Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering

Computer- Generated Image Identification Based on Image Gradient

Authors
Haiyu Li, Yanjun Sun
Corresponding Author
Haiyu Li
Available Online April 2015.
DOI
10.2991/isrme-15.2015.84How to use a DOI?
Keywords
computer- generated image;natural image; image identification
Abstract

In consideration about human eyes’ incapability of computer- generated image identification, this thesis proposes an identification algorithm that uses image gradient in difference analysis between texture of computer generated images and natural images; image gradient is an efficient image detail presentation, which is feature that the algorithm takes advantage of for characteristic value collection and further categorization with SVM classifier. Test results indicate that the algorithm proposed in this thesis is capable of efficient identification on computer- generated image and real images.

Copyright
© 2015, 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)

Volume Title
Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering
Series
Advances in Intelligent Systems Research
Publication Date
April 2015
ISBN
10.2991/isrme-15.2015.84
ISSN
1951-6851
DOI
10.2991/isrme-15.2015.84How to use a DOI?
Copyright
© 2015, 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/).

Cite this article

TY  - CONF
AU  - Haiyu Li
AU  - Yanjun Sun
PY  - 2015/04
DA  - 2015/04
TI  - Computer- Generated Image Identification Based on Image Gradient
BT  - Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering
PB  - Atlantis Press
SP  - 394
EP  - 397
SN  - 1951-6851
UR  - https://doi.org/10.2991/isrme-15.2015.84
DO  - 10.2991/isrme-15.2015.84
ID  - Li2015/04
ER  -