Acoustics, Speech, and Signal Processing, IEEE International Conference on (2009)
Apr. 19, 2009 to Apr. 24, 2009
Gopinath Sankar , Department of Computing Science, University of Alberta, Canada
Vicky Zhao , Department of Electrical and Computer Engineering, University of Alberta, Canada
Yee-Hong Yang , Department of Computing Science, University of Alberta, Canada
Photorealistic images can now be created using advanced techniques in computer graphics (CG). Synthesized elements could easily be mistaken for photographic (real) images. Therefore we need to differentiate between CG and real images. In our work, we propose and develop a new framework based on an aggregate of existing features. Our framework has a classification accuracy of 90% when tested on the de facto standard Columbia dataset, which is 4% better than the best results obtained by other prominent methods in this area. We further show that using feature selection it is possible to reduce the feature dimension of our framework from 557 to 80 without a significant loss in performance (≪ 1%). We also investigate different approaches that attackers can use to fool the classification system, including creation of hybrid images and histogram manipulations. We then propose and develop filters to effectively detect such attacks, thereby limiting the effect of such attacks to our classification system.
Y. Yang, V. Zhao and G. Sankar, "Feature based classification of computer graphics and real images," Acoustics, Speech, and Signal Processing, IEEE International Conference on(ICASSP), Taipei, Taiwan, 2009, pp. 1513-1516.