In the image fusion process,the sparse representation has block processing to break the continuity of the image,result ing in serious loss of clear measurement information of the multi-focus fused i mage.To solve this problem,a multi-focus image fusion algorithm based on convol ution sparse representation and neighborhood features is proposed.This algorithm deco mposes the low-frequency subgraphs of the non-down sampling contourlet transform (NSCT) d omain into the base layer and the detail layer by Gaussian filtering, and then uses the alternating direction multiplier algorithm (ADMM) to solve the sparse coefficients to complete the fusion of feature response coefficients of the detail layer.At the same time,a reasonable neighborhood feature is designed based on the focus degree measureme nt function to complete the fusion of high-frequency subgraphs in the NSCT domain.The experimental res ults show that the edge information transfer factor (QAB/F) of this algori thm is only slightly lower than that of the comparison algorithm,but the spatial frequency (SF),aver age gradient (AG),sharpness (SP) and visual information fidelity (VIFF) increase by about 16.31%,41. 87%,19.2%,and 12.07%,respectively, compared with the comparison algorithm.The proposed algorithm effectively extrac ts the deeper clear measurement information of the source image,also overcomes the bloc kiness defect of sparse representation,and has better fusion performance.