A Remote Sensing Images Fusion Based on the NLEMD and Local Contrast

A remote sensing images fusion algorithm based on the NLEMD (NLEMD, neighborhood limited empirical mode decomposition) and local contrast is presented in this paper. At first the original image is performed a multi-resolution decomposition by using NLEMD. Then a fusing algorithm is presented according to the truth that the human visual system is sensitive to the local contrast. During NLEMD, the local average stationarity is used to get the optimal local average of image, which is avoided extracting the extrema of image in the traditional EMD. The experiment results show that our algorithm can reflect more complex textures than the DWT method could. This algorithm can get better fused image.