Distinguishing Computer-generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

TL;DR

This paper presents a deep learning approach utilizing sensor pattern noise and high-pass filtering to accurately distinguish computer-generated graphics from natural images, even after compression.

Contribution

It introduces a novel CNN-based method with multiple high-pass filters that significantly improves CG versus NI classification accuracy, achieving 100% accuracy under challenging conditions.

Findings

The method with three HPFs outperforms other configurations.

Achieves 100% accuracy on compressed images.

Deep learning combined with sensor pattern noise effectively detects CGs.

Abstract

Computer-generated graphics (CGs) are images generated by computer software. The~rapid development of computer graphics technologies has made it easier to generate photorealistic computer graphics, and these graphics are quite difficult to distinguish from natural images (NIs) with the naked eye. In this paper, we propose a method based on sensor pattern noise (SPN) and deep learning to distinguish CGs from NIs. Before being fed into our convolutional neural network (CNN)-based model, these images---CGs and NIs---are clipped into image patches. Furthermore, three high-pass filters (HPFs) are used to remove low-frequency signals, which represent the image content. These filters are also used to reveal the residual signal as well as SPN introduced by the digital camera device. Different from the traditional methods of distinguishing CGs from NIs, the proposed method utilizes a five-layer CNN to classify the input image patches. Based on the classification results of the image patches, we deploy a majority vote scheme to obtain the classification results for the full-size images. The~experiments have demonstrated that (1) the proposed method with three HPFs can achieve better results than that with only one HPF or no HPF and that (2) the proposed method with three HPFs achieves 100\% accuracy, although the NIs undergo a JPEG compression with a quality factor of 75.