Assessing and Improving the Identification of Computer-Generated Portraits

作者: Olivia Holmes , Martin S. Banks , Hany Farid

DOI: 10.1145/2871714

关键词:

摘要: Modern computer graphics are capable of generating highly photorealistic images. Although this can be considered a success for the community, it has given rise to complex forensic and legal issues. A compelling example comes from need distinguish between computer-generated photographic images as pertains legality prosecution child pornography in United States. We performed psychophysical experiments determine accuracy with which observers distinguishing find that have considerable difficulty performing task—more than we observed 5 years ago when imagery was not photorealistic. also more likely report an image is rather generated, resolution surprisingly little effect on performance. Finally, small amount training greatly improves accuracy.

参考文章(17)
Francesco G.B. De Natale, Duc-Tien Dang-Nguyen, Giulia Boato, Discrimination between computer generated and natural human faces based on asymmetry information european signal processing conference. pp. 1234- 1238 ,(2012)
Keith A. May, Robert F. Hess, Ladder contours are undetectable in the periphery: A crowding effect? Journal of Vision. ,vol. 7, pp. 9- 9 ,(2007) , 10.1167/7.13.9
V. Conotter, E. Bodnari, G. Boato, H. Farid, Physiologically-based detection of computer generated faces in video 2014 IEEE International Conference on Image Processing (ICIP). pp. 248- 252 ,(2014) , 10.1109/ICIP.2014.7025049
Shaojing Fan, Tian-Tsong Ng, Jonathan S. Herberg, Bryan L. Koenig, Shiqing Xin, Real or Fake?: human judgments about photographs and computer-generated images of faces international conference on computer graphics and interactive techniques. pp. 17- ,(2012) , 10.1145/2407746.2407763
Sintayehu Dehnie, Taha Sencar, Nasir Memon, Digital Image Forensics for Identifying Computer Generated and Digital Camera Images international conference on image processing. pp. 2313- 2316 ,(2006) , 10.1109/ICIP.2006.312849
Tian-Tsong Ng, Shih-Fu Chang, Jessie Hsu, Lexing Xie, Mao-Pei Tsui, Physics-motivated features for distinguishing photographic images and computer graphics Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05. pp. 239- 248 ,(2005) , 10.1145/1101149.1101192
Hany Farid, Mary J Bravo, None, Perceptual discrimination of computer generated and photographic faces Digital Investigation. ,vol. 8, pp. 226- 235 ,(2012) , 10.1016/J.DIIN.2011.06.003
H. Farid, M. Bravo, Photorealistic rendering: How realistic is it? Journal of Vision. ,vol. 7, pp. 766- 766 ,(2010) , 10.1167/7.9.766
Wen Chen, Yun Q. Shi, Guorong Xuan, Identifying Computer Graphics using HSV Color Model and Statistical Moments of Characteristic Functions international conference on multimedia and expo. pp. 1123- 1126 ,(2007) , 10.1109/ICME.2007.4284852
A. E. Dirik, S. Bayram, H. T. Sencar, N. Memon, New Features to Identify Computer Generated Images international conference on image processing. ,vol. 4, pp. 433- 436 ,(2007) , 10.1109/ICIP.2007.4380047