Medical Image Fusion with Adaptive Local Geometrical Structure and Wavelet Transform

Abstract

This paper presents a novel medical image fusion method based on an adaptive local geometrical structure within wavelet framework. The local image structure is described by the eigenvalues and eigenvectors of structure tensor of every image. The fused high frequency wavelet coefficients are composed by an adaptive weighted sum of that of two source images. Fine structures, such as edges and corners, can be preserved with this method. Experimental results on medical images show that the the performance of the new method.