Image super-resolution based on structural dissimilarity learning dictionary

Image super-resolution based on learning dictionary has recently attracted enormous interests in the field of image super-resolution. In the general, learning dictionary is trained from a large number of training samples. In this paper, we proposed to use the nonlocal self-similarity to filter blocks that are not similar in structure. Based on the judgment method of structural dissimilarity, we can get a small set of dissimilar training samples and then obtain a pair of high quality Structural Dissimilarity Learning Dictionary (SDLD). Extensive experiments on image super-resolution (SR) are carried out to validate the generality, effectiveness and robustness of the proposed method. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness and robustness of the proposed method. Experimental results demonstrate that our method can not only reduce the training time largely, but also achieve better results of SR.