Deep learning for image forgery classification based on modified Xception net and dense net

This paper deals with the problem of image forgery detection because of the problems it causes. Where The Fake images can lead to social problems, for example, mislead society, divert people’s mentality, denigrating an individual, and using them as evidence in law may mislead the court. This work proposes a deep learning approach based on Deep CNN (Convolutional Neural Network) Architecture, to detect fake images .the network is based on a modified structure of Xception net, The CNN based on depthwise separable convolution layers, The CNN feature maps can be separated. After extracting the feature maps, pooling layers used with dense connection with Xception output, to increase feature maps. Inspired by the idea of a densenet network. On the other hand, the work uses the YCbCr color system for images, which gave better Accuracy up to 99.41, more than RGB, HSV, and XYZ color systems.