{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:38:20Z","timestamp":1758083900679,"version":"3.44.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046260"},{"type":"electronic","value":"9783032046277"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04627-7_35","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:07:59Z","timestamp":1757988479000},"page":"605-619","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MIDV-UP: A Dataset of Pakistani and\u00a0Iranian ID Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9520-3278","authenticated-orcid":false,"given":"Yulia S.","family":"Chernyshova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7744-3991","authenticated-orcid":false,"given":"Daniil A.","family":"Ilyukhin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3260-9104","authenticated-orcid":false,"given":"Vladimir V.","family":"Arlazarov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"35_CR1","doi-asserted-by":"publisher","unstructured":"Al-Ghadi, M., Ming, Z., Gomez-Kramer, P., Burie, J., Coustaty, N., Sidere, N.: Guilloche detection for id authentication: a dataset and baselines. In: 2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP), pp.\u00a01\u20136 (2023). https:\/\/doi.org\/10.1109\/MMSP59012.2023.10337681","DOI":"10.1109\/MMSP59012.2023.10337681"},{"issue":"3","key":"35_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.14357\/20790279220301","volume":"72","author":"VV Arlazarov","year":"2022","unstructured":"Arlazarov, V.V.: Problems and features of 2D, 3D, and 4D identity document recognition systems. Trudy ISA RAN (Proceedings of ISA RAS) 72(3), 3\u20139 (2022). https:\/\/doi.org\/10.14357\/20790279220301","journal-title":"Trudy ISA RAN (Proceedings of ISA RAS)"},{"key":"35_CR3","doi-asserted-by":"publisher","unstructured":"Arlazarov, V.V., Bulatov, K., Chernov, T., L, A.V.: MIDV-500: a dataset for identity document analysis and recognition on mobile devices in video stream. Comput. Optics 43(5), 818\u2013824 (2019). https:\/\/doi.org\/10.18287\/2412-6179-2019-43-5-818-824","DOI":"10.18287\/2412-6179-2019-43-5-818-824"},{"key":"35_CR4","doi-asserted-by":"publisher","first-page":"10","DOI":"10.14357\/20718632220302","volume":"3","author":"VV Arlazarov","year":"2022","unstructured":"Arlazarov, V.V.: Analysis of the usage of problem-oriented datasets in scientific research. ITiVS 3, 10\u201323 (2022). https:\/\/doi.org\/10.14357\/20718632220302","journal-title":"ITiVS"},{"key":"35_CR5","unstructured":"Asadi, A.A.: Shotor dataset (2020). https:\/\/www.kaggle.com\/amir137825\/persian ocrdataset\/version\/2"},{"key":"35_CR6","doi-asserted-by":"publisher","unstructured":"Awal, A.M., Ghanmi, N., Sicre, R., Furon, T.: Complex document classification and localization application on identity document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol.\u00a001, pp. 426\u2013431 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.77","DOI":"10.1109\/ICDAR.2017.77"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) Computer Vision \u2013 ECCV 2006, pp. 404\u2013417. Springer Berlin Heidelberg, Berlin, Heidelberg (2006)","DOI":"10.1007\/11744023_32"},{"key":"35_CR9","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1038\/s41597-024-04160-9","volume":"11","author":"C Boned","year":"2024","unstructured":"Boned, C., Talarmain, M., Ghanmi, N.: Synthetic dataset of id and travel documents. Sci. Data 11, 1356 (2024). https:\/\/doi.org\/10.1038\/s41597-024-04160-9","journal-title":"Sci. Data"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Bulatov, K., Matalov, D., Arlazarov, V.V.: