Abstract: In order to avoid the local unclear image details of the multi-focus image fusion method, a novel multi-focus image fusion algorithm is proposed, which combines the non-subsampled shearlet transform (NSST) with the simple linear iterative method (SLIC)that belongs to super pixels segmentation method.The main idea of this algorithm is to use NSST decomposition to get the multi-scale and multi-direction image of the source image, then the high frequency and low frequency coefficients are fused by the SLIC segmentation method and the regional gradient.Super pixel can preserve the local details of the image and can effectively maintain the target edge information, the SLIC application in the high frequency coefficient of fusion can enhance the resolution of the image.Experimental results demonstrate that the fused image based on the proposed technique has much clearer visual performance, more reasonable objective metric results.