Multi-focus image fusion algorithm based on Nonsubsampled Contourlet Transform

Abstract

A Multi-focus Image Fusion(MFIF) Algorithm based on Nonsubsampled Contourlet Transform (NSCT) is proposed in this paper, which can select the fusion low-frequency coefficients via the Regional Energy Ratio (RER) algorithms. The NSCT is a flexible multi-scale, multi-direction and shift invariant image decomposition, which is suitable for representing images bearing abundant detail and direction information, the NSCT can also avoid introducing ringing artifacts to fused images compared to ordinary method. This is employed for fusing the directional high-frequency coefficients. For the direction high-frequency coefficient, the maximum of the regional energy is used to select the better coefficient for fusion. Experimental results show that the proposed method achieves better fusion efficiency compared to fusion methods based on wavelet transform and contourlet transform respectively.