Open AccessAutomated Vision Defect Detection Supported Deep Convolutional Neural Networks
Author(s) -
S. Lalitha,
N. Shanthi,
S. Gopinath
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 - 10.1088/1742-6596/1964/4/042044
Subject(s) - convolutional neural network , computer science , artificial intelligence , deep learning , pattern recognition (psychology) , deep neural networks , computer vision , optometry , medicine
They should more truly detect abnormalities in the refractive error, used to prevent the children of amblyopia, which can lead to permanent visual impairment, but at first it was detected. A variety of tools have been adopted to protect the area of amblyopia more easily. Amblyopia is a lifetime serious eye disease. Amblyopia contributes to forecasting and treatment and rapid public treatment. They are also useful for completely automatic detection of amblyopia deep neural networks. A tele amblyopia dataset is used for detection. Then proposed deep convolutional neural networks are used for automated amblyopia detection on tele amblyopia dataset. The proposed algorithm comprises of 2 phases. In the first phase, the Enhanced Firefly Algorithm (EFA) is used to segment the eye region. In second phase, a DCNN is designed and trained to classify the segmented eye areas as amblyopia or normal. The test comes about appear that the proposed strategy can work well with the programmed discovery of amblyopia.