Open AccessConvolution neural network and histogram equalization for COVID-19 diagnosis system
Author(s) -
Bashra Kadhim Oleiwi,
Layla H. Abood
Publication year - 2021
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v24.i1.pp420-427
Subject(s) - computer science , convolutional neural network , covid-19 , histogram , artificial intelligence , histogram equalization , convolution (computer science) , graphics processing unit , heuristic , artificial neural network , pattern recognition (psychology) , computer vision , data mining , image (mathematics) , medicine , disease , pathology , infectious disease (medical specialty) , operating system
The coronavirus disease-2019 (COVID-19) is spreading quickly and globally as a pandemic and is the biggest problem facing humanity nowadays. The medical resources have become insufficient in many areas. The importance of the fast diagnosis of the positive cases is increasing to prevent further spread of this pandemic. In this study, the deep learning technology for COVID-19 dataset expansion and detection model is proposed. In the first stage of proposed model, COVID-19 dataset as chest X-ray images were collected and pre-processed, followed by expanding the data using data augmentation, enhancement by image processing and histogram equalization techniuque. While in the second stage of this model, a new convolution neural network (CNN) architecture was built and trained to diagnose the COVID-19 dataset as a COVID-19 (infected) or normal (uninfected) case. Whereas, a graphical user interface (GUI) using with Tkinter was designed for the proposed COVID-19 detection model. Training simulations are carried out online on using Google colaboratory based graphics prossesing unit (GPU). The proposed model has successfully classified COVID-19 with accuracy of the training model is 93.8% for training dataset and 92.1% for validating dataset and reached to the targeted point with minimum epoch’s number to train this model with satisfying results.