Image Fusion Method Based on Entropy Rate Segmentation and Multi-Scale Decomposition

In order to improve the correlation of the fusion coefficients in multi-focus image fusion technology and enhance regional information abundance, we propose a method based on the entropy rate segmentation and multi-scale decomposition on multi-focus image fusion. After multi-scale decomposition, the edge and detail information are stored in the high frequency subband. We can better preserve the details of the image through model value and comparison consistency check. At the same time, the similar information coefficients of image are assigned to the same area, combined with low frequency subband and entropy rate segmentation. Then the image is fused according to the regional spatial frequency and energy, the correlation of the coefficients is improved, and the fusion image edge transition is more natural. Finally, the inverse transformation is carried out on the images to get the fusion results. Experimental results show that the proposed method has better performance in both subjective and objective evaluation, and achieves better fusion effect with high applicability.