摘要
多小波理论是小波理论的扩展,在图像处理方面具有单小波所不具有的优点。它能为图像提供一种比小波多分辨分析更精确的分析方法。在图像的多小波分解的不同尺度上的子图像间有自相似性,而自相似性又是分形分维的基础。于是,根据图像多小波分解的特点,提出了一种新的基于图像多小波分解的分维融合算法,将不同源图像经多小波变换分别分解成不同尺度的子图像,对高频子图像在相应的尺度上以分形分维作为权系数进行融合,对低频子图像在相应的尺度上以区域能量作为权系数进行融合,并分别采用多聚焦图像、可见光和红外图像作为源图像进行融合实验,实验结果表明该方法是可行的。
Multi-wavelet is an extension from wavelet theory,and has several particular advantages m companson with scalar wavelets on image processing.Multiwavelet analysis can offer a more precise way for image analysis than wavelet multi-resolution analysis.Because images in different levels of image multiwavelet decomposition were self-similar,which was the foundation of fractal,a new image fusion algorithm was presented based on image muhiwavelet decomposition and fractal dimension.Different source images were separately decomposed by multi-wavelet transform with different scales.Corresponding-level high frequency images were merged,with fractal dimension as weight.Corresponding-level lowest frequency images were merged,with energy as weight.An experiment was given using multi-focus images,visual light and infrared image separately as two source images.Experiment results show the algorithm is feasible.
出处
《计算机工程与应用》
CSCD
北大核心
2006年第32期83-86,共4页
Computer Engineering and Applications
基金
国家自然科学基金资助项目(60475021)
河南省杰出青年基金资助项目(0412000400)
国家教育部科研基金重点项目(03081)。
关键词
图像融合
离散多小波变换
分维
image fusion
discrete muhiwavelet transform
fractal dimension
