Distinguishing Computer Graphics from Natural Images Based on Statistical Characteristics


Article Preview

In this paper, we propose a new discrimination method using image statistical characteristics is proposed which is designed to distinguish natural images from photorealistic computer graphics. Using Benford model as statistical basis, we conclude statistical properties of the MSD (most significant digit) of AC (Alternating Current) coefficients in DCT (Discrete Cosine Transform) domain of natural images and computer graphics, and then we constructed the detection model of the proposed algorithm. Experimental results show that this method can identify natural images and computer graphics effectively, compared with the existing algorithms this method has a higher recognition rate, which comes to 95.22%.



Edited by:

X.D. Yu






S. F. Tong et al., "Distinguishing Computer Graphics from Natural Images Based on Statistical Characteristics", Applied Mechanics and Materials, Vols. 380-384, pp. 1306-1309, 2013

Online since:

August 2013




[1] S. L yu, H. Farid, IEEE Transactions on Signal Processing. 53, 845(2005).

[2] X. L. Wang, S. H. Li, B. Jin, A. X. Zhang, T. Zhu, Journal of Optoelectronics• Laser. 21, 783(2010).

[3] X. W. Li, T. Zhang, E. G. Zhang, T. Ran, X. J. Ping, Journal of Computer-Aided Design & Computer Graphics. 22, 195(2010).

[4] P. H. Theodore, Transaction on Statistical Science. 10, 354(1995).

[5] G. F. Perez, G. Helileman, C. T. Abdallah, A Generalization of Benfod's Law and Its Application to Images, European Control Conference 2007, (2007) July ; Kos, Greece.

[6] G. Qadir, X. Zhao, A.T. Ho, Image forensic of glare feature for improving image retrieval using Benford's Law, IEEE International Symposium on Circuits and Systems, (2011) May15-18; Rio de Janeiro, Brazil.

DOI: 10.1109/iscas.2011.5938152

[7] S. Zhao, Q. Zhao, Computer Engineering. 36, 190(2010).

[8] D. Fu, Y. Q. Shi, W. Su, A Generalized Benford's Law for JPEG Coefficients and Its Applications in Image Forensics, SPIE Electronic Imaging, (2007) January2-5; San Jose, United States.

[9] L. N. Zhou, D. M. Dong, Digital Image Forensics, Beijing University of Posts and Telecommunications Press, Beijing (2008).

[10] Columbia DVMM Research Lab. [DB/OL]. http: /www. ee. columbia. edu/ln/dvmm.

In order to see related information, you need to Login.