Abstract

Abstract: A major cause of human vision loss worldwide is Diabetic Retinopathy (DR). The disease requires early screening forslowing down the progress. However, in low-resource settings where few ophthalmologists are available to care for all patients withdiabetes, the clinical diagnosis of DR will be a considerable challenge. The recent studies on the detection of DR by using one of theefficient algorithms of deep learning, which is Convolutional Neural Networks (CNN), which highly used to detect DR features fromretinal images. CNNs approach to DR detection saves time and expense, and is more efficient and accurate than manual diagnostics.Therefore, CNN is essential and beneficial for DR detection. The suggested approach employs the CNN machine learning techniqueto diagnose diabetic eye illness by analyzing thermal pictures. These photos are pre-processed by transforming them from RGB toGRAY, which is then used to extract the relevant characteristics. The Convolutional Neural Network is used to identify 5 stages ofdiabetic retinopathy in order to detect it.Keywords: Diabetic retinopathy; retinal images; detection; convolutional neural networks, image processing