A Novel Algorithm of Image Fusion Based on Non-subsampled Shearlet-Contrast Transform

To solve the shortcomings of results based on image fusion algorithm, such as lack of contrast and details, we proposed a novel algorithm of image fusion based on non-subsampled Shearlet-contrast transform (NSSCT). Firstly, we analyze the correlation and the diversity between different coefficients of non-subsampled Shearlet transform (NSST), build the high level coefficients which are the same orientation to NSSCT. Then, fuse the high level coefficients which can reserve details and contrast of image; fuse the low level coefficients based on the characters of it. Eventually, obtain the fused image by inverse NSSCT. To verify the advantage of the proposed algorithm, we compare with several popular algorithms such as DWT, saliency map, NSST and so on, both the subjective visual and objective performance conform the superiority of the proposed algorithm.