Multi-focus Image Fusion by SML in the Shearlet Subbands

Abstract

It is now widely acknowledged that traditional wavelets are not very effective in dealing with multidimensional signals containing distributed discontinuities. Shearlet Transform is a new discrete multiscale directional representation, which combines the power of multiscale methods with a unique ability to capture the geometry of multidimensional data and is optimally efficient in representing images containing edges. In this work, coefficients with greater Sum-Modified-Laplacian are selected to combine images when high-frequency and low-frequency Shearlet subbands of source images are compared. Numerical experiments demonstrate that the method base on Shearlet Transform and Sum-Modified-Laplacian is very competitive and better than other multi-scale geometric analysis tools in multifocus image fusion both in terms of objectives performance and objective criteria.

DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3365