基于小波变换与块分割的多聚焦图像融合

Multi-focus image fusion based on wavelet transform and block segment

提出了1种新的多聚焦图像融合方法.首先,对2幅源图像采用小波变换的方法进行图像融合,得到初始的融合图像;其次,针对多聚焦图像的特点,采用块区域局部小波空间频率将图像划分为3部分:聚焦清晰区域、聚焦模糊区域以及两者的交界区域.对于聚焦清晰和模糊区域,直接选取清晰区域作为融合后的相应块区域;对于边界区域,则选取小波融合的图像块区域.实验对比结果表明,该方法的融合效果明显优于常见的融合方法,并消除了块效应.

A new method of multi-focus image fusion is proposed. Firstly, by using wavelet transform method, two source images are fused to get the primary fusion image. Then, with regard to characteristics of multi-focus images, the measurement between clear and blurring one is based on the wavelet space frequency of image block. As to the clear and blurring one, the former is selected as the corresponding block of fusion image, while the part between clear part and blurring one is fused by the choice of the image using wavelet transform. The experiments show that the proposed method outperforms the common methods, and eliminates block effects.