Artificial intelligence

Scientific journal

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Search by:

Year of publication
Author name
Paper title

Comprehensive digital image analysis to detect manipulation

Dreshpak V.1, Prokopovych-Tkachenko D.2, Rybalchenko L.3
1 University of Customs and Finance
2 University of Customs and Finance
3 University of Customs and Finance
dreshpak.ucf@gmail.com; omega2417@gmail.com
https://orcid.org/0000-0001-9802-3769https://orcid.org/0000-0002-6590-3898https://orcid.org/0000-0003-0413-8296

Full text (PDF)

UDC: 004.62; 004.8; 004.94
Publication Language: English
Stuc. intelekt. 2025; 30(1):77-83

Abstract: Comprehensive digital image analysis plays an important role in modern digital forensics and cybersecurity, as it allows detecting fakes, tampering and hidden traces of editing in photographs or other visual data. These methods can be used by OSINT (Open Source Intelligence) specialists and investigative journalists to detect fakes and counter-propaganda. This article describes a scientific and methodological approach aimed at detecting manipulations in digital images based on a combination of various algorithms and data processing technologies. The article considers contour and gradient analysis (Kenny's method), detection of editing traces through metadata analysis (EXIF), Error Level Analysis (ELA), as well as spectral and wavelet analysis. Based on a systematic review of the results of applying these methods to a sample of different types of images, it is demonstrated that comprehensive analysis has significant advantages over the use of individual methods, as it allows for the fullest possible identification of potential traces of manipulation, including copying and pasting of fragments, digital artefacts from excessive compression, and inconsistencies in the internal structures of images. The article contains a description of the methodology, including the necessary mathematical models, which allows us to generalise and formalise the analysis procedure. The results of the study confirm the high accuracy and reliability of the proposed approach. Recommendations for the practical use of complex digital image analysis in the fields of forensic science, media, cyberattack investigations and intellectual property protection are proposed, and promising areas for further research in this area are outlined.

Keywords: image manipulation, digital analysis, integrated approach, counterfeit detection, cybersecurity, fraud.

References:

  1. H. Farid. Image Forgery Detection: A Survey. IEEE Signal Processing Magazine, 26(2), 2009, p.16-25.
  2. W. Stallings. Cryptography and Network Security: Principles and Practice. 8th ed. Pearson, 2018.
  3. C. M. Pun, X. C. Yuan. Digital Image Forgery Detection Using Discrete Wavelet Transform. Optical Engineering, 47(5), 2008, 057007.
  4. T. Ng, S. F. Chang. A Model for Image Splicing. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), 2004, pp. 1169- 1172.
  5. P. K. Gupta, R. Kaushal. Analysis of Image Forgery Detection Techniques: A Comprehensive Review. Artificial Intelligence Review, 54, 2021, pp. 4421-4460.
  6. H. Liu, X. Li. Image Forgery Localization Based on Multi-Scale Convolutional Neural Networks. IEEE Transactions on Information Forensics and Security, 13(5), 2018, pp. 1230-1244.
  7. R. C. Gonzalez, R. E. Woods. Digital Image Processing. 4th ed. Pearson, 2018.
  8. R. Wolf. Modern JPEG Forensics and ELA Testing. Journal of Digital Investigation, 3(2), 2007, pp. 89-97.
  9. I. Amerini, L. Ballan, R. Caldelli et al. A SIFT-based Forensic Method for CopyMove Attack Detection and Transformation Recovery. IEEE Transactions on Information Forensics and Security, 6(3), 2011, pp. 1099- 1110.
  10. B. Mahdian, S. Saic. Methods for Blind Image Forgery Detection: A Survey. Signal Processing, 89(9), 2009, pp. 2286-2300.
  11. J. Wen, F. Gao, X. He, Y. Chu. An Improved Error Level Analysis Method for Image Forensics. In: Proceedings of the 2020 IEEE International Workshop on Information Forensics and Security (WIFS), 2020, pp. 1-6.
  12. J. Fridrich, D. Soukal, J. Lukáš. Detection of Copy-Move Forgery in Digital Images. In: Proc. of Digital Forensic Research Workshop, 2003, pp. 1-10.
  13. W. Li, Y. Yuan. Detection of Copy-move Forgery in Digital Images. 9th International Conference on Signal Processing, 2008, pp. 1-4.
  14. H. Farid. Digital Image Ballistics from JPEG Quantization: A Followup Study. Technical Report TR2008 647, Dartmouth College, 2008.
  15. J. Krawetz. Picture Anomaly Detection in Forensic Analysis. Embedded.com, 2007. (Online resource).
  16. S. Bayram, H. T. Sencar, N. Memon. An Efficient and Robust Method for Detecting CopyMove Forgery. In: IEEE Transactions on Information Forensics and Security, 2(3), 2009, pp. 461-474.
  17. D. Cozzolino, G. Poggi, L. Verdoliva. Efficient Dense-Field Copy-Move Forgery Detection. IEEE Transactions on Information Forensics and Security, 10(11), 2015, pp. 2284-2297.
  18. J. H. Bappy, A. K. Roy-Chowdhury, J. Bunk, L. Nataraj, B. S. Manjunath. Exploiting Spatial Structure for Localizing Manipulated Image Regions. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4970-4979.
  19. H. Chai, L. T. Yang, X. Zhu. Detection of Region Duplication Forgery in Digital Image Using Gabor Filter and Reduced Dimensional SVD. In: Journal of Applied Mathematics & Information Sciences, 5(2), 2011, pp. 343- 352.
  20. Z. Wu, Y. Yang. Image Splicing Detection via Interchangeable Domain Knowledge. ACM Transactions on Multimedia Computing, Communications, and Applications, 14(2s), 2018, pp. 1-22.
  21. X. Bao, D. Zhang, G. Liu. A Review of Reliable Image Forgery Detection Approaches. ACM Computing Surveys, 49(2), 2016, Article 27.
  22. W. Li, M. Fang, J. Liu. Wavelet-based Image Forensics for Splicing Detection. Pattern Recognition Letters, 125, 2019, pp. 324-331.
  23. G. Bradski, A. Kaehler. Learning OpenCV 3: Computer Vision in

View full text (PDF)