NEAR-DUPLICATE VIDEO DETECTION EXPLOITING NOISE RESIDUAL TRACES

Video phylogeny research about joint analysis of correlated video sequences has shown the possibility of developing interesting forensic applications. As an example, it is possible to study the provenance of near-duplicate (ND) video sequences, i.e., videos generated from the same original one through content preserving transformations. To perform this kind of analysis, accurate detection of ND videos is paramount. In this paper, we propose an algorithm for ND video detection and clustering in a challenging setup. Specifically, we analyze a scenario in which many videos, depicting the same event, are recorded by different users. This situation is critical as non-ND videos acquired from very close viewpoints run the risk of being incorrectly detected as ND. The proposed approach leverages on robust hashing properties and the concept of sensor noise traces.

[1]  Paolo Bestagini,et al.  Codec and GOP Identification in Double Compressed Videos , 2016, IEEE Transactions on Image Processing.

[2]  Nasir D. Memon,et al.  Spatio–Temporal Transform Based Video Hashing , 2006, IEEE Transactions on Multimedia.

[3]  Joydeep Ghosh,et al.  Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions , 2002, J. Mach. Learn. Res..

[4]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[5]  Mo Chen,et al.  Source digital camcorder identification using sensor photo response non-uniformity , 2007, Electronic Imaging.

[6]  Shih-Fu Chang,et al.  Internet image archaeology: automatically tracing the manipulation history of photographs on the web , 2008, ACM Multimedia.

[7]  Paolo Bestagini,et al.  Hash-based frame selection for video phylogeny , 2016, 2016 IEEE International Workshop on Information Forensics and Security (WIFS).

[8]  Miroslav Goljan,et al.  Digital camera identification from sensor pattern noise , 2006, IEEE Transactions on Information Forensics and Security.

[9]  Paolo Bestagini,et al.  Who is my parent? Reconstructing video sequences from partially matching shots , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[10]  C. Mallows,et al.  A Method for Comparing Two Hierarchical Clusterings , 1983 .

[11]  William M. Rand,et al.  Objective Criteria for the Evaluation of Clustering Methods , 1971 .

[12]  Jessica J. Fridrich,et al.  Camera identification from cropped and scaled images , 2008, Electronic Imaging.

[13]  Paolo Bestagini,et al.  Phylogeny reconstruction for misaligned and compressed video sequences , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[14]  Shih-Fu Chang,et al.  Duplicate detection in consumer photography and news video , 2002, MULTIMEDIA '02.

[15]  John R. Kender,et al.  Video genetics: a case study from YouTube , 2010, ACM Multimedia.

[16]  Nasir D. Memon,et al.  Video copy detection based on source device characteristics: a complementary approach to content-based methods , 2008, MIR '08.

[17]  P. Jaccard.  THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE.1 , 1912 .

[18]  K. J. Ray Liu,et al.  Temporal Forensics and Anti-Forensics for Motion Compensated Video , 2012, IEEE Transactions on Information Forensics and Security.

[19]  Davide Cozzolino,et al.  Video forgery detection and localization based on 3D patchmatch , 2015, 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[20]  A. Piva,et al.  overview paper An overview on video forensics , 2012 .

[21]  Paolo Bestagini,et al.  Near-duplicate detection and alignment for multi-view videos , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[22]  Anderson Rocha,et al.  Video Phylogeny: Recovering near-duplicate video relationships , 2011, 2011 IEEE International Workshop on Information Forensics and Security.

[23]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[24]  Paolo Bestagini,et al.  Phylogenetic analysis of near-duplicate and semantically-similar images using viewpoint localization , 2016, 2016 IEEE International Workshop on Information Forensics and Security (WIFS).