An Optimal Color Image Fusion Approach Based on Quantitative Evaluation Indexes

The fusion technology of multi-sources images is important for spatial information applications, such as digital city. In order to keep the spectral information and spatial information in the process of multi-sources spatial images fusion, an optimal image fusion method based on quantitative evaluation indexes is proposed in this paper. In IHS (intensity, hue and saturation) transform space, the feature image of high frequency of intensity component I is fused with multi-resolution wavelet. And the low frequency of intensity component I is fused on pixel level with optimal weight coefficients. Spectral information index E_SP and spatial resolution index AG are used to adjust the fusion rule and achieve the optimum weight. The test results with QuickBird data show the effectiveness of presented method