Classification of COVID-19 using feature extraction GLCM and SVM algorithm

Abstract

Coronavirus Disease (COVID-19) is a new variant of the corona virus that mutates and spreads rapidly between humans. The high rate of transmission and spread is not matched by the fast process of diagnosis because it has to go through a polymerase chain reaction (PCR) test in the laboratory.To identify quickly, efficiently and effectively, then a classification system is used using x-ray images of the chest using the Gray Level Co-occurrence Matrix (GLCM) method and the Support Vector Machine (SVM) algorithm. The data used are digital images of normal chest X-Ray (CXR) diagnosis and positive diagnosis of Covid-19 with 408 training data and 128 test data. The test is carried out on the GLCM parameters, namely with a distance of d = 1,2,3 and angles , , , and feature extraction with contrast, correlation, energy, homogeneity, and dissimilarity.The test results show that the highest accuracy is at the distance d = 1 and the angle ?= is 90.47% and the lowest accuracy is at the distance d = 3 and the angle ? = is 80.35%.