IDTrust: Deep Identity Document Quality Detection with Bandpass Filtering
Abstract: The increasing use of digital technologies and mobile-based registration procedures highlights the vital role of personal identity documents (IDs) in verifying users and safeguarding sensitive information. However, the rise in counterfeit ID production poses a significant challenge, necessitating the development of reliable and efficient automated verification methods. This paper introduces IDTrust, a deep-learning framework for assessing the quality of IDs. IDTrust is a system that enhances the quality of identification documents by using a deep learning-based approach. This method eliminates the need for relying on original document patterns for quality checks and pre-processing steps for alignment. As a result, it offers significant improvements in terms of dataset applicability. By utilizing a bandpass filtering-based method, the system aims to effectively detect and differentiate ID quality. Comprehensive experiments on the MIDV-2020 and L3i-ID datasets identify optimal parameters, significantly improving discrimination performance and effectively distinguishing between original and scanned ID documents.
- āIdentity authentication on mobile devices using face verification and id image recognition,ā Procedia Computer Science, vol. 162, pp. 932ā939, 1 2019.
- āPersonal verification system using thai id card and face photo for cross-age face,ā in ICSEC 2019 - 23rd International Computer Science and Engineering Conference, 10 2019, pp. 325ā330.
- āRecurrent comparator with attention models to detect counterfeit documents,ā in Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 9 2019, pp. 1332ā1337, IEEE Computer Society.
- āMachine learning techniques for identity document verification in uncontrolled environments: A case study,ā in Mexican Conference on Pattern Recognition. 2020, vol. 12088 LNCS, pp. 271ā281, Springer.
- āChecksim: A reference-based identity document verification by image similarity measure,ā in Document Analysis and Recognition ā ICDAR 2021 Workshops. 2021, vol. 12916 LNCS, pp. 422ā436, Springer Science and Business Media Deutschland GmbH.
- Mohamed Sirajudeen and R.Ā Anitha, āForgery document detection in information management system using cognitive techniques,ā Journal of Intelligent & Fuzzy Systems, vol. 39, pp. 8057ā8068, 12 2020.
- āAn efficient method to detect series of fraudulent identity documents based on digitised forensic data,ā Science &\&& Justice, vol. 62, no. 5, pp. 610ā620, 2022.
- āHologram detection for identity document authentication,ā in Pattern Recognition and Artificial Intelligence, MounĆ®m ElĀ Yacoubi, Eric Granger, PongĀ Chi Yuen, Umapada Pal, and Nicole Vincent, Eds., Cham, 2022, pp. 346ā357, Springer International Publishing.
- āAuthentication of holograms with mixed patterns by direct LBP comparison,ā in Proceedings of the International Workshop on MultiMedia Signal Processing (MMSP). IEEE, 2023, pp. 7ā12.
- āA new descriptor for pattern matching: application to identity document verification,ā in Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, 6 2018, pp. 375ā380.
- āCheckScan: a reference hashing for identity document quality detection,ā in 14tā¢hsuperscript14š”ā14^{th}14 start_POSTSUPERSCRIPT italic_t italic_h end_POSTSUPERSCRIPT International Conference on Machine Vision (ICMV 2021), Wolfgang Osten, Dmitry Nikolaev, and Jianhong Zhou, Eds. International Society for Optics and Photonics, 2022, vol. 12084, p. 120840J, SPIE.
- āA system based on intrinsic features for fraudulent document detection,ā in 12tā¢hsuperscript12š”ā12^{th}12 start_POSTSUPERSCRIPT italic_t italic_h end_POSTSUPERSCRIPT International Conference on Document Analysis and Recognition, 2013, pp. 106ā110.
- āPrinted and scanned document authentication using robust layout descriptor matching,ā Multimedia Tools and Applications, 2023.
- āGuilloche detection for ID authentication: A dataset and baselines,ā in Proceedings of the International Workshop on MultiMedia Signal Processing (MMSP). IEEE, 2023, pp. 1ā6.
- āEfficientnet: Rethinking model scaling for convolutional neural networks,ā CoRR, vol. abs/1905.11946, 2019.
- āExtracting color halftones from printed documents using texture analysis,ā Pattern Recognition, vol. 33, no. 3, pp. 445ā463, 2000.
- āVisual enhancement of old documents with hyperspectral imaging,ā Pattern Recognition, vol. 44, no. 7, pp. 1461ā1469, 2011.
- āMidv-2020: A comprehensive benchmark dataset for identity document analysis,ā Computer Optics, vol. 46, pp. 252ā270, 7 2021.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
