<p>This paper proposes a novel approach to medical image processing based on single image super resolution. This method is based on the sparse representation of fundus fluorescein angiogram (FFA) images affected with diabetic maculopathy. It is necessary to enhance the quality of these images to visualize the different leakages that characterize diabetic maculopathy for further analysis. In this method a dictionary is created from the patches that are obtained from the input FFA image. These patches can be written as a sparse linear combination of over complete dictionary. From the down sampled input signal we can recover the sparse representation. The coefficients of sparse representation of each low resolution patch can be used to generate the high-resolution output. Finally a comparison of this method with popular interpolation approaches like bilinear and bicubic was done. Experimental results prove that the sparse method gives better results when compared with other methods. © Research India Publications.</p>
cited By 0
T. Ra Swapna, Indu, Da, and Chakraborty, Cb, “Retinal image enhancement using super resolution via sparse representation and evaluation using quality metrics”, International Journal of Applied Engineering Research, vol. 10, pp. 117-122, 2015.