Fusion of Vision Transformer, Inception-V3 and ResNet50 for Efficient Eye Disease Detection
Keywords:
Inverse Weibull distribution, Moments, quantiles, Inverse Weibull-G familyAbstract
The diagnosis and categorization of retinal illnesses in the medical system is severely hampered by the increasing incidence of retinal disorders worldwide. Preventing irreversible vision loss requires prompt detection and treatment of conditions including glaucoma, DR, and macular degeneration. The use of Artificial Intelligence (AI), Machine Learning (ML) algorithms, and contemporary imaging technologies can significantly improve the accuracy and efficacy of identifying a range of ocular diseases, leading to better patient outcomes and less burden on healthcare systems. This paper presents the Vision Transfer (ViT) Algorithm, a revolutionary approach for the precise diagnosis and classification of ocular abnormalities. Our system is quite good at identifying different eye disorders using standard datasets. The ViT Algorithm performs well in distinguishing between different eye diseases by combining advanced image processing techniques with machine learning. The results show how well it improves diagnostic accuracy and enables prompt actions. This discovery greatly advances the area of eye healthcare and improves patient outcomes by offering an effective way for accurate and quick disease detection.