Multi-spectral image fusion method based on two channels non-separable wavelets  

作　　者：LIU Bin1,2 & PENG JiaXiong3 1 School of Mathematics and Computer Science, Hubei University, Wuhan 430062, China 2 Key Laboratory of Applied Mathematics of Hubei Province, Wuhan 430062, China 3 Institute of Image Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan 430074, China 

出　　处：《Science in China(Series F)》2008年第12期2022-2032,共11页中国科学（F辑英文版）

基　　金：the National Natural Science Foundation of China (Grant No. 10477007);Natural Science Foundation of Hubei Province (Grant No. 2006ABA015);the Key Project of Hubei Provincial Department of Education (Grant No. D200510004)

摘　　要：A construction method of two channels non-separable wavelets filter bank which dilation matrix is [1, 1; 1,-1] and its application in the fusion of multi-spectral image are presented. Many 4×4 filter banks are designed. The multi-spectral image fusion algorithm based on this kind of wavelet is proposed. Using this filter bank, multi-resolution wavelet decomposition of the intensity of multi-spectral image and panchromatic image is performed, and the two low-frequency components of the intensity and the panchromatic image are merged by using a tradeoff parameter. The experiment results show that this method is good in the preservation of spectral quality and high spatial resolution information. Its performance in preserving spectral quality and high spatial information is better than the fusion method based on DWFT and IHS. When the parameter t is closed to 1, the fused image can obtain rich spectral information from the original MS image. The amount of computation reduced to only half of the fusion method based on four channels wavelet transform.A construction method of two channels non-separable wavelets filter bank which dilation matrix is [1, 1; 1,-1] and its application in the fusion of multi-spectral image are presented. Many 4×4 filter banks are designed. The multi-spectral image fusion algorithm based on this kind of wavelet is proposed. Using this filter bank, multi-resolution wavelet decomposition of the intensity of multi-spectral image and panchromatic image is performed, and the two low-frequency components of the intensity and the panchromatic image are merged by using a tradeoff parameter. The experiment results show that this method is good in the preservation of spectral quality and high spatial resolution information. Its performance in preserving spectral quality and high spatial information is better than the fusion method based on DWFT and IHS. When the parameter t is closed to 1, the fused image can obtain rich spectral information from the original MS image. The amount of computation reduced to only half of the fusion method based on four channels wavelet transform.

关 键 词：image fusion non-separable wavelets multi-spectral image panchromatic image 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]