In this paper, an algorithm based on finite ridgelet transform is proposed for remote sensing image fusion. This method mainly involves three steps: performing the finite radon transform(FRAT), decomposition of the coefficients on the projections of the FRAT by taking the 1-D Wavelet Packet Transform(WPT) and selection of proper fusion criterion in the ridgelet subband. The main merit of the proposed method is that the finite radon transform can map a line singularity into a point singularity and the wavelet packet transform can decompose the high frequency parts of the images which are not decomposed in discrete wavelet transform. This algorithm of fusing the images from different sensors can take advantage of the line features of the source images more effectively. The experimental results demonstrate that this algorithm performs better than classical fusion methods both in visual effect and object evaluation.
展开▼
