基于证据理论的小波域多特征医学图像融合

摘要

To address the uncertainty of weights selection in multi-source medical image fusion process, the basic probability assignment function of the evidence was used to express decision result's uncertainty based on Dempster-Shafer (DS) evidential theory. Three features of the detected image, which are regional variance, regional energy, and regional information entropy, were used and normalized, then the basic probability assignment could be got according to the features. Image fusion rules with multi-feature based on DS evidence theory were used for high frequency components in wavelet domain. Adaptive fusion rules of Energy of Laplacian { EOL) were used for low frequency component in wavelet domain according to EOL. The experimental results show that the proposed algorithm is superior to other fusion algorithms. It combines the advantages of multi-feature, reduces the uncertainty during the image fusion process and retains the details of the image in large extent.%针对多源医学图像融合过程中融合权值选择的不确定性,根据DS证据理论,采用证据理论中的基本概率分配函数来描述判决结果的不确定性.利用图像的区域方差、区域能量、区域信息熵三个特征,然后对特征进行归一化,将各个特征值作为基本概率分配的依据,在小波域内对高频分量采用基于DS证据理论的多特征融合规则进行图像融合.利用拉普拉斯能量,在小波域内对低频分量采用拉普拉斯能量自适应融合规则.实验结果表示:所提算法综合了多个特征的优势,降低了融合过程中的不确定性,较大程度地保留了图像信息.