Copy-Paste Detection Based on a SIFT Marked Graph Feature Vector  

作　　者：LYU Yingda SHEN Xuanjing CHEN Haipeng 

机构地区：[1]College of Computer Science and Technology, Jilin University, Changchun 130012, China [2]Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China

出　　处：《Chinese Journal of Electronics》2017年第2期345-350,共6页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.61305046);the Natural Science Foundation of the Jilin Province(No.20140101193JC,No.20130522117JH,No.20150101055JC)

摘　　要：To detect copy-paste tampering,an improved SIFT(Scale invariant feature transform)-based algorithm was proposed.Maximum angle is defined and a maximum angle-based marked graph is constructed.The marked graph feature vector is provided to each SIFT key point via discrete polar coordinate transformation.Key points are matched to detect the copy-paste tampering regions.The experimental results show that the proposed algorithm can effectively identify and detect the rotated or scaled copy-paste regions,and in comparison with the methods reported previously,it is resistant to postprocessing,such as blurring,Gaussian white noise and JPEG recompression.The proposed algorithm performs better than the existing algorithm to dealing with scaling transformation.To detect copy-paste tampering,an improved SIFT（Scale invariant feature transform）-based algorithm was proposed.Maximum angle is defined and a maximum angle-based marked graph is constructed.The marked graph feature vector is provided to each SIFT key point via discrete polar coordinate transformation.Key points are matched to detect the copy-paste tampering regions.The experimental results show that the proposed algorithm can effectively identify and detect the rotated or scaled copy-paste regions,and in comparison with the methods reported previously,it is resistant to postprocessing,such as blurring,Gaussian white noise and JPEG recompression.The proposed algorithm performs better than the existing algorithm to dealing with scaling transformation.

关 键 词：Copy-paste tampering Image forensics Marked graph Maximum angle 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN912.3[自动化与计算机技术—计算机科学与技术]