Multifocus image fusion using convolutional neural network

Acquiring all-in-focus images is significant in the multi-media era. Limited by the depth-of-field of the optical lens, it is hard to acquire an image with all targets are clear. One possible solution is to merge the information of a few complementary images in the same scene. In this article, we employ a two-channel convolutional network to derive the clarity map of source images. Then, the clarity map is smoothed by using morphological filtering. Finally, the fusion image is constructed via merging the clear parts of source images. Experimental results prove that our approach has a better performance on both visual quality and quantitative evaluations than many previous fusion approaches.