Olivia Holmes
Abstract
Modern computer graphics are capable of generating highly photorealistic images. Although this can be considered a success for the computer graphics community, it has given rise to complex forensic and legal issues. A compelling example comes from the need to distinguish between computer-generated and photographic images as it pertains to the legality and prosecution of child pornography in the United States. We performed psychophysical experiments to determine the accuracy with which observers are capable of distinguishing computer-generated from photographic images. We find that observers have considerable difficulty performing this task—more difficulty than we observed 5 years ago when computer-generated imagery was not as photorealistic. We also find that observers are more likely to report that an image is photographic rather than computer generated, and that resolution has surprisingly little effect on performance. Finally, we find that a small amount of training greatly improves accuracy.
- 1982. New York v. Ferber.Google Scholar
- 1996. Child Pornography Prevention Act (CPPA).Google Scholar
- 2003. Prosecutorial Remedies and Other Tools to End the Exploitation of Children Today (PROTECT) Act.Google Scholar
- Valentia Conotter, Ecaterina Bodnari, Boato Giulia, and Hany Farid. 2014. Physiologically-based detection of computer generated faces in video. In Proceedings of the IEEE International Conference on Image Processing.Google ScholarCross Ref
- Duc-Tien Dang-Nguyen, Giulia Boato, and Francesco G. B. De Natale. 2012a. Discrimination between computer generated and natural human faces based on asymmetry information. In Proceedings of the IEEE European Signal Processing. 1234--1238.Google Scholar
- Duc-Tien Dang-Nguyen, Giulia Boato, and Francesco G. B. De Natale. 2012b. Identify computer generated characters by analysing facial expressions variation. In Proceedings of the IEEE Workshop on Information Forensics and Security. 252--257.Google Scholar
- Sintayehu Dehnie, Taha Sencar, and Nasir Memon. 2006. Digital image forensics for identifying computer generated and digital camera images. In Proceedings of the IEEE International Conference on Image Processing. 2313--2316.Google ScholarCross Ref
- Ahmet Emir Dirik, Sevinc Bayram, Husrev T. Sencar, and Nasir Memon. 2007. New features to identify computer generated images. In Proceedings of the IEEE International Conference on Image Processing, Vol. 4.Google ScholarCross Ref
- Shaojing Fan, Tian-Tsong Ng, Jonathan S. Herberg, Bryan L. Koenig, and Shiqing Xin. 2012. Real or fake? Human judgments about photographs and computer-generated images of faces. In Proceedings of the SIGGRAPH Asia 2012 Technical Briefs (SA’12). Article No. 17. Google ScholarDigital Library
- Hany Farid and Mary J. Bravo. 2007. Photorealistic rendering: How realistic is it? Journal of Vision 7, 9, 766.Google Scholar
- Hany Farid and Mary J. Bravo. 2012. Perceptual discrimination of computer generated and photographic faces. Digital Investigation 8, 226--235.Google ScholarCross Ref
- Andrew C. Gallagher and Tsuhan Chen. 2008. Image authentication by detecting traces of demosaicing. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 1--8.Google Scholar
- David M. Green and John A. Sweats. 1966. Signal Detection Theory and Psychophysics. Peninsula Pub.Google Scholar
- Nitin Khanna, George T.-C. Chiu, Jan P. Allebach, and Edward J. Delp. 2008. Forensic techniques for classifying scanner, computer generated and digital camera images. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. 1653--1656.Google Scholar
- Jean-Francois Lalonde and Alexei A. Efros. 2007. Using color compatibility for assessing image realism. In Proceedings of the IEEE International Conference on Computer Vision. 1--8.Google Scholar
- Christine E. Looser and Thalia Wheatley. 2010. The tipping point of animacy: How, when, and where we perceive life in a face. Psychological Science 21, 1854--1862.Google ScholarCross Ref
- Siwei Lyu and Hany Farid. 2005. How realistic is photorealistic? IEEE Transactions on Signal Processing 53, 2, 845--850. Google ScholarDigital Library
- Tian-Tsong Ng, Shih-Fu Chang, Jessie Hsu, Lexing Xie, and Mao-Pei Tsui. 2005. Physics-motivated features for distinguishing photographic images and computer graphics. In Proceedings of the ACM International Conference on Multimedia. 239--248. Google ScholarDigital Library
- Ying Wang and Pierre Moulin. 2006. On discrimination between photorealistic and photographic images. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 2.Google ScholarCross Ref
- Chen Wen, Q. Shi Yun, and Xuan Guorong. 2007. Identifying computer graphics using HSV color model. In Proceedings of the IEEE International Conference on Multimedia and Expo.Google Scholar
Index Terms
- Assessing and Improving the Identification of Computer-Generated Portraits
Recommendations
Illumination for computer generated pictures
The quality of computer generated images of three-dimensional scenes depends on the shading technique used to paint the objects on the cathode-ray tube screen. The shading algorithm itself depends in part on the method for modeling the object, which ...
Texture and reflection in computer generated images
In 1974 Catmull developed a new algorithm for rendering images of bivariate surface patches. This paper describes extensions of this algorithm in the areas of texture simulation and lighting models. The parametrization of a patch defines a coordinate ...
Teaching a Shader-Based Introduction to Computer Graphics
Recent GPU technology advances have led to dramatic changes in graphics software that let applications exploit the GPU's full power through programmable shaders. Introductory computer graphics courses should reflect these advances.
Comments