Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks

Nicolas Rahmouni (1) , Vincent Nozick (2) , Junichi Yamagishi (3) , Isao Echizen (3)

1 X - École polytechnique
2 JFLI - Japanese French Laboratory for Informatics
3 NII - National Institute of Informatics

This paper presents a deep-learning method for distinguishing computer generated graphics from real photographic images. The proposed method uses a Convolutional Neural Network (CNN) with a custom pooling layer to optimize current best-performing algorithms feature extraction scheme. Local estimates of class probabilities are computed and aggregated to predict the label of the whole picture. We evaluate our work on recent photo-realistic computer graphics and show that it outperforms state of the art methods for both local and full image classification.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]

Nicolas Rahmouni, Vincent Nozick, Junichi Yamagishi, Isao Echizen. Distinguishing Computer Graphics from Natural Images Using Convolution Neural Networks. IEEE Workshop on Information Forensics and Security, WIFS 2017, Dec 2017, Rennes, France. ⟨hal-01664590⟩