计算机科学 ›› 2018, Vol. 45 ›› Issue (4): 173-177.doi: 10.11896/j.issn.1002-137X.2018.04.029

• 信息安全 • 上一篇    下一篇

基于多残差马尔科夫模型的图像拼接检测

罗霄阳,霍宏涛,王梦思,陈亚飞   

  1. 中国人民公安大学信息技术与网络安全学院 北京100038,中国人民公安大学信息技术与网络安全学院 北京100038,中国人民公安大学信息技术与网络安全学院 北京100038,中国人民公安大学信息技术与网络安全学院 北京100038
  • 出版日期:2018-04-15 发布日期:2018-05-11
  • 基金资助:
    本文受公安部技术研究计划项目(2014JSYJB007)资助

Passive Image-splicing Detection Based on Multi-residual Markov Model

LUO Xiao-yang, HUO Hong-tao, WANG Meng-si and CHEN Ya-fei   

  • Online:2018-04-15 Published:2018-05-11

摘要: 针对传统马尔科夫特征计算差值矩阵的方式单一、拼接检测鲁棒性不强的问题,提出彩色多残差马尔科夫特征拼接检测模型。该模型引入隐写检测模型(Rich Models for Steganalysis,SRM)中的多种残差类型来改进传统马尔科夫特征,从R,G,B 3个通道分别提取10种不同类型的马尔科夫特征,训练30个独立的SVM分类器,最后通过决策判断进行分类预测。该方法在哥伦比亚大学彩色拼接检测库上达到了95.40%的准确率。

关键词: 图像取证,拼接检测,隐写检测模型(SRM),马尔科夫特征

Abstract: Aiming at the problem that calculating the difference matrix singly for the traditional Markov feature is not robust to the splicing detection,this paper presented a color multi-residual type Markov feature for splicing detection.This method introduces the residual model from rich models for steganalysis(SRM) to improve the traditional Markov features,respectively extracts 10 different types of Markov features from three color channels,and trains 30 unique SVM classifiers to make the classification through the proposed decision-making algorithm.This method achieves the accuracy of 95.40% at Columbia image splicing detection evaluation dataset.

Key words: Image forensics,Splicing detection,Rich models for steganalysis,Markov feature

[1] FARID H,LYU S.Higher-order Wavelet Statistics and theirApplication to Digital Forensics[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2003.
[2] FU D,SHI Y Q,SU W.Detection of image splicing based on Hilbert-Huang transform and moments of characteristic functions with wavelet decompo-sition[C]∥Proceedings of the 5th International Workshop on Digital Watermarking.Berlin:Springer,2006:177-187.
[3] LIU X X,LI F,XIONG B.Image splicing detection using Weber local descriptors[J].Computer Engineering and Applications,2013,9(12):140-143.(in Chinese) 刘晓霞,李峰,熊兵.基于韦伯局部特征的图像拼接检测[J].计算机工程与应用,2013,9(12):140-143.
[4] SHI Y Q,CHEN C,CHEN W,et al.A natural image model approach to splicing detection[C]∥The Workshop on Multimedia &Security.ACM,2007:51-62.
[5] HE Z,LU W,SUN W,et al.Digital image splicing detectionbased on Markov features in DCT and DWT domain[J].Pattern Recognition,2012,45(12):4292-4299.
[6] SU B,YUAN Q,ZHANG Y,et al.Rapid Image Splicing Detection Based on Relevance Vector Machine[M]// Digital Forensics and Watermaking.Springer Berlin Heidelberg,2012:300-310.
[7] YUAN Q Q.Image Splicing Blind Detection Based on Enhanced MavkovModel in DWT Domain[D].Shanghai:Shanghai Jiao Tong University,2014.(in Chinese) 袁全桥.基于小波域改进马尔科夫模型的图像拼接盲检测研究[D].上海:上海交通大学,2014.
[8] LI Y,ZHONG L,LI J.Detection of image splicing forgery based on LBP and co-occurrence matrix[J].Journal of Wuhan University (Natural Science Edition),2015,1(6):517-524.(in Chinese) 李燕,钟磊,李健.基于LBP和共生矩阵的图像拼接篡改检测[J].武汉大学学报(理学版),2015,1(6):517-524.
[9] QIU X,LI H,LUO W,et al.A universal image forensic strategy based on steganalytic model[C]∥Proceedings of the 2nd ACM Workshop on Information Hiding and Multimedia Security.ACM,2014:165-170.
[10] FRIDRICH J,KODOVSKY J.Rich Models for Steganalysis of Digital Images[J].IEEE Transactions on Information Forensics &Security,2012,7(3):868-882.
[11] BATTISTI F,CARLI M,NERI A.Image forgery detection by means of no-reference quality metrics[C]∥Media Watermar-king,Security,and Forensics.International Society for Optics and Photonics,2012:265-298.
[12] YUAN Q Q,SU B,ZHAO X D,et al.Image splicing detectionbased on high frequency wavelet Markov features[J].Journal of Computer Applications,2014,4(5):1477-1481.(in Chinese) 袁全桥,苏波,赵旭东,等.基于高频小波子带马尔可夫特征的图像拼接检测[J].计算机应用,2014,4(5):1477-1481.
[13] Columbia DVMM Research Lab(2004) Columbia image splicing detection evaluation dataset.http://www.ee.columbia.edu/ln/dvmm/downloads/authsplcuncmp.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!