CT and MRI Image Fusion Based on Contourlet Using a Novel Rule

Contourlet can efficiently represent image and be used as image fusion method. When fusion scheme is selected, fusion performance mainly rests on fusion rules. Fusion rules based on region energy is often used in multiresolution analysis (MRA) image fusion scheme. It is more robust and less sensitive to noise. But small region window is often not the best one, and large window blurs the gap between edges and none edges. This paper proposed a novel fusion rule based on weighted region energy. Each pixel in the window has a weight in inverse proportion to the distance between it and the current fusion pixel. And this rule is applied to both lowpass and bandpass coefficients of contourlet transform. Experiments show that the new fusion scheme has better performance than the fusion methods based on traditional region.