Diabetes is causing serious problems to one’s health in which the person has high blood glucose, either because insulin production is insufficient, or due to the fact the body’s cells does not react properly to insulin or both. The diabetic maculopathy (DM) is a condition that can result from diabetic retinopathy which causes the damage to the macula, the part of the eye which provides us with our central vision. This paper presents a method to detect DM based on retinal fundus image features. During the first stage the input image is enhanced and the optic disc is masked to determine the presence of regions of foveal neighborhood. In the second stage, transforming the input image into a set of features is called feature extraction. The extracted features want to be classified as belonging to Healthy or affected images. Here we go for classification task using the Support Vector Machine (SVM) classification, the process can be termed as the training phase since we are training the image as whether it contains the maculopathy texture or not. Above techniques has been tested on retinal databases and these are compared with trained phase to categorize Healthy and DM images. This method can detect DM with a level accuracy on par with human retinal specialists.
Volume 11 | Issue 2
Pages: 88-98