Classification of COVID-19 Chest X-Ray Images Based on Speeded Up Robust Features and Clustering-Based Support Vector Machines

Abstract Due to the worldwide deficiency of medical test kits and significant time required by radiology experts identify new COVID-19, it is essential develop fast, robust, intelligent chest X-ray (CXR) image classification system. The proposed method consists two major components: feature extraction classification. Bag features algorithm creates visual vocabulary from training data categories images: Normal COVID-19 patients’ datasets. extracts salient descriptors CXR images using Speeded Up Robust Features (SURF) algorithm. Machine learning with Clustering-Based Support Vector Machines (CB-SVMs) multiclass classifier trained SURF classify categories. careful collection ground truth datasets, provided expert radiologists, has certainly influenced performance CB-SVMs preserve generalization capabilities. high accuracy 99 % demonstrates effectiveness method, where assessed on an independent sets.