(49-6) 25 * << * >> * Russian * English * Content * All Issues

MIDV-DM: A Document-Oriented Dataset for Image Manipulation Detection and Localization
A.V. Chuiko 1,2, I.A. Kunina 1,2, S.A. Usilin 1,2, C. Chen 3, S. Tan 3, D.P. Nikolaev 1,2, V.V. Arlazarov 1,2

1 Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences,
Prospekt 60-letiia Oktiabria 9, Moscow, 119333, Russia;
2 Smart Engines Service LLC,
Prospekt 60-letiia Oktiabria 9, Moscow, 117312, Russia;
3 Shenzhen MSU-BIT University (SMBU),
Shenzhen, Guangdong, China

 PDF, 2622 kB

DOI: 10.18287/COJ1768

Pages: 1093-1101.

Full text of article: English language.

Abstract:
As the scope of application of document recognition systems in business processes increases, so does the number of attacks on these systems. One form of such attacks could involve software for manipulating a digital image of a document. The development of methods for image manipulation detection and localization is complicated with the fact that available datasets neither contain images of documents nor lack diversity in capture conditions and document types. Furthermore, these datasets do not cover the range of possible kinds of manipulations that occur under natural conditions. In this paper, we introduce MIDV-DM – a publicly available benchmark designed for the development and testing of methods aimed at detecting and localizing manipulations in identity document images. It contains images subjected to eight types of manipulations, which we have conceptually categorized based on our analysis of over 2000 real-world fraud attempts. In total, MIDV-DM contains 1000 original document images from the public MIDV-2020 dataset and 8000 automatically created manipulated images based on them, along with the ground truth masks and annotations. The paper also describes the process of obtaining baseline quality based on the IML-ViT model. The authors believe that MIDV-DM will open new opportunities for researchers to advance technologies for document image authenticity analysis.

Keywords:
image manipulation detection, document forgery, copy-move, splicing, visible watermark, image forensic, document images, benchmark dataset.

Citation:
Chuiko AV, Kunina IA, Usilin SA, Chen C, Tan S, Nikolaev DP, Arlazarov VV. MIDV-DM: A Document-Oriented Dataset for Image Manipulation Detection and Localization. Computer Optics 2025; 49(6): 1093-1101. DOI: 10.18287/COJ1768.

References:
  1. Matalov D P, Usilin S A, Arlazarov V V. Modification of the Viola-Jones approach for the detection of the government seal stamp of the Russian Federation. In: Proc Int Conf Machine Vision (ICMV) 2018; SPIE; 2019. Vol. 11041: 110411Y-1-110411Y-7. DOI: 10.1117/12.2522793.
  2. Polevoy D V, Panfilova E I, Nikolaev D P. White balance correction for detection of holograms in color images of black and white photographs [In Russian]. Inform Techn Comput Syst 2021; (3): 82-95. DOI: 10.14357/20718632210308.
  3. Kada O, Kurtz C, van Kieu C, Vincent N. Hologram detection for identity document authentication. In: El Yacoubi M, Granger E, Yuen P C, Pal U, Vincent N, eds. Pattern Recognition and Artificial Intelligence. Cham: Springer; 2022: 346-357. DOI: 10.1007/978-3-031-09037-0_29.
  4. Chernyshova Y S, Aliev M A, Sheshkus A V. Optical font recognition of images captured with mobile devices and its application for detecting identity documents forgery [In Russian]. Trudy ISA RAN 2018; 68(S1): 183-191. DOI: 10.14357/20790279180521.
  5. Ma X, Zhu X, Su L, Du B, Jiang Z, Tong B, et al. IMDL-BenCo: A comprehensive benchmark and codebase for image manipulation detection & localization. arXiv preprint arXiv:2406.10580 (2024).
  6. Verma M, Singh D. Survey on image copy-move forgery detection. Multimed Tools Appl 2024; 83: 23761-23797. DOI: 10.1007/s11042-023-16455-x.
  7. Barglazan A-A, Brad R, Constantinescu C. Image inpainting forgery detection: A review. J Imaging 2024; 10(2): 42. DOI: 10.3390/jimaging10020042.
  8. Tralic D, Zupancic I, Grgic S, Grgic M. CoMoFoD — new database for copy-move forgery detection. In: Proc ELMAR; 2013: 49-54.
  9. Amerini I, Ballan L, Caldelli R, Del Bimbo A, Serra G. A SIFT-based forensic method for copy–move attack detection and transformation recovery. IEEE Trans Inf Forensics Secur 2011; 6(3): 1099-1110. DOI: 10.1109/TIFS.2011.2129512.
  10. Dong J, Wang W, Tan T. CASIA image tampering detection evaluation database. In: Proc IEEE China Summit & Int Conf Signal Inf Process; 2013: 422-426. DOI: 10.1109/ChinaSIP.2013.6625374.
  11. Wen B, Zhu Y, Subramanian R, Ng T-T, Shen X, Winkler S. COVERAGE — a novel database for copy-move forgery detection. In: Proc IEEE Int Conf Image Process (ICIP); 2016: 161-165. DOI: 10.1109/ICIP.2016.7532339.
  12. Mahfoudi G, Morain-Nicolier F, Retraint F, Pic M. CMID: A new dataset for copy-move forgeries on ID documents. In: Proc IEEE Int Conf Image Process (ICIP); 2021: 3028-3032. DOI: 10.1109/ICIP42928.2021.9506723.
  13. Sidere N, Cruz F, Coustaty M, Ogier J-M. A dataset for forgery detection and spotting in document images. In: Proc Int Conf Emerging Security Technologies (EST); 2017: 26-31. DOI: 10.1109/EST.2017.8090394.
  14. Al-Ghadi M, Ming Z, Gomez-Krämer P, Burie J-C, Coustaty M, Sidere N. Guilloche detection for ID authentication: A dataset and baselines. In: Proc IEEE Int Workshop Multimedia Signal Process (MMSP); 2023: 1-6. DOI: 10.1109/MMSP59012.2023.10337681.
  15. Bulatov K B, Emelyanova E V, Tropin D V, Skoryukina N S, Chernyshova Y S, Sheshkus A V, et al. MIDV-2020: A comprehensive benchmark dataset for identity document analysis. Comput Opt 2022; 46(2): 252-270. DOI: 10.18287/2412-6179-CO-1006.
  16. Ma X, Du B, Jiang Z, Du X, Al Hammadi A Y, Zhou J. IML-ViT: Benchmarking image manipulation localization by vision transformer. arXiv preprint arXiv:2307.14863 (2024)
    .

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20