Multi-focus image fusion method based on Linked twist map (LTM) in shearlet domain

Multi-focus image fusion is the process of producing a single image by combining multiple images taken with different focal distances, the entire view is focused in the resultant image. The fused image has larger depth of field than each of the input images. In this paper, we present a new technique for multi-focus image fusion via Linked twist maps (LTM) from a blinking flow model on shearlet domain. The proposed method first transforms the source image into shearlet-image by using shearlet transform (ST), and then, we have used Linked twist maps (LTM) from a blinking flow model for focus detection in which all the pixels in smooth parts are estimated differently according to their arrangement. We have used five sets of test images for our experiment and the experimental results are superior in terms of mutual information and edge indexing compared to the other related research works.