Open AccessGlaucoma Image Classification Using Entropy Feature and Maximum Likelihood Classifier
Author(s) -
Anisha Rebinth,
S. Mohan Kumar,
T. Kumanan,
G. Varaprasad
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1964/4/042075
Subject(s) - pattern recognition (psychology) , artificial intelligence , glaucoma , entropy (arrow of time) , principle of maximum entropy , contextual image classification , classifier (uml) , computer science , mathematics , classification scheme , machine learning , image (mathematics) , physics , medicine , ophthalmology , quantum mechanics
In general, the nerve that links the eye to the brain is affected because of high eye pressure. The most common kind of glaucoma sometimes has no other symptoms than a gradual loss of vision. In this study, the Glaucoma Image Classification (GIC) is made by using different entropy features and Maximum Likelihood Classifier (MLC). Initially, the input fundus images are decomposed by using rankles transform, then the entropy features like sample entropy, Shannon entropy and approximate entropy are used to extract features. Finally, MLC is applied for classification. The GIC scheme’s function produces the classification accuracy of 96 % by using Shannon entropy feature and MLC.