Image Fusion Algorithm Based on the Second Generation Bandelet

There are more and more images, with the characters of multi-sensory, multi-temporal, multi-resolution and Multi-Band. In the same area these images are fused to be complementary. The Second Generation Bandelet transform can take advantage of the geometrical regularity of image structure and represent sharp image transitions such as edges efficiently in image fusion. Based on this advantage, an algorithm based on the second generation Bandelet transformation was proposed. The average and the maximum rule is used to select source images´ geometric flow and Bandelet coefficients. Experimental shows that result of the method is superior to that of the wavelet-based and Laplacian pyramid methods.