Preprocessing, Feature Extraction, and Classification Methodologies on Diabetic Retinopathy Using Fundus Images

Significant progress has been made throughout the detection of Diabetic Retinopathy (DR) over the past few decades because of the utilization of Deep-Learning (DL) techniques. Accurate and economical identification of DR using Fundus Images (FI) is made possible by combining state-of-the-art methods for image-processing, feature-extraction, and classification algorithms. This survey aims to explore and analyze the latest developments in preprocessing, feature extraction, and classification approaches, highlighting their key ideas and contributions. Novel approaches to feature extraction, involving traditional handcrafted features and DL-based methods, are investigated to capture relevant characteristics of DR lesions effectively. Furthermore, the survey explores diverse classification algorithms, including Support-Vector-Machines (SVM), Convolutional-Neural-Networks (CNNs), and ensemble methods, which enable accurate categorization of DR severity levels. This survey provides valuable insights into the state-of-the-art methodologies for DR detection, facilitating a comprehensive understanding of the key approaches and innovations in preprocessing, feature extraction, and classification techniques.