Detection of COVID-19 infected lungs from chest x-ray using wavelet transform, HOG features extraction and SVM

Coronavirus SARS-CoV-2 referred to as COVID-19, is a both spreadable and infectious disease, which has footprinted global pandemic still infecting millions across the globe. At present, COVID-19 made devastating impact on our daily life. To detect coronavirus, some medical radiography technique prominent such chest X-ray images. This work represented distinguishing features between normal infected images through Discrete Wavelet transform (DWT) Histogram of Oriented Gradients (HOG) methods helps indicate whether person COVID positive or negative. DWT HOG transformations were performed extract from x-ray Support Vector Machine (SVM) classifier used for model training validation. evaluate performance accuracy, sensitivity, specificity precision calculated. DWT-SVM provides accuracy 98.58%, sensitivity 98.38%, 98.47% 98.48% whereas HOG-SVM 99.39%, 99.19%, 99.28% 99.29%. So, result indicates that shows better than model. The experimental results may help personnel diagnose easily take necessary steps treatment.