IMAGE FUSION BASED ON NONSUBSAMPLED CONTOURLET TRANSFORM

Image fusion is the process of generating a single combined image, which contains a more accurate description of the scene than the multiple images from different sources. Many approaches have been developed for the combination of complementary information coming from input images in order to create a new image where the informative content is more suitable for human visual or machine perception. Nonsubsampled Contourlet Transform (NSCT) can realize a flexible multiscale, multidirection, and shift-invariant image decomposition. As a result, when NSCT is introduced to image fusion, more information and better characteristics from the original images for fusion could be obtained. In this paper, NSCT is proposed when different registered source images are decomposed. Then with two distinct modes of fusion method in low-frequency and in high-frequency separately, the fused image will be obtained by inverse NSCT. Compared with the fusion method based on wavelet and other fusion methods, the experiments show that this approach can achieve better results than them.