Downloads: 187
Research Paper | Computers Electrical Engineering | Volume 9 Issue 4, April 2020 | Pages: 601 - 604 | Iraq
COVID-19 Pandemic Detection in Chest X-ray Images by Deep Features with SVM Classifier
Abstract: The X-ray scanner is the first imaging technique that plays an important role in the diagnosis of coronavirus disease 2019 (COVID-19). The early recognition of COVID-19 is now a very important mission for the medical practitioner. The COVID-19 spread so quicklyamong humans and around 1, 236, 791 infected humans with more than 67, 249 death cases in the world, this number of infections is continuously increasing till the present time. In this consequence, it is a very important mission to recognize the infected humans so that can be separated to reduce the spread of COVD-19 among humans and save the people life. In this paper, we presented a method that uses deep feature extraction done by Convolutional Neural Networks (CNNs) and the classification done by Support Vector Machine (SVM) with nonlinear kernel function algorithms to recognize COVID-19 in Chest X-ray images. However, due to the limited availability of annotated medical images, the classification of medical images remains the biggest challenge in medical diagnosis. The results of the proposed method were Accuracy, Recall, False Positive Rate (FPR), and True Negative Rate (TNR), 91.53 %, 91.68 %, 91.06 %, and 8.32 % respectively. this rate of Accuracy shows the success of the proposed method and can be used in hospitals for the detection of COVID-19 in Chest X-ray images.
Keywords: Detection COVID-19 in Chest X-ray images, coronavirus disease 2019 pneumonia, COVID-19, deep feature, SVM, Chest X-ray images
How to Cite?: Bashar AL-SAFFAR, Nusaibah Khalid Abdulmajeed, "COVID-19 Pandemic Detection in Chest X-ray Images by Deep Features with SVM Classifier", Volume 9 Issue 4, April 2020, International Journal of Science and Research (IJSR), Pages: 601-604, https://www.ijsr.net/getabstract.php?paperid=SR20406025309, DOI: https://dx.doi.org/10.21275/SR20406025309