MIDV-2019: challenges of the modern mobile-based document OCR. ICMV 2019, SPIE 11433 (2020)","DOI":"10.1117\/12.2558438"},{"issue":"2","key":"35_CR11","doi-asserted-by":"publisher","first-page":"252","DOI":"10.18287\/2412-6179-CO-1006","volume":"46","author":"K Bulatov","year":"2022","unstructured":"Bulatov, K., et al.: MIDV-2020: a comprehensive benchmark dataset for identity document analysis. Comput. Opt. 46(2), 252\u2013270 (2022)","journal-title":"Comput. Opt."},{"key":"35_CR12","doi-asserted-by":"publisher","unstructured":"Bulatov, K., Arlazarov, V.V., Chernov, T., Slavin, O., Nikolaev, D.: Smart IDReader: document recognition in video stream. In: ICDAR 2017. vol.\u00a06, pp. 39\u201344. Institute of Electrical and Electronics Engineers Inc. (IEEE), Manhattan, New York, U.S. (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.347","DOI":"10.1109\/ICDAR.2017.347"},{"key":"35_CR13","doi-asserted-by":"publisher","unstructured":"Chazalon, J., et al.: Bid dataset: a challenge dataset for document processing tasks. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 4, pp. 11\u201316 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.306","DOI":"10.1109\/ICDAR.2017.306"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Chernyshova, Y.S., Emelianova, E.V., Sheshkus, A.V., Arlazarov, V.V.: MIDV-LAIT: a challenging dataset for recognition of ids with Perso-Arabic, Thai, and Indian scripts. ICDAR 2021, Springer Nature Group, Lecture Notes in Computer Science (LNCS), vol. 12822 (2021)","DOI":"10.1007\/978-3-030-86331-9_17"},{"key":"35_CR15","unstructured":"Dutta, A., Gupta, A., Zisserman, A.: VGG Image Annotator (VIA). https:\/\/www.robots.ox.ac.uk\/~vgg\/software\/via\/. Accessed 05 Mar 2025"},{"key":"35_CR16","doi-asserted-by":"publisher","unstructured":"Guan, H., et al.: IDNet: a novel identity document dataset via few-shot and quality-driven synthetic data generation. In: 2024 IEEE International Conference on Big Data (BigData) (2024). https:\/\/doi.org\/10.1109\/BigData62323.2024.10825017","DOI":"10.1109\/BigData62323.2024.10825017"},{"key":"35_CR17","unstructured":"Hosseini, F., kashef, S., Shabaninia, E., Nezamabadi-pour, H.: IDPL-PFOD an image dataset of printed Farsi text for Farsi OCR research, pp. 22\u201331 (2023)"},{"key":"35_CR18","doi-asserted-by":"publisher","unstructured":"Koliaskina, L.I.: MIDV-HOLO: a dataset for id document hologram detection in a video stream. ICDAR 2023. Lecture Notes in Computer Science, vol. 14189 (2022). https:\/\/doi.org\/10.1007\/978-3-031-41682-8_30","DOI":"10.1007\/978-3-031-41682-8_30"},{"key":"35_CR19","unstructured":"Lerouge, J., Betmont, G., Bres, T., Stepankevich, E., Berg\u00e8s, A.: DocXPand-25k: a large and diverse benchmark dataset for identity documents analysis (2024). https:\/\/arxiv.org\/abs\/2407.20662"},{"key":"35_CR20","unstructured":"Li, C., et al.: PP-OCRv3: More attempts for the improvement of ultra lightweight OCR system (2022). https:\/\/arxiv.org\/abs\/2206.03001"},{"key":"35_CR21","doi-asserted-by":"publisher","unstructured":"Matalov, D.P., Limonova, E.E., Skoryukina, N.S., Arlazarov, V.V.: RFDOC: memory efficient local descriptors for id documents localization and classification. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. Lecture Notes in Computer Science (LNCS), vol. 12822, pp. 209\u2013224. Springer Nature Group, London, UK (main office) (2021). https:\/\/doi.org\/10.1007\/978-3-030-86331-9_14","DOI":"10.1007\/978-3-030-86331-9_14"},{"key":"35_CR22","doi-asserted-by":"publisher","unstructured":"Ngoc, M.O.V., Fabrizio, J., G\u00e9raud, T.: Saliency-based detection of identity documents captured by smartphones. