6th International Young Scientist Congress (IYSC-2020) will be Postponed to 8th and 9th May 2021 Due to COVID-19. 10th International Science Congress (ISC-2020).  International E-publication: Publish Projects, Dissertation, Theses, Books, Souvenir, Conference Proceeding with ISBN.  International E-Bulletin: Information/News regarding: Academics and Research

Forensic approach for detecting the region of Copy-Create video forgery by applying frame similarity approach

Author Affiliations

  • 1Department of Computer Applications, Basaveshwar Engineering College, Bagalkot, India
  • 2Department of Computer Science & Engineering, Maharaja Institute of Technology, Mysore, India
  • 3Department of Computer science & Engineering, KLE Institute of Technology, Hubli, India

Res. J. Computer & IT Sci., Volume 7, Issue (2), Pages 12-17, December,20 (2019)

Abstract

Now a day′s videos are living in the heart of the modern communication world. Every one socio living being in this world uses videos are parts of social media like Whats-app, Facebook, Instagram, and Twitter. However, the problem persists the trustworthiness of those video published in the media world. Due to high-end open source free video editing software are readily available for editing the source video and modifying the content of the video becomes simpler. In forensically a part of media information copied and pasted in the same or another footage without changing the source of information is called it as copy-create forgery techniques. At presently some researcher found the methods in both active and passive forgery techniques those are all focusing on hardware embedded and high processing detection with the lowest accuracy and executed by considering minimal parameters which are becoming a bottleneck for the unique solution. Now we are proposing techniques with the help of necessary video vision processing to identify the forged region with extracting necessary information and applying the backtrack methods for investigation method to detect the forged part and authenticating the source of the video. We are proposing concepts and implementation by considering the region of interest parameter by visualizing and analyzing the very basic pixel mapping along with block matching of a group of pictures converted by forged video along with source information. We are taking the statistical mean frame of each forged frame along with color channels and deducing and mapping with each block and generating a forged region of copy-create forged video. We are using forensically standard forgery data set created by Surrey University as SULPA and its parser dataset REWIND with customizing with the help of visionary parameter for testing the result. We succeeded 96% for accuracy and precession of the result. We also got the excellent accuracy in other standard dataset YTD and SYSU-OBJ-FORGE dataset.

References

  1. Al-Sanjary O.I., Ahmed A.A., Jaharadak A.A.B., Ali M.A. and Zangana H.M. (2018)., Detection clone an object movement using an optical flow approach., In 2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), 388-394. IEEE. doi: 10.1109/ISCAIE.2018.8405504
  2. Jia S., Xu Z., Wang H., Feng C. and Wang T. (2018)., Coarse-to-fine copy-move forgery detection for video forensics., IEEE Access, 6, 25323-25335. doi: 1109/ACCESS.2018.2819624
  3. Üstübıoğlu B., Ulutaş G., Nabıyev V.V., Ulutas M. and Üstübıoğlu A. (2018)., Using correlation matrix to detect frame duplication forgery in videos., 26th Signal Processing and Communications Applications Conference (SIU), Izmir, 1-4. doi: 10.1109/SIU.2018.840436 4
  4. Su L., Li C., Lai Y. and Yang J. (2017)., A fast forgery detection algorithm based on exponential-Fourier moments for video region duplication., IEEE Transactions on Multimedia, 20(4), 825-840. April 2018 doi: 10.1109/TMM.2017.2760098.
  5. Verde S., Bondi L., Bestagini P., Milani S., Calvagno G. and Tubaro S. (2018)., Video Codec Forensics Based on Convolutional Neural Networks., 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece, 2018, 530-534. doi: 10.1109/ICIP.2018.8451143
  6. Feng C., Xu Z., Jia S., Zhang W. and Xu Y. (2016)., Motion-Adaptive Frame Deletion Detection for Digital Video Forensics., in IEEE Transactions on Circuits and Systems for Video Technology, 27(12), 2543-2554, Dec. 2017. doi: 10.1109/TCSVT.2016.2593612 .
  7. Huang C.C., Zhang Y. and Thing V.L. (2017)., Inter-frame video forgery detection based on multi-level subtraction approach for realistic video forensic applications., IEEE 2nd International Conference on Signal and Image Processing (ICSIP), Singapore, 2017, 20-24. doi: 10.1109/SIPROCESS.2017.8124498.
  8. Sitara K. and Mehtre B.M. (2017)., A comprehensive approach for exposing inter-frame video forgeries., In 2017 IEEE 13th International Colloquium on Signal Processing & its Applications (CSPA), 73-78. IEEE. doi:1109/CSPA.2017.8064927.
  9. Xu J., Liang Y., Tian X. and Xie A. (2016)., A novel video inter-frame forgery detection method based on histogram intersection., In 2016 IEEE/CIC international conference on communications in China (ICCC), 1-6. IEEE. doi: 10.1109/ICCChina.2016.7636851
  10. Mathai M., Rajan D. and Emmanuel S. (2016)., Video forgery detection and localization using normalized cross-correlation of moment features., 2016 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), Santa Fe, NM, 149-152. doi: 10.1109/SSIAI.2016.7459197.
  11. Chittapur G.B., Murali S., Prabhakara H.S. and Anami B.S. (2014)., Exposing Digital Forgery in Video by Mean Frame Comparison Techniques., In: Sridhar V., Sheshadri H., Padma M. (eds) Emerging Research in Electronics, Computer Science and Technology. Lecture Notes in Electrical Engineering, 248. Springer, New Delhi
  12. Murali S., Chittapur G.B. and Prabhakara H.S. (2013)., Detection of Digital Photo Image Forgery Using Copy-Create Techniques., In: S M., Kumar S. (eds) Proceedings of the Fourth International Conference on Signal and Image Processing 2012 (ICSIP 2012). Lecture Notes in Electrical Engineering, 221. Springer, India doi: 10.1007/978-81-322-0997-3_26.
  13. Murali S., Chittapur Govindraj S., Prabhakara H. and Anami Basavaraj (2013)., Comparison and analysis of photo. image forgery detection techniques., doi:10.5121/ijcsa.2012.2605.
  14. Chen S., Tan S., Li B. and Huang J. (2015)., Automatic detection of object-based forgery in advanced video., IEEE Transactions on Circuits and Systems for Video Technology, 26(11), 2138-2151.. 26.1-1.10.1109/TCSVT. 2015.2473436.
  15. Qadir G., Yahaya S. and Ho A.T. (2012)., Surrey university library for forensic analysis (SULFA) of video content., Insert Name of Site in Italics. N.p., n.d. Web. 21 Jul. 2019 http://sulfa.cs.surrey.ac.uk/.
  16. REWIND Video: Copy-move Forgeries Dataset - Rewind Project. (2019). Retrieved from https:// sites.google.com/ site/rewindpolimi/downloads/datasets/video-copy-move-fo, undefined, undefined
  17. Al-Sanjary O.I., Ahmed A.A. and Sulong G. (2016)., Development of a video tampering dataset for forensic investigation., Forensic science international, 266, 565-572. 10.1016/j.forsciint.2016.07.013.
  18. Andy S. and Haikal A. (2017)., Simple duplicate frame detection of MJPEG codec for video forensic., 2nd International conferences on Information Technology, Information Systems and Electrical Engineering (ICITISEE), Yogyakarta, 321-324. doi: 10.1109/ ICITISEE.2017.8285520