Classification of Different Stages of Glaucoma Using Deep Learning Approaches

Shukla, Manoj Kumar (2020) Classification of Different Stages of Glaucoma Using Deep Learning Approaches. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Classification of glaucoma with high accuracy is most critical in slowing down glaucoma at an early stage. For the detection of glaucoma using fundus images, an analysis of an expert is required. The purpose of this research is to classify glaucoma in the Mild and severe category. A MESSIDOR dataset consists of 3200 fundus TIFF images were used. These images were converted in jpg before using for further analysis. In this study, six classification deep learning models were used. VGG16, VGG19, InceptionV3, InceptionResNetV2, ResNet50 and DenseNet16 9 to classify glaucoma in Mild and Severe categories. In this study accuracy of all the model are examined. From all the deep learning models used in this research, DenseNet169 was able to produce an accuracy of 85.19%. This strategy was successful in classifying the glaucoma stage using fundus images with highest accuracy achieved based on known previous researches.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	25 Jan 2021 15:16
Last Modified:	25 Jan 2021 15:16
URI:	https://norma.ncirl.ie/id/eprint/4471

Actions (login required)

View Item