Multi-Focus Image Fusion Based on Non-Subsampled Shearlet Transform and Consistency Optimization

Abstract

Aiming at the problems of information richness and insufficient edge definition of multi-focus fusion images, this paper proposes a multi-focus image fusion algorithm based on non-subsampled shear wave transform (NSST) and consistent optimization strategy. Firstly, the source image is decomposed by NSST transform in multi-scale and multi-direction to obtain high and low frequency subband coefficients. Secondly, Locally improved Laplacian energy and spatial consistency optimization strategy are used for low-frequency subband coefficients to construct low-frequency subband coefficient fusion weights; for high-frequency subband coefficients, spatial frequency and energy based on correlation coefficients are used, and phase consistency optimization is used. The strategy is to construct high-frequency sub-band coefficient fusion weights; finally, the final fusion image is obtained through NSST inverse transformation. The experimental results show that the proposed algorithm can improve the information retention and visual clarity of the fused image, whether in subjective vision or in objective evaluation.