Proceedings of the 2012 National Conference on Information Technology and Computer Science

A Novel Photographic and Computer Graphic Composites Detection Method

Authors
Zhenwei Chen, Yongzhen Ke
Corresponding Author
Zhenwei Chen
Available Online November 2012.
DOI
https://doi.org/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.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2012 National Conference on Information Technology and Computer Science
Part of series
Advances in Intelligent Systems Research
Publication Date
November 2012
ISBN
978-94-91216-39-8
ISSN
1951-6851
DOI
https://doi.org/10.2991/citcs.2012.108How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

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  - 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  - https://doi.org/10.2991/citcs.2012.108
ID  - Chen2012/11
ER  -