A novel image fusion scheme by integrating local image structure and directive contrast

In multi-resolution analysis of images, the total structures are characterized by the approximate component, and the specific features such as lines, edges and contours are contained in the detail components. This paper proposes a fusion scheme to combine the structure information which represents the background of the source images and the directive contrast information which contains the features of lines, edges and contours along different directions in the source images into a single image. Here, the structure information can be attained by similar structures index. And the contrast information is defined as the ratio of the local maxima of the detail components in a Gaussian window and the mean of the corresponding approximate components. The visual and statistical results show that the proposed method has improved the fusion performance compared to the existing fusion schemes, especially in term of the visual effects.