Macular Region Enhancement of Fundus Fluorescein Angiogram Images Using Super Resolution via Sparse Representation and Quality Analysis

This paper presents a novel methodology for enhancement of macular region using sparse representation of segmented macular region and super resolution of Fundus Fluorescein Angiogram (FFA) images affected by diabetic maculopathy. The proposed methodology enhances the quality of images which is a necessary step for further analysis of images. The segmented region of the macular region is used to construct a dictionary of patches. These patches can be expressed as a sparse linear combination of an over complete dictionary. The patches of the low-resolution input are taken and the coefficients of the corresponding sparse representations are used to generate the high-resolution output. It has been observed that the proposed image enhancement algorithm achieves better quality of images. The results were evaluated using statistical quality metrics and compared with various interpolation techniques like bilinear and bicubic.