Curvelet变换在多聚焦岩心图像融合中的应用  

Application of Curvelet transform in multi-focus core image fusion

作　　者：毕春艳[1] 吴晓红[1] 王正勇[1] 何小海[1] 程潇[1] 

机构地区：[1]四川大学电子信息学院图像信息研究所,成都610064

出　　处：《计算机工程与应用》2009年第16期246-248,共3页Computer Engineering and Applications

基　　金：四川省科技攻关项目(No.05GG021-026-03)~~

摘　　要：利用基于光流的运动估计对岩心图像配准后,针对岩心高低不平图像出现部分模糊现象,提出了一种基于Curvelet变换的多聚焦图像融合方法,先对不同聚焦图像进行Curvelet变换,采取低频分量取加权平均、高频分量取绝对值最大的融合规则,再进行Curvelet反变换。实验表明,基于Curvelet变换的融合方法可有效综合多聚焦图像,相比基于小波变换的图像融合,能获得更好的融合效果。After using the motion estimation based on optical flow to make the core image registration,and because of the fuzzy part of rugged core image,a new multi-focus image fusion method based on Curvelet transform is proposed.First,two different focus images are decomposed using Curvelet transform separately,then the new Curvelet coefficients are acquired by adopting a simple fusion rule, i.e.low -frequency coefficients uses the weighted average and high-frequency coefficients uses the largest absolute value.Finally,the fused image is obtained by performing an inverse Curvelet transform.Thus the experiment demonstrates that the fusion method based on Curvelet transform can effectively integrate the multi-focus images.Compared with wavelet transform method,the proposed method can get better fusion effect.

关 键 词：图像配准 CURVELET变换 图像融合 多聚焦图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]