A robust forgery detection algorithm for object removal by exemplar-based image inpainting
- 448 Downloads
Object removal is a malicious image forgery technique, which is usually achieved by exemplar-based image inpainting in a visually plausible way. Most existing forgery detection approaches utilize similar block pairs between inpainted area and the rest areas, but they invalidate when those inpainted images are further subjected to some post-processing operations such as JPEG compression, Gaussian noise addition and blurring. It is desirable to develop a forensic method which is robust to object removal with post-processing. From some preliminary experiments, we observe that post-processing destroys the similarity of block pairs and simultaneously disturbs the correlations among adjacent pixels to some extent. Inspired by the strong ability of joint probability density matrix (JPDM) in characterizing such correlation, we propose a hybrid forensics strategy. Firstly, our earlier method is employed to detect whether a candidate image is forged or not. Secondly, for those undetected images after the first step, JPDM is computed for each difference array to model the correlations among adjacent DCT coefficients, and the average of these matrixes are computed as feature vectors to further expose tampering traces. Experimental results show that the proposed approach can effectively detect object removal by exemplar-based inpainting either with or without post-processing.
KeywordsPassive image forensics Exemplar-based image inpainting Post-processing Joint probability density matrix
We would like to thank the anonymous reviewers for their professional comments and valuable suggestions. This work is partially or fully sponsored by National Natural Science Foundation of China (61572183, 61379143), the Specialized Research Fund for the Doctoral Program of Higher Education (20120161110014), the Scientific Research Fund of Hunan Provincial Education Department of China (14C0029), Natural Science Foundation of Hunan Province (2016JJ2005). The authors appreciate the nice help from Mr Moses Odero for his improving the English usages.
- 2.Bacchuwar KS, Ramakrishnan K R (2013) A jump patch-block match algorithm for multiple forgery detection. In: Proc. of IEEE international multi-conference on automation, computing, communication, control and compressed sensing (iMac4s), pp 723–728Google Scholar
- 5.Cozzolino D, Gragnaniello D, Verdoliva L (2014) Image forgery detection through residual-based local descriptors and block-matching. In: IEEE International conference on image processing (ICIP), pp 5297–5301Google Scholar
- 12.Kirchner M, Fridrich J (2010) On detection of median filtering in digital images. SPIE Electron Imag Int Soc Opt Photon 754110–754110Google Scholar
- 16.Liu Q, Chen Z (2014) Improved approaches with calibrated neighboring joint density to steganalysis and seam-carved forgery detection in JPEG images. ACM Trans Intell Syst Technol 5(4):63Google Scholar
- 19.Shi Y Q, Chen C, Xuan G et al (2007) Steganalysis versus splicing detection. Int Workshop Digit Watermark 158–172Google Scholar
- 21.Wu Q, Sun S J, Zhu W et al (2008) Detection of digital doctoring in exemplar-based inpainted images. In: Proc. of IEEE international conference on machine learning and cybernetics, vol 3, pp 1222–1226Google Scholar
- 25.Zhao X, Wang S, Li S et al (2013) Image splicing detection based on noncausal markov model. In: IEEE International conference on image processing, pp 4462–4466Google Scholar