COVID DETECTION USING DEEP LEARNING TECHNIQUES

The new coronavirus (COVID-19), declared by the World Health Organization as a pandemic, hasinfected more than 1 million people and killed more than 50 thousand. An infection causedbyCOVID-19 can develop into pneumonia, which can be detected by a chest X-ray examand shouldbetreatedappropriately. In this work, we propose an automatic detection method for COVID-19 infectionbasedonchest X-ray images. The datasets constructed for this study are composed of 194 X-ray images of patientsdiagnosed with coronavirus and 194 X-ray images of healthy patients. Since fewimages of patientswithCOVID-19 are publicly available, we apply the concept of transfer learning for this task.Thetransferlearning method is used in the feature extraction step for the COVID-19 detection. Earlydetectionofpatients with the new coronavirus is crucial for choosing the right treatment and for preventingthequick spread of the disease. We use different architectures of convolutional neural networks (CNNs) trained on ImageNet, andadaptthem to behave as feature extractors for the X-ray images. Then the transferlearning is appliedwiththehelp of famous CNN image classifiers likeVGG16,Xception,Inception -V3,Resnet-50. The project file size is greater than upload limit of github so i have uploaded on the anonfiles https://anonfiles.com/q1W80d34y8/courseproject_rar