Fraud detection from paper texture using Siamese networks


Emiroğlu E. E., ŞAHİN E., Vural F. T. Y.

Signal, Image and Video Processing, vol.17, no.7, pp.3369-3376, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 17 Issue: 7
  • Publication Date: 2023
  • Doi Number: 10.1007/s11760-023-02558-3
  • Journal Name: Signal, Image and Video Processing
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, zbMATH
  • Page Numbers: pp.3369-3376
  • Keywords: Fraud detection, Hypothesis testing, Image matching, Siamese networks
  • Middle East Technical University Affiliated: Yes

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.