Medical Image Fusion Algorithm Based on Bidimensional Empirical Mode Decomposition
基于二维经验模态分解的医学图像融合算法

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.