Multi-focus Image Fusion Algorithm Based on Non-subsampled Shearlet Transform and Focus Measure

摘要

A novel multi-focus image fusion algorithm is proposed in the Sheartlet domain. The core idea of this paper is to utilize the focus measure to detect the focused region from the multi-focus images. The proposed algorithm can be divided into three procedures: image decomposition, subbands coefficients selection and image reconstruction. At first, the multi-focus images are decomposed by non-subsampled Sheartlet transform (NSST), and the low frequency subbands and high frequency subbands can be obtained. For the low frequency subbands, saliency detection and improved sum-modified-Laplacian are combined to detect the focused regions. A modified edge measure algorithm is utilized to guide the coefficients combination for high frequency subbands at different levels. Moreover, in order to avoid the erroneous results introduced by the above procedures, mathematical morphology technique is used to revise the decision maps of the low frequency subbands and high frequency subbands. The final fused image can be obtained by taken the inverse NSST. The performance of the proposed method is tested on series of multi-focus images extensively. Experimental results indicate that the proposed method outperformed some state-of-the-art fusion methods, in terms of both subjective observation and objective evaluations.