Blind copy-paste detection using improved SIFT ring descriptor

Authors:
Lin-na Zhou;Yun-biao Guo;Xin-gang You
Affiliations:
Department of Electronic Engineering, Tsinghua University, Beijing, China,Beijing Institute of Electronic Technology Application, Beijing, China;Beijing Institute of Electronic Technology Application, Beijing, China;Beijing Institute of Electronic Technology Application, Beijing, China
Venue:
IWDW'11 Proceedings of the 10th international conference on Digital-Forensics and Watermarking
Year:
2011

Citing 5
Cited 0

Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Robust Detection of Region-Duplication Forgery in Digital Image

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Detecting filtered cloning in digital images

Proceedings of the 9th workshop on Multimedia & security
Detection of Copy-Move Forgery in Digital Images Using SIFT Algorithm

PACIIA '08 Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application - Volume 02
Region duplication detection using image feature matching

IEEE Transactions on Information Forensics and Security

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent studies on digital watermarking and forensics techniques for multimedia security have been focused on digital multimedia forensics & anti-forensics. The digital forensic to detect image content tampering is a typical application of multimedia security. Based on improved scale invariant feature transform(SIFT), a new copy-move detection method using ring and sequence of each feature vector to ensure rotation invariance is proposed in this paper, which reduces the operator dimension of description. Experimental results show that the improved algorithm is more stable and faster when copy-paste fake combination in post-processing such as rotation, scaling and intensity adjustment.