The invention provides a multi-focus image fusion method based on sparse decomposition and a differential image. The multi-focus image fusion method is characterized by comprising the steps of utilizing RPCA to decompose an original image to obtain its sparse component and low-rank component, enhancing an edge of the sparse component through guide filtration, adding the enhanced sparse component to the low-rank component to construct an enhanced image comprising a strong edge, performing differential processing on the enhanced image and the original image, calculating spatial frequency of an obtained differential image, utilizing a self-adaptive threshold algorithm to obtain a spatial frequency diagram of the differential image, utilizing a morphological algorithm to remove a pseudo-focus region in the spatial frequency diagram to obtain a fusion decision-making diagram, and reconstructing a fusion image according to the fusion decision-making diagram and a fusion rule. Three index of the multi-focus image fusion method in evaluating an image fusion algorithm, namely a correlation coefficient, edge gradient information and an edge correlation factor are higher than that of other classical algorithms by more than 45%, 6% and 15% respectively.