Abstract
In this paper, we present a model for the fraud detection of documents, using the texture of the paper on which they are printed. Different from prior studies, we present a data generation process through which we generate a dataset of papers and propose a deep learning model based on Siamese networks that is trained with samples from the dataset to reliably detect fraud from the original. Toward this end, we introduced a new regularization parameter for the training that would reduce the likelihood of the network making a Type-II error (i.e., classifying a fraud document as original), while being more tolerant of Type-I error (i.e., classifying an original document as fraud). Our analysis has shown that, combined with a Meta Learner, the proposed model can provide better fraud detection performance than that obtained with the Local Binary Pattern method, Prototypical Networks, and Matching Networks as the baseline.
Similar content being viewed by others
Availability of data and materials
The raw dataset containing scanned paper textures and its augmented version publicly available along with the augmentation scripts is publicly available at https://github.com/ezgiekiz/fraud-detection-paper
References
Buchanan, J.D., Cowburn, R.P., Jausovec, A.-V., Petit, D., Seem, P., Xiong, G., Atkinson, D., Fenton, K., Allwood, D.A., Bryan, M.T.: Fingerprinting documents and packaging. Nature 436(7050), 475–475 (2005)
Clarkson, W., Weyrich, T., Finkelstein, A., Heninger, N., Halderman, J.A., Felten, E.W.: Fingerprinting blank paper using commodity scanners. In: Symposium on Security and Privacy , pp. 301–314. IEEE, (2009)
Sharma, A., Subramanian, L., Brewer, E.A.: Paperspeckle: microscopic fingerprinting of paper. In: Proceedings of the 18th ACM Conference on Computer and communications security, pp. 99–110, (2011)
Chen, D., Hu, Q., Zeng, S.: An anti-counterfeiting method of high security and reliability based on unique internal fiber pattern of paper. In: International Conference on Anti-counterfeiting, Security, and Identification (ASID), pp. 174–178. IEEE, (2020)
Kauba, C., Debiasi, L., Schraml, R., Uhl, A.: Towards drug counterfeit detection using package paperboard classification. In: Pacific Rim Conf. on Multimedia, pp. 136–146. Springer, (2016)
Sharma, A., Srinivasan, V., Kanchan, V., Subramanian, L.: The fake vs real goods problem: microscopy and machine learning to the rescue. In: Proceedings of the 23rd ACM sigkdd international conference on knowledge discovery and data mining, pp. 2011–2019, (2017)
Toreini, E., Shahandashti, S.F., Hao, F.: Texture to the rescue: Practical paper fingerprinting based on texture patterns. ACM Trans. Privacy & Security 20(3), 1–29 (2017)
Wong, C.-W., Wu, M.: Counterfeit detection using paper puf and mobile cameras. In: Int. WS on Information Forensics and Security, pp. 1–6. IEEE, (2015)
Liu, R., Wong, C.-W., Wu, M.: Enhanced geometric reflection models for paper surface based authentication. In: International Workshop on Information Forensics and Security (WIFS), pp. 1–7. IEEE, (2018)
Guarnera, F., Allegra, D., Giudice, O., Stanco, F., Battiato, S.: A new study on wood fibers textures: documents authentication through LBP fingerprint. In: International Conference on Image Processing (ICIP) , pp. 4594–4598. IEEE, (2019)
Guarnera, F., Giudice, O., Allegra, D., Stanco, F., Battiato, S., Livatino, S., Matranga, V., Salici, A.: A robust document identification framework through FBP fingerprint. J. Imag. 7(8), 126 (2021)
Pham, T.Q., Perry, S.W., Fletcher, P.A., Ashman, R.: Paper fingerprinting using alpha-masked image matching. IET Comput. Vision 5(4), 232–243 (2011)
Berchtold, W., Sütter, M., Steinebach, M.: Fingerprinting blank paper and printed material by smartphones. Electronic Imaging, 298–1 (2021)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708. (2017)
Wang, J., Song, Y., Leung, T., Rosenberg, C., Wang, J., Philbin, J., Chen, B., Wu, Y.: Learning fine-grained image similarity with deep ranking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1386–1393. (2014)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. AdV. Neural Inform. Process. Syst.29 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. Adv. Neural Inform. Process. Syst. 30 (2017)
https://github.com/boyuanjiang/matching-networks-pytorch last access: 02.03.2023
https://github.com/orobix/prototypical-networks-for-few-shot-learning-pytorch last access: 02.03.2023
Funding
This study is partially supported by METU-ROMER (Center for Robotics and AI) infrastructure
Author information
Authors and Affiliations
Contributions
EEE conducted the experimental studies. FTYV and E.Ş. guided the work. All authors contributed to the writing of the manuscript text.
Corresponding author
Ethics declarations
Ethical approval
Not Applicable
Conflict of interest
The authors declare no competing interests
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Emiroğlu, E.E., Şahin, E. & Vural, F.T.Y. Fraud detection from paper texture using Siamese networks. SIViP 17, 3369–3376 (2023). https://doi.org/10.1007/s11760-023-02558-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02558-3