Discriminating Between Computer-Generated Facial Images and Natural Ones Using Smoothness Property and Local Entropy

  • Huy H. Nguyen
  • Hoang-Quoc Nguyen-Son
  • Thuc D. Nguyen
  • Isao Echizen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9569)

Abstract

Discriminating between computer-generated images and natural ones is a crucial problem in digital image forensics. Facial images belong to a special case of this problem. Advances in technology have made it possible for computers to generate realistic multimedia contents that are very difficult to distinguish from non-computer generated contents. This could lead to undesired applications such as face spoofing to bypass authentication systems and distributing harmful unreal images or videos on social media. We have created a method for identifying computer-generated facial images that works effectively for both frontal and angled images. It can also be applied to extracted video frames. This method is based on smoothness property of the faces presented by edges and human skin’s characteristic via local entropy. Experiments demonstrated that performance of the proposed method is better than that of state-of-the-art approaches.

Keywords

Facial image Computer-generated image Image forensics Face spoofing 

References

  1. 1.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 187–194. ACM (1999)Google Scholar
  2. 2.
    Conotter, V., Bodnari, E., Boato, G., Farid, H.: Physiologically-based detection of computer generated faces in video. In: International Conference on Image Processing (ICIP), pp. 248–252. IEEE (2014)Google Scholar
  3. 3.
    Conotter, V., Cordin, L.: Detecting photographic and computer generated composites. In: IS&T/SPIE Electronic Imaging, pp. 7870–7876. SPIE (2011)Google Scholar
  4. 4.
    Dang-Nguyen, D.T., Boato, G., De Natale, F.G.: Discrimination between computer generated and natural human faces based on asymmetry information. In: European Signal Processing Conference (EUSIPCO), pp. 1234–1238. IEEE (2012)Google Scholar
  5. 5.
    Dang-Nguyen, D.T., Boato, G., De Natale, F.G.: Identify computer generated characters by analysing facial expressions variation. In: International Workshop on Information Forensics and Security (WIFS), pp. 252–257. IEEE (2012)Google Scholar
  6. 6.
    Dang-Nguyen, D.T., Boato, G., De Natale, F.G.: Revealing synthetic facial animations of realistic characters. In: International Conference on Image Processing (ICIP), pp. 5327–5331. IEEE (2014)Google Scholar
  7. 7.
    Khanna, N., Chiu, G.C., Allebach, J.P., Delp, E.J.: Forensic techniques for classifying scanner, computer generated and digital camera images. In: Acoustics, Speech and Signal Processing (ICASSP), pp. 1653–1656. IEEE (2008)Google Scholar
  8. 8.
    Lyu, S., Farid, H.: How realistic is photorealistic? IEEE Trans. Signal Process. 53(2), 845–850 (2005)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Peng, F., Li, J.T., Long, M.: Identification of natural images andcomputer-generated graphics based on statistical and textural features. J. Forensic Sci. 60, 435–443 (2014)CrossRefGoogle Scholar
  10. 10.
    Peng, F., Zhou, D.I.: Discriminating natural images and computer generated graphics based on the impact of CFA interpolation on the correlation of PRNU. Digit. Invest. 11(2), 111–119 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Huy H. Nguyen
    • 1
  • Hoang-Quoc Nguyen-Son
    • 2
  • Thuc D. Nguyen
    • 1
  • Isao Echizen
    • 3
  1. 1.VNUHCM - University of ScienceHo Chi Minh CityVietnam
  2. 2.SOKENDAI (The Graduate University for Advanced Studies)KanagawaJapan
  3. 3.National Institute of InformaticsTokyoJapan

Personalised recommendations