基于二维经验模态分解的医学图像融合算法

Medical Image Fusion Algorithm Based on Bidimensional Empirical Mode Decomposition

提出了一种自适应的二维经验模态分解(bidimensional empirical mode decomposition,简称BEMD)医学图像融合算法.待融合的医学图像经过BEMD分解成二维的内蕴模函数(bidimensional intrinsic mode function,简称BIMF)和趋势图像.BIMF图像经过Hilbert-Huang变换提取图像特征,然后,图像分解的各部分数据在区域融合规则下形成综合BEMD表示.最后,综合BEMD表示进行BEMD逆变换得到融合后的医学图像.BEMD分解方法是一种完全自适应的数据分解表达形式,具有比Fourier变化和小波分解更好的特性.该医学图像融合算法不需要预先定义滤波器或小波函数.实验结果表明,该算法与传统融合算法相比性能优越,能够大幅度提高融合图像的质量。

An adaptive medical image fusion algorithm based on the representation of bidimensional empirical mode decomposition （BEMD） is proposed. Source medical images are decomposed into a number of bidimensional intrinsic mode functions （BIMF） as well as a residual image. Image features are extracted through Hilbert-Huang transform on the BIMF. Then the composite BEMD is formed by region-based fusion rules on data representations of BEMD. Finally, the fused image is obtained by inverse BEMD on the composite representation. The BEMD is an adaptive data decomposition representation, and has better performance than Fourier and wavelet transform. The proposed algorithm does not need predetermined filters or wavelet functions. Experimental results show that the proposed algorithm provides superior performance over conventional fusion algorithms in improving the quality of fused images.