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

Nowadays, the internet has become a typical medium for sharing digitalimages through web applications or social media and there was a rise inconcerns about digital image privacy. Image editing software’s have preparedit incredibly simple to make changes to an image's content without leavingany visible evidence for images in general and medical images in particular.In this paper, the COVID-19 digital x-rays forgery classification modelutilizing deep learning will be introduced. The proposed system will be ableto identify and classify image forgery (copy-move and splicing) manipulation.Alexnet, Resnet50, and Googlenet are used in this model for feature extractionand classification, respectively. Images have been tampered with in threeclasses (COVID-19, viral pneumonia, and normal). For the classification of(Forgery or no forgery), the model achieves 0.9472 in testing accuracy. Forthe classification of (Copy-move forgery, splicing forgery, and no forgery),the model achieves 0.8066 in testing accuracy. Moreover, the model achieves0.796 and 0.8382 for 6 classes and 9 classes problems respectively.Performance indicators like Recall, Precision, and F1 Score supported theachieved results and proved that the proposed system is efficient for detectingthe manipulation in images.