Image super-resolution via multistage sparse coding

Abstract

To reduce the reconstruction error in dictionary training and reconstruction, an image super-resolution algorithm via multistage sparse coding (SMSC) is proposed in this paper. The combined Lanczos3 and IBP algorithm is used as the first method to estimate the high resolution image. In dictionary training, the feature and reconstruction error of estimated images are used to train multistage feature dictionaries and error dictionaries. In reconstruction, using feature dictionaries and error dictionaries, the error term of the estimated image is reconstructed by sparse coding to improve the image quality stage by stage. The experiment shows that, the proposed algorithm outperforms other the-state-of-art SR algorithm SISR in image quality, while the reconstruction time remains in low level.