摘要
提出一种基于小波变换的多聚焦图像融合方法.该方法首先通过小波变换得到源图像的小波系数,然后对低频和高频分量采用不同的融合规则和融合算子构造融合图像的小波系数,最后基于一致性检测由高低频融合系数得到最终的融合结果.用两组源图像数据验证所提出的融合算法,并与其他融合算法进行比较,仿真结果表明该算法在多聚焦图像融合中优于其他方法.
A multi-focus image fusion approach based on wavelet transform is presented. First, multi-scale wavelet transform is applied to obtain the wavelet coefficients of the source images. Then, applying different fusion rules and fusion operators to the corresponding low-and high frequency wavelet coefficients, the wavelet coefficients of fused image are constructed. Finally, the last fusion image is generated based on consistence measurement of its high and low frequency coefficients obtained before. Two sets of images are applied to verify the fusion approach proposed and compare it with other fusion approach. The experimental results show that the performance of the approach presented is superior to that of other approaches.
出处
《控制与决策》
EI
CSCD
北大核心
2005年第11期1256-1260,共5页
Control and Decision
基金
公安部重点基金项目(20029322301)
黑龙江省自然科学基金项目(F0318)
关键词
图像融合
小波变换
多聚焦
图像处理
Image fusion
Wavelet transform
Multi-focus
Image processing
