130 likes | 344 Views
Identification of Tamper Detection Techniques for Digital Video Forensics. By Susinda Perera Department of Computer Science and Engineering, University of Moratuwa, Supervised by Dr. Chathura De Silva PhD (NUS-Singapore), MEng (NTU-Singapore), BSc Eng.( Hons ) (Moratuwa)
E N D
Identification of Tamper Detection Techniques for Digital Video Forensics By Susinda Perera Department of Computer Science and Engineering, University of Moratuwa, Supervised by Dr. Chathura De Silva PhD (NUS-Singapore), MEng (NTU-Singapore), BSc Eng.(Hons) (Moratuwa) Senior Lecturer Department of Computer Science and Engineering, University of Moratuwa, 22-10-2011
Problem Statement • Can we trust digital videos? • Are they real, computer generated or tampered • Extract some wanted Information from video • Difficult due to unclearness of video
Can we trust digital videos? Figure 1‑1 : A still from controversial video aired on Channel 4
Video Analysis Softwares • Cognitech • ElecardStreamEye • Ocean Systems dTective • Salient Stills VideoFOCUS • StarWitness • Avid Technology, Inc. • Intergraph Video Analyst • TREC, Inc. • Forevid • MotionDSPIkena • Amped FIVE • Kinesense • Cellforensics(Video Recovery from Mobile Device)
Some Features • Navigation and display of media stream picture-by-picture (I, P, B). • Display of the current frame. • Display of the time, type, size and number of a current frame in a stream, decoding order and offset from the file beginning. • Display of the bit rate (declared in the sequence header) and a calculated bit rate. • Display of a diagram representative average bit rate (moving average). • Display of detailed information about macroblocksin MPEG-1 (ISO/IEC 11172-2), MPEG 2 (ISO/IEC 13818-2), MPEG-4 (ISO/IEC 14496-2) and AVC/H.264 (ISO/IEC 14496-10) video streams. • Frame-accurate positioning. • Display of current frame and its properties: size, type, PTS. • Display of the stream and gathering of statistics relating to the entire file.
Some Features • DeblurFilters • Demultiplexing • DenoiseFilters • Detection Filters • Enhancement • Histogram Editor • Segmentation • Tracking • Transform • Zoom • Velocity • Reconstruction • Photogrammetry
Algorithms/Techniques • Correlation Matching • Line Segment Matching • Motion Segmentation • Shape Matching • Median and Average Frames • Total Variation Denoise • + many more……….
What will be covered in PG dip Project • Study of techniques/algorithms used in commercial video analysis tools • Literature review of video enhancing techniques • Study of different video formats and representation • Literature review of video forensic techniques
in M.Sc. Research Project • Basic video analysis tool • with some number of features (not yet decided) • Identification of a Tamper Detection Techniques for Digital Video Forensics • From the number of possible techniques studied on PG dip literature review
Timeline • Project idea selection and initial literature review • 27 August - 30 September • Literature review on the digital video forensics • 1 October - 14 October • Literature review on video formats (specially MPEG) • 15 October - 21 October • Literature review existing video analysis and forensic tools • 22 October - 28 October • Literature review on theory and algorithms used in above tools • 29 October - 4 November • Literature review on theory and algorithms used in above tools • 5 November - 18 November • Initial implementation of some algorithms • 19 November - 25 November • Submission of PG-Dip project • 26 November - 2 December
Thank you • [1] A.C. Popescu and H. Farid, Statistical Tools for Digital Forensics. 6th Int’l Workshop onInformation Hiding, Toronto, Canada, 2004. • [2] T.-T. Ng, S.-F. Chang, and Q. Sun. Blind detection of photomontage using higher order statistics. In Proceeding of IEEE International Symposium on Circuits and Systems, 2004. • [3] Stamm, M.C.; Liu, K.J.R, Anti-forensics for frame deletion/addition in MPEG video, Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, 2011 • [4] W. Wang and H. Farid . Exposing Digital Forgeries in Video by Detecting Double MPEG Compression. ACM Multimedia and Security Workshop, Geneva, Switzerland, 2006. • [5] Farid, H, Exposing Digital Forgeries in Interlaced and Deinterlaced Video, Information Forensics and Security, IEEE Transactions on, 2007 • [6] ElecardStreamEye Pro [Online] http://www.elecard.com/en/products/professional/analysis/streameye-pro.html • [7] Cognitech Video Investigator [Online] http://www.cognitech.com/?p=151&page=2 • [8] Exposing Digital Forgeries in Video by Detecting Double MPEG Compression [Online] http://www.cs.dartmouth.edu/~csrs/2006/csrs-slides/WeihongWang.pdf • [9]Video Stabilization and Enhancement [Online] http://www.ists.dartmouth.edu/library/354.pdf • [10] Exposing Digital Forgeries in Video by Detecting Duplication [Online] http://www.ists.dartmouth.edu/library/356.pdf • [11] Weihong Wang, "Digital Video Forensics", Ph.D. Thesis, Dartmouth College, Computer Science Department, Hanover, NH, June 2009. [Online] http://www.ists.dartmouth.edu/library/424.pdf