关键词: 图像融合, 小波变换, 多聚焦图像, 欧氏距离

Abstract: In this paper，a new multi-focus image fusion algorithm based on wavelet transform（WMFFA） is proposed.Firstly，a reference image is acquired by synthesizing the source images，and then the wavelet transform is applied to each source image and reference image to get a series of low-frequency images and high-frequency images.Secondly，calculates the wavelet coefficient distance between source images and reference image.Thirdly，applying the distance feature selection rules to select wavelet coefficients which will be viewed as the wavelet coefficients of fused image from the source images.Finally，the fused image is obtained by applying inverse wavelet transform to the selected wavelet coefficient.We also give the experiment results which demonstrate that the fusion algorithm is effective for multi-focus image fusion.

Key words: image fusion, wavelet transform, multi-focus image, Euclidean distance