Detection of exudates in the color retinal images based on morphological techniques

Diabetic Retinopathy (DR) is one of the complications resulted from prolonged diabetic conditions usually affected after ten to fifteen years of having diabetes. It causes damage to the tiny blood vessels inside the retina. This blood vessel will leak blood and fluid on the retina, forming lesions such as micro aneurysms, hemorrhages, exudates. This research work focuses one of the causes of diabetic retinopathy called exudates. Exudates look like tiny yellow patches on the retina. Various existing research works to detect the exudates are surveyed in this thesis and an automatic system is proposed to detect the exudates on the retinal image. This project is discussed about the morphological operations such as Dilation, Erosion, Opening, Closing and Gradient to extract the exudates. And also done the comparison between each of these methods to identify which one is suitable for extracting the exudates from the color retinal image based on the features like entropy, kurtosis, standard deviation, and mean.