Multi-modality medical images fusion based on local-features fuzzy sets and novel sum-modified-Laplacian in non-subsampled shearlet transform domain

To obtain maximum information and key features from the source images, enhance visual quality and contrast of the fused image, and decrease computational task; an improved algorithm based on local featured fuzzy sets and NSML in NSST domain is presented here. First, by taking full advantages of NSST, two registered images of the same scene are decomposed into one Low Frequency Subbands (LFS) and several High Frequency Subbands (HFS). Then, Fuzzy Pixel-based fusion rules are applied on the LFS for computing weights of every pixel in the required fused coefficient. Weights are totally based on the local energies and entropies of the LFS. Where, fused HFS coefficients are selected by computing and comparing NSML of every HFS, to extract maximum and more useful information. Finally, inversed NSST is applied to get the required fused image. Additionally, the scheme is extended to color medical image fusion that effectively restrain color distortion and enhance visual quality. To assess the performance, several experiments were conducted on different data-sets of gray-scale and color medical images. Results obtained shows that the proposed algorithm is not only superior in edge and contour detection, visual feature and in computational performance but also presents an improvement in quantitative parameters compared to other state-of-art proposed schemes.