Optimization of Romanian Identity Documents Processing

Milașcon, Delia-Victoria; Constantinescu, Constantin; Brad, Raluca

doi:10.2478/ijasitels-2025-0012

Abstract

This paper presents the development of an application based on computer vision and deep learning aimed at the automatic recognition of data from Romanian national identity documents. Its primary goal is to optimize the processing of such documents within public and private institutions. Developing such a system involves several challenges. These include the variability in the visual appearance of documents caused by wear and tear, scanning angles, camera quality, and ambient lighting conditions; the difficulty of accurately recognizing Romanian diacritics; and the correct identification of textual fields based on their positioning within the document. The system must be sufficiently robust to adapt to these variations while maintaining a high level of accuracy.

References

European Commission, eIDAS 2.0 Regulation, EU 2024/1183, Official Journal of the EU, April 2024.
Search in Google Scholar Back to article
Ministerul Investițiilor și Proiectelor Europene, Planul Național de Redresare și Reziliență Componenta C7: Transformare Digitală, 2025 Update.
Search in Google Scholar Back to article
*, European Payments Council, 2025 Fraud Report, Brussels, October 2025.
Search in Google Scholar Back to article
*, Eurostat, Digital Economy and Society Index (DESI), Romania 2025, Publications Office of the EU.
Search in Google Scholar Back to article
*, BCR Internal Audit Report, AI-OCR Deployment Results Q3 2025, Bucharest, September 2025.
Search in Google Scholar Back to article
Zhao Y., Lv W., Xu S., Wei J., Wang G., Dang Q., Liu Y., DETRs Beat YOLOs on Real-time Object Detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16965–16974, ISBN 978-1-6654-6547-0, Vancouver, Canada, 2024
Search in Google Scholar Back to article
Pfitzmann B., Auer C., Dolfi M., Nassar A.S., Staar P., DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis, Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2860–2870, ISBN 978-1-4503-9232-0, Washington DC, USA, 2022.
Search in Google Scholar Back to article
https://ubiai.tools/the-role-of-layoutlmv3-in-document-layout-understanding/, accessed 4.11.2025
Search in Google Scholar Back to article
Huang Y., Lv T., Cui L., Lu Y., Wei F, LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking, Proceedings of the 30th ACM International Conference on Multimedia (MM), 4083–4092, ISBN 978-1-4503-9203-0, Lisboa, Portugal, 2022.
Search in Google Scholar Back to article
Nguyen-Trong, Khanh. “An End-to-End Method to Extract Information from Vietnamese ID Card Images.” International Journal of Advanced Computer Science and Applications 13, no. 3 ( 2022 ).
Search in Google Scholar Back to article
Satyawan, W., Pratama, M. O., Jannati, R., Muhammad, G., Fajar, B., Hamzah, H., ... & Kristian, K. (2019, June). Citizen ID card detection using image processing and optical character recognition. In Journal of physics: Conference series (Vol. 1235, No. 1, p. 012049). IOP Publishing
Search in Google Scholar Back to article
Li H., Wang Y., Chen Y., Liu Z. Foreground and Text-lines Aware Document Image Rectification, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 19574–19583, ISSN 2380-7504, Paris, France, 2023.
Search in Google Scholar Back to article
Li, M., Lv, T., Chen, J., Cui, L., Lu, Y., Florencio, D., Zhang, C., Li, Z., Wei, F, TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models, Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 13094-13102, ISSN 2374-3468, Washington DC, USA, 2023.
Search in Google Scholar Back to article
Low, L. M., Salleh, F. H. M., Law, Y. F., & Zakaria, N. Z. (2024). Detecting and recognizing seven segment digits using a deep learning approach. In ITM Web of Conferences (Vol. 63, p. 01007). EDP Sciences.
Search in Google Scholar Back to article
Tan, Z., Zhou, J., & Liu, Y. (2023, August). CRNN-based abstract artistic text recognition. In 2023 IEEE Smart World Congress (SWC) (pp. 652-659). IEEE.
Search in Google Scholar Back to article
Smith, R. (2007, September). An overview of the Tesseract OCR engine. In Ninth international conference on document analysis and recognition (ICDAR 2007) (Vol. 2, pp. 629-633). IEEE.
Search in Google Scholar Back to article
Deng, G., & Cahill, L. W. (1993, October). An adaptive Gaussian filter for noise reduction and edge detection. In 1993 IEEE conference record nuclear science symposium and medical imaging conference (pp. 1615-1619). IEEE.
Search in Google Scholar Back to article
Rong, W., Li, Z., Zhang, W., & Sun, L. (2014, August). An improved CANNY edge detection algorithm. In 2014 IEEE international conference on mechatronics and automation (pp. 577-582). IEEE.
Search in Google Scholar Back to article
Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., & Liang, J. (2017). East: an efficient and accurate scene text detector. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (pp. 5551-5560).
Search in Google Scholar Back to article

Optimization of Romanian Identity Documents Processing

Abstract

Paradigm

My account