Diabetic retinopathy (DR) is a leading cause of vision impairment among individuals with diabetes, making early detection and timely treatment essential. This study presents an automated approach for diagnosing diabetic retinopathy using digital image processing techniques applied to retinal fundus images. The proposed system enhances image quality through preprocessing steps such as noise reduction, contrast enhancement, and normalization. Key pathological features, including microaneurysms, hemorrhages, and exudates, are detected using segmentation and morphological operations. Feature extraction techniques are employed to quantify these abnormalities, followed by classification using machine learning algorithms to determine the severity of DR. The model is evaluated using standard retinal image datasets, demonstrating improved accuracy, sensitivity, and specificity compared to traditional manual screening methods. This approach reduces dependency on expert ophthalmologists and enables scalable, cost-effective screening, particularly in resource-limited settings. The results indicate that digital image processing combined with intelligent classification can significantly enhance early diagnosis and management of diabetic retinopathy, ultimately preventing vision loss.\n\n