Photorealistic Computer Graphics Identifying Algorithm based on Edge Detection

DOI

10.2991/ameii-15.2015.15How to use a DOI?

Keywords

Photorealistic Computer Graphics; natural image; Image Authenticity; SVM

Abstract

As for the problem the image can be generated by computer software, so that we cannot recognize the authenticity of these images using our eyes. In this paper by analyzing the differences between photorealistic computer graphics and natural image on image texture, we put forward a photorealistic computer graphics identifying algorithm based on edge detection. Image gradient can describe the details of the image and then we extract the feature value according to details of the image. The last we use SVM classifier to classify. The results show that the presented method can not only identify the photorealistic computer graphics and natural image but also have better identification rate.

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)

TY  - CONF
AU  - Lin Deng
AU  - Changming Liu
AU  - Haiyu Li
PY  - 2015/04
DA  - 2015/04
TI  - Photorealistic Computer Graphics Identifying Algorithm based on Edge Detection
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 90
EP  - 93
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.15
DO  - 10.2991/ameii-15.2015.15
ID  - Deng2015/04
ER  -