Paper Contents
Abstract
Preventing vision loss requires the early detection of eye conditions such macular degeneration, glaucoma, and diabetic retinopathy. This article aims to investigate the role of machine learning (ML) and artificial intelligence (AI) in automating the detection of various disorders using color fundus photography (CFP). Examining the different machine learning (ML) approaches for efficient classification and prediction of eye disorders, such as support vector machines (SVM), K-nearest neighbor (KNN), logistic regression (LR), and artificial neural networks (ANN), is the goal. We also look into sophisticated image processing techniques like Bag of Visual Words (BoVW) and Speeded up Robust Features (SURF) and feature extraction methods like Principal Component Analysis (PCA) in order to increase accuracy. Despite encouraging results, issues like processing vast amounts of data, generalizing the model, and integrating it into clinical practice still exist. Future work should concentrate on integrating multi-modal data, strengthening interpretability, and strengthening model resilience. Technological developments in deep learning and hybrid models will improve automated systems; diagnostic capabilities even further, leading to better patient outcomes and early diagnosis.
Copyright
Copyright © 2024 Krishnaveni Kondagadupula. This is an open access article distributed under the Creative Commons Attribution License.
