Multi-focus images may be fused to get the relevant information of a particular scene. Due to the limited depth of field of a convex lens of a camera, some objects in the image may not be focused. These images are fused to get all-in-focus image. This paper proposes an innovative way to fuse multi-focus images. The proposed algorithm calculates weights indicating the sharp regions of input images with the help of Deep Belief Network (DBN) and then fuses input images using weighted superimposition fusion rule. The proposed algorithm is analyzed and examined using various parameters like entropy, mutual information, SSIM, IQI etc. © 2018, Springer International Publishing AG.