노이즈 기반의 새로운 피쳐(feature)와 SVM에 기반한 개선된 CG(Computer Graphics) 및 PI(Photographic Images) 판별 방법
New feature and SVM based advanced classification of Computer Graphics and Photographic Images
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
컴퓨터 그래픽 기술은 사람의 눈으로 컴퓨터 그래픽과 카메라로 촬영한 사진을 구분하기 힘들 정도로 발전하였다. 그래픽 기술의 진보는 인간에게 많은 편의를 주었으나 악의적인 조작·편집 및 사기 기법으로 사용되는 등 부작용도 수반하였다. 이에 대응하기 위해 이미지의 피쳐(feature)를 이용하여 컴퓨터 그래픽을 판별해내는 알고리즘에 대한 연구가진행되고 있다. 본 논문에서는 기존에 제안된 알고리즘을 직접 검증해보고 컴퓨터 그래픽의 특성을 잘 나타내는 노이즈에 기반한 새로운 피쳐를 제안한다. 또한 선행 연구에서 제안한 피쳐와 함께 SVM(Support Vector Machine)을 활용하여 판별 정확도를 높이는 방법을 소개한다.
Abstract
As modern computer graphics technology has been developed, it is hard to discriminate computer graphics from photographicimages with the naked eye. Advances in graphics technology has brought a lot of convenience to human, it has side effects suchas image forgery, malicious edit and fraudulent means. In order to cope with such problems, studies of various algorithms usinga feature that represents a characteristic of an image has been processed. In this paper, we verify directly the existing algorithm,and provide new features based a noise that represents the characteristics of the computer graphics well. And this paperintroduces the method of using SVM(Support Vector Machine) with features proposed in previous research to improve thediscrimination accuracy.
참고문헌 (9)
- S. Dehnie, "Digital image forensics for identifying computer generated and digital camera images", Proceedings of the 2006 IEEE International Conference on Image Processing, pp.2313~2316 (2006)
- Y. Wang, "On discrimination between photorealistic and photographic images", Proceedings of the 2006 IEEE international conference on acoustics, speech and signal processing, 2, pp.II-161~II-164 (2006)
- R. Wu, "Identifying computer generated graphics VIA histogram features", Proceedings of the 2011IEEE International Conference on Image Processing, pp.1933~1936 (2011)
- P. Sutthiwan, "Computer graphics classification based on markov process model and boosting feature selection technique", Proceedings of the 2009 IEEE International Conference on Image Processing, pp.2913~2916 (2009)
- T.-T. Ng, "Discrimination of computer synthesized or recaptured images from real images", Digital Image Forensics, pp.275~309 (2013)
- I. W. Selesnick, "The double-density dual-tree DWT", Signal Processing, IEEE Transactions on, 52(5), pp.1304~1314 (2004)
- N. Khanna, "Forensic techniques for classifying scanner, computer generated and digital camera images", Proceedings of the 2008 IEEE international conference on acoustics, speech and signal processing, pp.1653~1656 (2008)
- S.Lyu, "How realistic is photorealistic?", Signal Processing, IEEE Transactions on, 53(2), pp.845~850 (2005)
- L. Zhang, "PCA-based spatially adaptive denoising of CFA images for single-sensor digital cameras", Image Processing, IEEE Transactions on, 18(4), pp.797~812 (2009)