Detection of COVID-19 Using Classification of an X-Ray Image Using a Local Binary Pattern and K-Nearest Neighbors

The recently identified coronavirus pneumonia, which was later given the name COVID-19, is a virus that can be fatal and has affected more than 300,000 individuals around the world. Because there is currently no antiviral therapy or vaccine that has been granted approval by the FDA to cure or prevent this sickness, an automatic method for disease identification is required because of the fast global distribution of this exceedingly contagious and lethal virus. A unique machine learning strategy for automatically detecting this ailment was discovered. Machine learning approaches should be applied in essential jobs in infectious illnesses. As a result, our major aim is to use computer vision algorithms to identify COVID-19 without the need for human interaction. This paper suggested using image processing to classify objects and make early detections using X-ray pictures. Features are extracted for this region using a variety of techniques, including (LBP), (HOG), and use K-Nearest Neighbor algorithm (KNN) for classification, with training percentages of 50%, 60%, 70%, 80%, and 90%. Experiments indicated that using the suggested approach to identify X-ray photos of corona patients, it is feasible to diagnose the disease using X-ray images by training the device on the image data set (about 2,400 photos). The results were tested on the average of the samples taken (random 2000 images) each time and the measurement of multiple training ratios (50%, 60%, 70%, 80%, and 90%). The experimental findings revealed remarkable prediction accuracy in all investigated scenarios, ranging from 85% to 99%.