Blind Identification of Photorealistic Computer Graphics Based on Fractal Dimensions

DOI

10.2991/ccit-14.2014.67How to use a DOI?

Keywords

Photorealistic Computer Graphic, Fractal Dimension, Colour Space, Gradient image

Abstract

The perceptual differences between photographic images and CG primarily exist in the colour and the surface texture. In this study a blind identification algorithm was proposed to identify CG, which is based on fractal dimensions. Firstly, change the image’s colour space from RGB to HSV and extract fractal dimensions on HSV colour space; Secondly, obtain fractal dimensions from image’s gradient image; Thirdly, calculate fractal dimensions of PEM and the global fractal dimension. The experimental results showed its effectiveness, and the correct detection rate of CG is 96%.

Copyright

© 2014, 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  - Yingda Lv
AU  - XuanJing Shen
AU  - Guofu Wan
AU  - HaiPeng Chen
PY  - 2014/01
DA  - 2014/01
TI  - Blind Identification of Photorealistic Computer Graphics Based on Fractal Dimensions
BT  - Proceedings of the 2014 International Conference on Computer, Communications and Information Technology
PB  - Atlantis Press
SP  - 257
EP  - 260
SN  - 1951-6851
UR  - https://doi.org/10.2991/ccit-14.2014.67
DO  - 10.2991/ccit-14.2014.67
ID  - Lv2014/01
ER  -