A new image fusion quality assessment method based on Contourlet and SSIM

As Contourlet transform can give an asymptotic representation of edges and contours in image by virtue of its characteristics of multidirectional and flexible, it is introduced into the quality assessment of fused image. A new method (CSSIM) for image fusion quality assessment based on Contourlet and structural similarity of images is put forward in this paper. We introduce distortion channel to simulate the fusion process, that is, using the process of the reference image transmitted through the distortion channel to obtained the fused image to simulate the process of the source images employed a certain fusion method and fusion rules to obtained the fused image. Through the evaluation of the structure similarity between reference image and the fused image, it will achieve the evaluation of the performance of fusion method. According to this algorithm, a set of experiments are implemented. The results illustrate that the proposed method has a good consistency with the subjective assessment of human beings, as well as comparison to the classical SSIM algorithm it has a better differentiation.