摘要
提出了一种基于小波变换的多聚焦图像融合算法(简记为WMFFA)。首先综合源图像求得参照图像,并对源图像和参照图像分别做小波变换,将其分解成低频和高频图像,然后求出源图像的每个小波系数与参照图像中对应位置上的小波系数之间的距离,按照距离特征从源图像中选取小波系数,组成融合后的小波系数并进行小波反变换,得到融合图像。对提出的融合算法性能进行了评价与分析,结果表明提出的算法对多聚焦图像融合是有效的。
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.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第24期47-50,90,共5页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60673092)
教育部科研重点项目(No.205059)
江苏省高技术研究计划项目(No.BG2005019)
关键词
图像融合小波变换多聚焦图像欧氏距离
image fusion
wavelet transform
multi-focus image
Euclidean distance
