Detecting computer generated images based on local ternary count
- 97 Downloads
Local binary patterns was used to distinguish the Photorealistic Computer Graphics and Photographic Images, however the dimension of the extracted features is too high. Accordingly, the Local Ternary Count based on the Local Ternary Patterns and the Local Binary Count was developed in this study. Furthermore, a novel algorithm is presented based on the Local Ternary Count to classify photorealistic Computer Graphics and Photographic images. The experiment results show that the proposed algorithm effectively reduces the dimension of the classification features and maintains a good classification performance.
Keywordspassive forensics photographic images photorealistic computer graphics local ternary count support vector machine
Unable to display preview. Download preview PDF.
- 1.T.-T. Ng, S.-F. Chang, J. Hsu, and M. Pepeljugoski, “Columbia photographic images and ohotorealistic computer graphics dataset,” ADVENT Tech. Rep. (Columbia Univ., Feb. 2005), no. 203-2004-3. http://www1.i2r.a-star.edu.sg/~ttng/Datasets.htmlGoogle Scholar
- 2.R. D. W. S. J. Fan and Y. P. Zhang, “Classifying computer generated graphics and natural imaged based on image contour information,” J. Inf. Comput. Sci. 9 (10), 2877–2895 (2012).Google Scholar
- 3.H. Farid and S. Lyu, “Higher-order wavelet statistics and their application to digital forensics,” in Proc. IEEE Workshop on Statistical Analysis in Computer Vision (Madison, 2003).Google Scholar
- 5.W. Chen, Y. Q. Shi, and G. Xuan, “Identifying computer graphics using HSV color model and statistical moments of characteristic functions,” in Proc. IEEE Int. Conf. on Multimedia and Expo (Bejing, 2007), pp. 1123–1126.Google Scholar
- 6.W. Chen, Y. Q. Shi, G. Xuan, et al., “Computer graphics identification using genetic algorithm,” in Proc. 19th Int. Conf. on Pattern Recognition ICPR 2008 (Tampa, 2008), pp 1–4.Google Scholar
- 7.X. Cui, X. Tong, G. Xuan, et al., “Discrimination between photo images and computer graphics based on statistical moments in the frequency domain of histogram,” in Proc. CIHW2007 (Nanjing, 2007), pp. 276–283.Google Scholar
- 12.C. C. Chang and C. J. Lin, “LIBSVM: A library for support vector machines,” ACM Trans. Intellig. Syst. Technol. 2 (3), 27 (2011).Google Scholar
- 13.Columbia University. Computer Vision Laboratory. http://www.cs.columbia.edu/CAVE/Google Scholar
- 14.E. G. Zheng and X. J. Ping, “Identifying computer graphics from digital photographs based on coherence of adjacent pixels,” J. Comput. Res. Develop. 46 (z1) (2009).Google Scholar