Viral Pneumonia Detection from Chest X-rays using GLCM and LBP features

The early contact less detection of viral pneumonia is important as the virus have the ability to mutate and adapt frequently resulting in an epidemic situation or potential pandemic in a short time. This work unveils a technique for identifying viral pneumonia from chest X-rays. A combination of Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP) features with Support Vector Machine (SVM) classifier is used for detection. The effect of various classifiers and feature combinations on viral pneumonia detection are also assessed. From the experimental results, the combination of GLCM and LBP features along with SVM classifier gives the best result with an accuracy of 90.5% and F1 score of 0.9073 compared to stat-of-the-art.