Multi-Spectral and Panchromatic Image Fusion Based on Region Correlation Coefficient in Nonsubsampled Contourlet Transform Domain
Genetic and Evolutionary Computing, International Conference on (2010)
Dec. 13, 2010 to Dec. 15, 2010
Several widely used fusion methods may not be satisfactory to merge a high-resolution panchromatic image and low-resolution multi-spectral images because they can distort the spectral characteristics of the multi-spectral image or worsen the spatial resolution of the panchromatic image. In this paper, a fusion algorithm for multi-spectral and panchromatic images based on region correlation coefficient and the Nonsubsampled Contour let Transform (NSCT) is proposed. According to the fusion idea of region division, the measurement named Region Correlation Coefficient (RCC) is presented to divide the multi-spectral image into the areas need to be spatially enhanced and need to preserve spectral characteristics. Then the NSCT is performed on the panchromatic image and the intensity component of the multi-spectral image at different scales and directions. The low-frequency subband coefficients and the high-frequency directional subband coefficients are fused with the different fusion strategy. Experimental results show that the algorithm proposed performs significantly better than the IHS transform, the redundant wavelet transform and the pixel-based NSCT.
image fusion, nonsubsampled contourlet transform, IHS transform, region correlation coefficient
X. Liu, Z. Zhang, C. Ye and P. Wang, "Multi-Spectral and Panchromatic Image Fusion Based on Region Correlation Coefficient in Nonsubsampled Contourlet Transform Domain," Genetic and Evolutionary Computing, International Conference on(ICGEC), Shenzhen, China, 2010, pp. 517-521.