Pixel level multifocus image fusion based on variational decomposition

An image fusion Algorithm based on variational decomposition and energy of edge is presented in this paper. Firstly, each source image is decomposed into a geometrical component and a textured component by applying Rudin-Osher-Fatemi (ROF) model in combination with Chambolle´s projection algorithm. Secondly, the corresponding components are fused separately. For fusing the geometrical components, a weighted average method is adopted. To construct the textured component, an indirect smoothing method is firstly applied to the composed textured component of each source image, and then a selection mode is used according to the local Energy of Laplacian measure. Finally, the sum of the fused components is calculated to obtain the fused resultant. Experiments show that the proposed algorithm works well in multi focus image fusion.