Exposing Copy-Paste-Blur Forgeries Based on Color Coherence  

作　　者：WANG Bo KONG Xiangwei Elisa Bertino FU Haiyan 

机构地区：[1]Department of Electronic and Information Engineering, DaIian University of Technology, Dalian 116023, China [2]CERIAS and Computer Science Department, Purdue University, West Lafayette, Indiana, 47907-2067, USA

出　　处：《Chinese Journal of Electronics》2009年第3期487-490,共4页电子学报（英文版）

基　　金：This work is supported by the National High Technology Research and Development Program of China （863 Program） （No.2008AA01Z418） and the National Natural Science Foundation of China （No.60572111）.

摘　　要：Exposing digital image forgeries is a major challenge for photography authentication and forensics investigations which aims at proving the authenticity of digital photos. In this paper, we introduce a digital image forensics approach based on color coherence to exposing copy-paste-blur forgeries. We first discuss the inherent color coherence introduced by imaging pipeline, and then obtain several statistical features from the coherence char- acterization. Using the SVM classifier, we reveal traces of copy-paste-blur tampering in photographic forgeries. Experimental results indicate that the proposed method can effectively expose the copy-paste-blur forgeries and localize the tampered regions with high accuracy.

关 键 词：Digital image forensics Photographic forgery Color coherence Copy-paste-blur tampering Feature extraction. 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] D918.92[自动化与计算机技术—控制科学与工程]