COVID-19 digital x-rays forgery classification model using deep learning

Abstract

<p>Nowadays, the internet has become a typical medium for sharing digital<br />images through web applications or social media and there was a rise in<br />concerns about digital image privacy. Image editing software’s have prepared<br />it incredibly simple to make changes to an image's content without leaving<br />any visible evidence for images in general and medical images in particular.<br />In this paper, the COVID-19 digital x-rays forgery classification model<br />utilizing deep learning will be introduced. The proposed system will be able<br />to identify and classify image forgery (copy-move and splicing) manipulation.<br />Alexnet, Resnet50, and Googlenet are used in this model for feature extraction<br />and classification, respectively. Images have been tampered with in three<br />classes (COVID-19, viral pneumonia, and normal). For the classification of<br />(Forgery or no forgery), the model achieves 0.9472 in testing accuracy. For<br />the classification of (Copy-move forgery, splicing forgery, and no forgery),<br />the model achieves 0.8066 in testing accuracy. Moreover, the model achieves<br />0.796 and 0.8382 for 6 classes and 9 classes problems respectively.<br />Performance indicators like Recall, Precision, and F1 Score supported the<br />achieved results and proved that the proposed system is efficient for detecting<br />the manipulation in images.</p><div align="center"> </div>