Distinguishing computer-generated graphics from natural images based on sensor pattern noise and deep learning

Ye Yao, Weitong Hu, Wei Zhang, Ting Wu, Yun Qing Shi

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

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.

Original languageEnglish (US)
Article number1296
JournalSensors (Switzerland)
Volume18
Issue number4
DOIs
StatePublished - Apr 23 2018

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Biochemistry
  • Atomic and Molecular Physics, and Optics
  • Instrumentation
  • Electrical and Electronic Engineering

Keywords

  • Computer-generated graphics
  • Convolutional neural network
  • Image forensics
  • Natural images
  • Sensor pattern noise

Fingerprint Dive into the research topics of 'Distinguishing computer-generated graphics from natural images based on sensor pattern noise and deep learning'. Together they form a unique fingerprint.

Cite this