Local energy based Multi-focus image fusion method on curvelet transforms

TLDR: Wang et al. as mentioned in this paper proposed a new multi-focus image fusion method based on curvelet transform, which can get better performance compared with wavelet transform method, compared with the numerical experiment results and visual effects show that the method performs well.

Abstract: Because of the limited depth-of-focus in optical lenses, it is usually difficult to get an image that contains all information of the objects clearly. So, Multi-focus image fusion method can be proposed. This paper introduces a new multi-focus image fusion method, which is based on curvelet transform. After analyzing the classical multi-focus image fusion method, we use the maximum local energy method to calculate the energy of two images. Firstly, we got the coefficients of two different source focus images by curvelet transform; Secondly, we select the low-frequency coefficients by local energy, and through a sliding window, obtained output the Maximum energy pixel information. Then, the high-frequency coefficients are gotten by absolute maximum method; Finally, the fused image was obtained by performing an inverse curvelet transform. The numerical experiment results and visual effects show that the method performs well. Compared with wavelet transform method, this method can get better performance.