Image fusion algorithm based on regional variance and multi-wavelet bases

Wavelet analysis is a multi-resolution method based on Fourier analysis. It has good localization characteristics both in time domain and frequency domain. This paper proposes a medical image fusion algorithm based on regional variance and multi-wavelet bases. The algorithm can fuse CT and MRI medical images. First, the two modalities of images are fused based on different wavelet bases. The low-frequency coefficients follow the fusion rule based on regional variance, and the high-frequency coefficients follow the fusion rule of taking the largest absolute value. Then some primary fused images can be obtained. The final fused images will be got after the processing of weighted average for the primary images. The simulate result shows that, the fused image based on multi-wavelet bases is better than the fused image based on single-wavelet basis.