A Novel Photographic and Computer Graphic Composites Detection Method

DOI

10.2991/citcs.2012.108How to use a DOI?

Keywords

digital image forensics; computer graphics; pattern noise; histogram features

Abstract

With the development of the rendering techniques, the visual difference between photographic images (PG) and computer graphics (CG) is becoming smaller. And the digital image forgery is not limited to the composite between photographic, splicing of computer graphics and photographic is also a problem to be resolved. To come up with this problem, in this paper we propose a novel hybrid classifier based on pattern noise statistics and histogram features. Experimental results show that proposed method is capable of improving the performance of the prior techniques. The proposed method also has a good performance on detection of local forgeries.

Copyright

© 2012, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhenwei Chen
AU  - Yongzhen Ke
PY  - 2012/11
DA  - 2012/11
TI  - A Novel Photographic and Computer Graphic Composites Detection Method
BT  - Proceedings of the 2012 National Conference on Information Technology and Computer Science
PB  - Atlantis Press
SP  - 415
EP  - 418
SN  - 1951-6851
UR  - https://doi.org/10.2991/citcs.2012.108
DO  - 10.2991/citcs.2012.108
ID  - Chen2012/11
ER  -