A Super-resolution-based Approach for the Detection of Covid—19 Infection From Chest X-ray Images

X-ray is the most accessible imaging modality for detecting Covid-19 infection. However, image resolution depends on amount of radiation dose. The Lesser dosage, lower resolution, higher noise and patient safety. Detecting infection would be more precise with high-resolution chest images. current article explores an edge-preserving single-scale residual learning-based super-resolution method to enhance low-resolution We used unsharp masking preserve small, medium, high-scale details while super-resolving given image. produces a clear view pulmonary opacities in images after reconstruction. Statistical feature metrics first second-order showed superior quality reconstruction by proposed Further, measure effectiveness super-resolution, we Inception v3 based deep learning model classify Covid-19, pneumonia, normal class. performance classification super-resolved was tested against 400 belonging two different classes at time. obtained increased precision 94% 96% accuracy compared 64% 68% before super-resolution.