Diabetic retinopathy (DR) is a common and serious complication of diabetes, recognized as one of the leading causes of vision impairment and blindness among diabetic individuals worldwide. Timely and accurate detection is critical for preventing irreversible vision loss and enabling early medical intervention. In this study, we present an automated image processing-based approach designed to detect early signs of diabetic retinopathy using retinal fundus images. The strategy involves preprocessing to enhance image quality, feature extraction to detect key indicators such as microaneurysms and hemorrhages, and classification to evaluate the severity of the disease. Experimental results proved that the proposed approach achieves high performance, making it suitable for large-scale diabetic screening programs. This approach can significantly support ophthalmologists by reducing diagnostic workload and improving consistency in identifying early stages of diabetic retinopathy. Furthermore, the proposed method aligns with the United Nations Sustainable Development Goals by promoting good health and well-being through accessible and scalable early-diagnosis healthcare solutions.
 

Diabetic retinopathy, Image processing, Fundus Images, Feature extraction, Automated detection systems