Projects

Retinal Image Enhancement using Super Resolution via Sparse Representation and Quality Analysis

This work presents a novel approach to medical image processing that is single image super resolution, based on sparse signal representation in fundus angiogram images for enhancing the quality which is affected by diabetes. Image enhancement is used to improve the quality of images for further analysis. Here we are applying super resolution technique for enhancement based on Sparsity. The dictionary is created from the patches that are obtained from the input image. This patch can be written as the sparse linear combination of over complete dictionary. From the down sampled input signal we can recover the sparse representation. For each patch of the low-resolution input, we can use the coefficients of this representation to generate the high-resolution output. This image enhancement algorithm achieves better visual effects from the input image. Finally the quality analysis was done it shows that sparse method is giving more enhanced outputs compared to other methods.