Automated Diabetic Retinopathy Detection System

This survey paper presents a comprehensive review of existing automated techniques for the detection of Diabetic Retinopathy using retinal fundus images. The study analyzes various image processing, machine learning, and deep learning approaches used for feature extraction, lesion detection, and disease classification. Different methodologies are compared based on accuracy, sensitivity, specificity, and computational efficiency. The survey also highlights commonly used datasets, evaluation metrics, and challenges such as data imbalance, image quality variation, and early-stage detection. The findings of this survey help in identifying research gaps and provide a strong foundation for designing an efficient and reliable automated diabetic retinopathy detection system.