Detecting COVID-19 from Chest X-Ray Images using Different Machine Learning Algorithms

Abstract Chest X-ray image classification is one of the research directions in the field of medical image analysis and computer-aided radiology diagnosis. X-rays have emerged as one of the most common methods of identifying abnormalities of the chest particularly those caused by respiratory diseases. Computer vision solutions provide a viable way of increasing the accuracy of COVID-19 detection. In this paper, the usefulness of HOG feature extraction methods and other classifiers are evaluated to identify COVID-19 to find out the most suitable classification model of COVID-19 detection model. Some of the classifiers that are used in the evaluation are DT (Decision Tree), K-NN (K Nearest Neighbor), SVM (Support Vector Machine), NB (Naive Bayes) and TB (Tree Bagger). In the case of COVID-19 CXR images and extracted HOG features, the results have a strong suggestion towards the utilization of Tree Bagger.