Title: Classification of Eye Refractive Error using Classifier-Fusion

Issue Number: Vol. 11, No. 3
Year of Publication: 2021
Page Numbers: 46-52
Authors: Sallam Osman Fageeri, S M Emdad Hossain, Arockiasamy Soosaimanickam
Journal Name: International Journal of Digital Information and Wireless Communications (IJDIWC)
- Hong Kong


Classifying eye refractive error is always challenging due to several factors including the selection of the right classifier. Similarly, correct classification of refractive error is very much important to have the right treatment. Both doctors and patients are definitive beneficiaries in this instance. Since the right classification is very much necessary, in this paper, some machine learning techniques have been used to classify the error type using a pre-collected dataset. Different types of refractive errors are tested in the experiments including myopia, hyperopia, high-astigmatism, etc. All collected data have been divided into two (2) different data sets; one for training and another for testing. The experiment includes the pre-processing of the dataset, adding the training set, algorithm selection, testing, and interpretation. The experimental result shows that the system is able to classify any types of eye refractive error using API, in real-time without specialized support. i.e. the patients and the doctors will be able to classify without the support of an ophthalmologist.