Sparse representation with morphologic regularizations for single image super-resolution

• A novel sparse representation algorithm with different morphologic regularizations for single image super-resolution is proposed.
• Various contents mixed in an image are decomposed into different morphological components.
• Different morphologic components are regularized by reasonable morphologic constraints.
• A dictionary training framework is presented to effectively learn multiple morphology dictionaries.

Due to the fact that natural images are inherently sparse in some domains, sparse representation has led to interesting results in image acquiring, representing, and compressing high-dimensional signals. Based on the experiences and learned priors in sparse domain from low and high resolution images, the typical ill-posed inverse problem of image super-resolution is effectively solved by the l1-norm optimization techniques. However, how to reasonably combine the sparse representation theory and the feature of natural images is still a critical issue for performances improvements of image super-resolution algorithms. Considering the fact that the different morphologic features in natural images should be regularized by different constrains in sparse domain, in this paper we present a novel sparse representation algorithm with reasonable morphologic regularization for single image super-resolution. Extensive experimental results on various natural images validate the superiority of the proposed algorithm in terms of qualitative and quantitative performance.