Block medical image fusion based on adaptive PCNN

Abstract

We proposed an effective block medical image fusion method based on adaptive pulse coupled neural networks (PCNN) in this paper. Source images are divided into several blocks, and then we calculate the spatial frequency (SF) of the blocks as linking strength β of the PCNN, so it adjusts β of the PCNN adaptively. The block images are input into PCNN to get the oscillation frequency graph (OFG), which expresses the quality of the block images, so we can fuse the clear part of the source images. The experimental results show that the block medical image fusion algorithm is more efficient than other common image fusion algorithms, and prove the adaptive PCNN method is effectively as well.