Region-based multifocus image fusion based on Hough transform and wavelet domain hidden Markov models

The objective of image fusion is to combine information from multiple images of the some scene. The fusion image is a single image, which is more suitable for human and machine perception or further image processing tasks. In this paper, we propose a novel region-based framework based on wavelet domain hidden Markov models (WD-HMM) and Hough transform (HT). Since the shift-variant of wavelets leads to artifacts and blurred edges in the fused image, wavelets in our framework are only used to judge natures of the source images. Besides this, the new framework also provides the fusion rules based on max-likelihood theory, which is proposed by us firstly and allows fusion on a systematic statistical theory. The region-based fusion is achieved through HT. Finally, our scheme is applied to merging two images in which have two clocks with different focus. The fusion results show the high ability of our scheme in preserving edge information and avoiding shift-variant.