Retinal image fusion based on wavelet transform

The purpose of image fusion is to combine complementary information in different images. In this paper, we develop and apply a multi-resolution method based on wavelet transform to fuse retinal images. It is different from traditional methods of fusing coefficient based on pixels, because it computes the fusion coefficient according to local regional matching degree, and it can gain better visual effect, more abundant details, more prominent fusion effect. We fuse the fluorescein angiography images with the corresponding red-free retinal images, and we evaluate the result according to information entropy. lt shows the effectiveness superiority of the proposed method to other methods. The method we bring forward can also be used in other medical image fusion.