NORMA eResearch @NCI Library

Detection and Revelation of Multiple Ocular Diseases using Transfer Learning Techniques

Vijayaraghavan, Uppiliappan (2022) Detection and Revelation of Multiple Ocular Diseases using Transfer Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (4MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Loss of vision is one of the most vigorous defect for surviving in the modern world and leading a peaceful life. The reason causing the defect in vision is a major problem in current generation since the use of unlimited electronic smart devices and gadgets which provides the light to create damage in the vision of the eyes. The detecting ability of examining the type of eye disease impacted, needs to be treated at the very initial stage so that the loss of vision can be prevented by providing proper treatment or surgery at timely manner with stages to improve the vision. This paper provides how the multi-classification of eye diseases such as Glaucoma, Diabetes, Pathological Myopia, Cataract, Age related Macular Degeneration, Hypertension and other eye related diseases are detected with the use of deep learning algorithms. The transfer learning algorithms of types : InceptionNetV3, VGG-16, VGG-19, MobileNet, RestNet, AlexNet are trained and executed in order to get the best results in detection. The InceptionNetV3 model provides the best results in terms of accuracy with 92.1% when compared to other models under consideration. The accuracies of other respective models are stated - VGG-16: 88.3%, VGG-19: 88%, RestNet50: 86.9%, MobileNet: 90.7%, AlexNet: 86.9%. Hence the automatic detection of ocular diseases and providing what kind of classification it belongs to, is accurately recognised by InceptionNetV3.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RE Ophthalmology
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 14 Mar 2023 14:09
Last Modified: 14 Mar 2023 14:09

Actions (login required)

View Item View Item