摘要
提出了一种基于双树复小波变换的图像融合方法。采用双树复小波变换对源图像进行分解后,该方法首先对各频域分别定义一种活性测度和匹配测度,再通过相应的匹配测度来计算各频域的融合因子,然后采用加权与选择相结合的规则融合高频系数和低频系数,得到融合图像的各频域系数。最后,采用双树复小波逆变换重构得到融合图像。实验表明,该融合方法具有良好的客观评价性能和主观视觉效果。
An image fusion method based on dual-tree complex wavelet transform is proposed in this paper.After source images decomposed through dual-tree complex wavelet transform,the activity measure and the match measure for each frequency field are defined respectively.The high frequency coefficients and the low frequency coefficients are fused by means of the combination of weighting and selection through fusion genes for each frequency field whieh are computed by corresponding match measure.Finally,the fused image is obtained through inverse dual-tree complex wavelet transform reconstruction.Experiments results indicate this fusion method possesses favorable objective evaluation performance and subjective vision effect.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第24期184-187,共4页
Computer Engineering and Applications
基金
国家自然科学基金重大项目No.79816101
湖南省自然科学基金No.05JJ30121~~
关键词
图像融合
双树复小波变换
活性测度
匹配测度
image fusion
dual-tree complex wavelet transform
activity measure
match measure