Improved Tampering Localization in Digital Image Forensics Based on Maximal Entropy Random Walk

In this paper we propose to use maximal entropy random walk on a graph for tampering localization in digital image forensics. Our approach serves as an additional post-processing step after conventional sliding-window analysis with a forensic detector. Strong localization property of this random walk will highlight important regions and attenuate the background - even for noisy response maps. Our evaluation shows that the proposed method can significantly outperform both the commonly used threshold-based decision, and the recently proposed optimization-based approach with a Markovian prior.

[1]  Jianquan Liu,et al.  Link prediction: the power of maximal entropy random walk , 2011, CIKM '11.

[2]  J. Duda.  Extended Maximal Entropy Random Walk , 2012 .

[3]  Chiou-Ting Hsu,et al.  What has been tampered? From a sparse manipulation perspective , 2013, 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP).

[4]  Davide Cozzolino,et al.  Image forgery detection based on the fusion of machine learning and block-matching methods , 2013, ArXiv.

[5]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Jing Dong,et al.  Exploring DCT Coefficient Quantization Effects for Local Tampering Detection , 2014, IEEE Transactions on Information Forensics and Security.

[7]  Mauro Barni,et al.  A Framework for Decision Fusion in Image Forensics Based on Dempster–Shafer Theory of Evidence , 2013, IEEE Transactions on Information Forensics and Security.

[8]  Gerald Schaefer,et al.  UCID: an uncompressed color image database , 2003, IS&T/SPIE Electronic Imaging.

[9]  Roberto Caldelli,et al.  Splicing forgeries localization through the use of first digit features , 2014, 2014 IEEE International Workshop on Information Forensics and Security (WIFS).

[10]  Jiwu Huang,et al.  Detect Digital Image Splicing with Visual Cues , 2009, Information Hiding.

[11]  Bin Li,et al.  Detecting doubly compressed JPEG images by using Mode Based First Digit Features , 2008, 2008 IEEE 10th Workshop on Multimedia Signal Processing.

[12]  Xinjian Chen,et al.  Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images , 2015, IEEE Transactions on Image Processing.

[13]  Davide Cozzolino,et al.  Guided filtering for PRNU-based localization of small-size image forgeries , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Davide Cozzolino,et al.  A feature-based approach for image tampering detection and localization , 2014, 2014 IEEE International Workshop on Information Forensics and Security (WIFS).

[15]  Yihua Tan,et al.  Maximal Entropy Random Walk for Region-Based Visual Saliency , 2014, IEEE Transactions on Cybernetics.

[16]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[17]  Mo Chen,et al.  Determining Image Origin and Integrity Using Sensor Noise , 2008, IEEE Transactions on Information Forensics and Security.

[18]  Z. Burda,et al.  Localization of the maximal entropy random walk. , 2008, Physical review letters.

[19]  Luisa Verdoliva,et al.  A Bayesian-MRF Approach for PRNU-Based Image Forgery Detection , 2014, IEEE Transactions on Information Forensics and Security.

[20]  Deepu Rajan,et al.  Random Walks on Graphs for Salient Object Detection in Images , 2010, IEEE Transactions on Image Processing.