multi-focus image fusion[J].Pattern Recognition Letters,2007,28(4):493-500.
[2]付梦印,赵诚.基于二代Curvelet变换的红外与可见光图像融合[J].红外与毫米波学报,2009,28(4):255-258.
[3]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.
[8]陈震,杨小平,张聪炫,等.基于补偿机制的NSCT域红外与可见光图像融合[J].仪器仪表学报,2016,37(4):861-870.