doi:

DOI: 10.3724/SP.J.1089.2010.11102

Journal of Computer-Aided Design & Computer Graphics (计算机辅助设计与图形学学报) 2010/22:9 PP.1613-1618

Discrimination between Natural Images and Photorealistic Computer Graphics Using Second-Order Difference Statistics


Abstract:
In this paper, a new discrimination method using second-order difference statistics is proposed which is designed to distinguish natural images from photorealistic computer graphics. Firstly, the second-order difference signals and predicting error signals of both original and calibrated images are extracted in the HSV color space, and then the variance and kurtosis of second-order difference signals and the first four order statistics of predicting error signals are extracted to be used as distinguishing features, the Fisher linear discriminant analysis is used to construct a classifier to do the differentiating job. Experimental results show that the proposed method exhibits excellent performance for the discrimination between natural images and computer graphics, outperforms previous proposed methods with a low computational complexity.

Key words:image forensics,second-order difference,predicting error,calibration,linear discriminant analysis

ReleaseDate:2014-07-21 15:25:49



[1] Sencar H T, Memon N. Overview of state-of-the-art in digital image forensics[M]. Kolkata: World Scientific Press, 2008

[2] Lyu S, Farid H. How realistic is photorealistic?[J]. IEEE Transactions on Signal Processing, 2005, 53(2): 845-850

[3] Wang Y, Moulin P. On discrimination between photorealistic and photographic images[C]// Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Toulouse, 2006: 161-164

[4] Chen W, Shi Y Q, Xuan G R. Identifying computer graphics using HSV color model and statistical moments of characteristic functions[C]// Proceedings of IEEE International Conference on Multimedia & Expo, Beijing, 2007: 1123-1126

[5] Cui Xia, Tong Xuefeng, Xuan Guorong, et al. Discrimination between photo images and computer graphics based on statistical moments in the frequency domain of histogram[C]// Proceedings of Chinese Information Hiding Workshop, Nanjing, 2007: 276-279 (in Chinese) (崔 霞, 童学锋, 宣国荣, 等. 基于直方图频域矩的自然图像和计算机图形的鉴别[C]// 第7届全国信息隐藏暨多媒体安全学术大会会议论文集, 南京, 2007: 276-279)

[6] Ng T T, Chang S F. Classifying photographic and photorealistic computer graphic images using natural image statistics[R]. Columbia: Columbia University, 2004

[7] Zheng Ergong, Ping Xijian. Identifying computer graphics from digital photographs based on coherence of adjacent pixels[J]. Journal of Computer Research and Development, 2009, 46(Suppl Ⅰ): 258-262 (in Chinese) (郑二功, 平西建. 一种基于相邻像素一致性的数码照片于计算机图像鉴别方法[J]. 计算机研究与发展, 2009, 46(增刊Ⅰ): 258-262)

[8] Ng T T, Chang S F, Hsu J,et al. Physics-motivated features for distinguishing photographic images and computer graphics[C]// Proceedings of the 13th Annual ACM International Conference on Multimedia, New York, 2005: 239-248

[9] Pan F, Cheng J B, Huang J W. Discriminating between photorealistic computer graphics and natural images using fractal geometry[J]. Science in China Series F: Information Sciences, 2009, 52(2): 329-337

[10] Dehnie S, Sencar T H, Memon N. Digital image forensics for identifying computer generated and digital camera images[C]// Proceedings of IEEE International Conference on Image Processing, Atlanta, 2006: 2313-2316

[11] Dirik A E, Bayram S, Sencar H T,et al. New features to identify computer generated images[C]// Proceedings of IEEE International Conference on Image Processing, San Antonio, 2007: 433-436

[12] Huang J G, Mumford D. Statistics of natural images and models[C]// Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, Collins, 1999: 541-547

[13] Ker A D. Steganalysis of LSB matching in grayscale images[J]. IEEE Signal Processing Letters, 2005, 12(6): 441-444

PDF