Classification of Chest X-ray COVID-19 Images Using the Local Binary Pattern Feature Extraction Method

Authors : Narin ASLAN, Sengul DOGAN, Gonca ÖZMEN KOCA

Pages : 299-308

Doi:10.55525/tjst.1092676

View : 17 | Download : 14

Publication Date : 2022-09-30

Article Type : Research Paper

Abstract :Background and Purpose: COVID-19, which started in December 2019, caused significant loss of life and economic losses. Early diagnosis of the COVID-19 is important to reduce the risk of death. Therefore, studies have increased to detect COVID-19 with machine learning methods automatically. Materials and Methods: In this study, the dataset consists of 15153 X-ray images for 4961 patient cases in three classes: Viral Pneumonia, Normal and COVID-19. Firstly, the dataset was preprocessed. And then, the dataset was given to the Cubic Support Vector Machine insert ignore into journalissuearticles values(Cubic SVM);, Linear Discriminant insert ignore into journalissuearticles values(LD);, Quadratic Discriminant insert ignore into journalissuearticles values(QD);, Ensemble, Kernel Naive Bayes insert ignore into journalissuearticles values(KNB);, K-Nearest Neighbor Weighted insert ignore into journalissuearticles values(KNN Weighted); classification methods as input data. Then, the Local Binary Model insert ignore into journalissuearticles values(LBP); texture operator was applied for feature extraction. Results: These values were increased from 94.1% insert ignore into journalissuearticles values(without LBP); to 98.05% using the LBP method. The Cubic SVM method`s highest accuracy was observed in these two applications. Conclusions: This study demonstrates that the performance of the presented methods with LBP feature extraction is improved.
Keywords : Covid 19, local binary pattern, feature extraction, machine learning, classification, Covid 19