Single Image Super-Resolution Based on Incoherent Dictionary Learning

Abstract

For image super-resolution problem, single image Super-Resolution algorithm based on incoherent dictionary learning is proposed. Firstly, a set of many samples is obtained by pre-processing applied on the given high-resolution images. Then incoherent dictionary learning technology is proposed, by which low-resolution dictionary and high-resolution dictionary are learned by incoherent dictionary learning technology. Finally, sparse representation problem is solved to obtain sparse coefficients and high resolution Image is recovered by these coefficients. Compared with state-of-the-art methods, for using incoherent dictionary learning technology, the learned redundant dictionary is more expressive to capture the details of image, and the super-resolution performance of the proposed algorithm is improved. Our experimental results validate the effectiveness of the proposed algorithm.