Example-based super-resolution for enhancing spatial resolution of medical images

This paper proposes an effective exampled-based super-resolution (SR) method to improve the spatial resolution of medical image heavily corrupted by noise. Based on the sparsity of patches, the reconstruction of a high-resolution (HR) patch from each low-resolution (LR) input patch can be performed with the help of a database, by solving a non-negative sparse optimization problem. The challenge is to effectively solve this problem in case of a large size database. To cope with this issue, we propose a metric to measure the similarity between image patches based on the Earth Mover's Distance (EMD) in order to select only the most similar candidates that will be used in the optimization problem. Experimental results demonstrate the efficiency of our algorithm over many existing SR methods, especially in case of noise-corrupted LR image.