Early Glaucoma Detection Using Machine Learning Algorithms of VGG-16 and Resnet-50
Parag Jibhakate, Shreshtha Gole, Prachi Yeskar, Neeraj Rangwani, Aishwarya Vyas, Kanchan Dhote
Abstract
The early detection of glaucoma is discussed in this paper. A comparison of two different transfer learning algorithms is carried out. The morphological markers of glaucoma, which predict the start of abnormalities, were quantified using machine learning algorithms. Glaucoma screening is an expensive, time-consuming, and human-error-prone technique. In developing and poor areas, there are fewer eye experts. This project will save time, money, and resources by making glaucoma screening more accessible to the general public. Because glaucoma is the leading cause of blindness in the United States, it is critical to diagnose it early. With this initiative, we hope to make a difference in society.