Classifying Photographic and Photorealistic Computer Graphic Images using Natural Image Statistics

As computer graphics (CG) is getting more photorealistic, for the purpose of image authentication, it becomes increasingly important to construct a detector for classifying photographic images (PIM) and photorealistic computer graphics (PRCG). To this end, we propose that photographic images contain natural-imaging quality (NIQ) and natural-scene quality (NSQ). NIQ is due to the imaging process, while NSQ is due to the subtle physical light transport in a real-world scene. We explicitly model NSQ of photographic images using natural image statistics (NIS). NIS has been used as an image prior in applications such as image compression and denoising. However, NIS has not been comprehensively and systematically employed for classifying PIM and PRCG. In this work, we study three types of NIS with different statistical order, i.e., NIS derived from the power spectrum, wavelet transform and local patch of images. The experiment shows that the classification is in line with the statistical order of the NIS. The local patch NIS achieves a classification accuracy of 83% which outperforms the features derived from modeling the characteristics of computer graphics.

[1]  Ilaria Venturini.  Counteracting Oracle attacks , 2004, MM&Sec '04.

[2]  Kim Steenstrup Pedersen,et al.  The Nonlinear Statistics of High-Contrast Patches in Natural Images , 2003, International Journal of Computer Vision.

[3]  Siwei Lyu,et al.  Higher-order Wavelet Statistics and their Application to Digital Forensics , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[4]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[5]  Mohamed F. Mansour,et al.  Secure watermark detection with nonparametric decision boundaries , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Brendan J. Frey,et al.  Unsupervised image translation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Eero P. Simoncelli,et al.  On Advances in Statistical Modeling of Natural Images , 2004, Journal of Mathematical Imaging and Vision.

[8]  Eero P. Simoncelli.  Modeling the joint statistics of images in the wavelet domain , 1999, Optics & Photonics.

[9]  D. Geman,et al.  Invariant Statistics and Coding of Natural Microimages , 1998 .

[10]  M. Langer.  Large-scale failures of f(-alpha) scaling in natural image spectra. , 2000, Journal of the Optical Society of America. A, Optics, image science, and vision.

[11]  Kim Steenstrup Pedersen,et al.  Toward a Full Probability Model of Edges in Natural Images , 2002, ECCV.

[12]  Takeo Kanade,et al.  Statistical calibration of CCD imaging process , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[13]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[14]  Erik Reinhard,et al.  Second order image statistics in computer graphics , 2004, APGV '04.

[15]  Mitchell G. A. Thomson,et al.  Higher-order structure in natural scenes , 1999 .

[16]  T Troscianko,et al.  Color and luminance information in natural scenes. , 1998, Journal of the Optical Society of America. A, Optics, image science, and vision.

[17]  Arjen van der Schaaf,et al.  Natural image statistics and visual processing , 1998 .

[18]  Siwei Lyu,et al.  How realistic is photorealistic , 2005 .

[19]  Arjen P. de Vries,et al.  Detecting cartoons: a case study in automatic video-genre classification , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[20]  Brendan J. Frey,et al.  Epitomic analysis of appearance and shape , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.