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 387\u2013392 (2018). https:\/\/doi.org\/10.1109\/DAS.2018.17","DOI":"10.1109\/DAS.2018.17"},{"key":"35_CR23","unstructured":"Paddle OCR: Paddle OCR. https:\/\/github.com\/PaddlePaddle\/PaddleOCR. Accessed 23 Jan 2025"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Polevoy, D., et al.: Document liveness challenge dataset (DLC-2021). J. Imaging. 8(7), 181\u20131\u2013181\u201312 (2022)","DOI":"10.3390\/jimaging8070181"},{"key":"35_CR25","doi-asserted-by":"publisher","unstructured":"Rahman, A., Ghosh, A., Arora, C.: UTRNet: high-resolution Urdu text recognition in printed documents. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) Document Analysis and Recognition - ICDAR 2023, pp. 305\u2013324. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41734-4_19","DOI":"10.1007\/978-3-031-41734-4_19"},{"key":"35_CR26","unstructured":"Rehman, A.U., Hussain, S.U.: Large scale font independent Urdu text recognition system (2020). https:\/\/arxiv.org\/abs\/2005.06752"},{"key":"35_CR27","unstructured":"Sabeti, B., Firouzjaee, H.A., Choobbasti, A.J., Najafabadi, S.M., Vaheb, A.: MirasText: an automatically generated text corpus Forpersian. In: Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"35_CR28","doi-asserted-by":"publisher","unstructured":"Soares, A., Das Neves\u00a0Junior, R., Bezerra, B.: Bid dataset: a challenge dataset for document processing tasks. Workshop De Trabalhos Em Andamento - Conference on graphics, patterns and images (SIBGRAPI) 33, 143\u2013146 (2020). https:\/\/doi.org\/10.5753\/sibgrapi.est.2020.12997","DOI":"10.5753\/sibgrapi.est.2020.12997"},{"key":"35_CR29","doi-asserted-by":"publisher","unstructured":"Su\u00e1rez, I., Sfeir, G., Buenaposada, J.M., Baumela, L.: BEBLID: boosted efficient binary local image descriptor. Pattern Recogn. Lett. 133, 366\u2013372 (2020). https:\/\/doi.org\/10.1016\/j.patrec.2020.04.005, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167865520301252","DOI":"10.1016\/j.patrec.2020.04.005"},{"key":"35_CR30","unstructured":"Tesseract OCR: Tesseract OCR. https:\/\/github.com\/tesseract-ocr\/tesseract. Accessed 23 Jan 2025"},{"key":"35_CR31","doi-asserted-by":"publisher","unstructured":"Torabzadeh, S., Safabaksh, R.: AUT-PFT: a real world printed Farsi text image dataset. In: Proceedings of the International Symposium on Artificial Intelligence and Signal Processing, AISP 2015, pp. 267\u2013272 (2015). https:\/\/doi.org\/10.1109\/AISP.2015.7123490","DOI":"10.1109\/AISP.2015.7123490"},{"key":"35_CR32","doi-asserted-by":"publisher","unstructured":"Tropin, D.V., Ershov, A.M., Nikolaev, D.P., Arlazarov, V.V.: Advanced hough-based method for on-device document localization. Comput. Optics 45(5), 702\u2013712 (2021). https:\/\/doi.org\/10.18287\/2412-6179-CO-895","DOI":"10.18287\/2412-6179-CO-895"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Wu, H., Qian, H., Wu, H., van Moorsel, A.: LDRNet: enabling real-time document localization on mobile devices. In: Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2022, Grenoble, France, September 19\u201323, 2022, Proceedings, Part I, pp. 618\u2013629. Springer (2023)","DOI":"10.1007\/978-3-031-23618-1_42"},{"key":"35_CR34","doi-asserted-by":"publisher","unstructured":"Zingerenko, M.V., Limonova, E.E., Arlazarov, V.V.: Template-based text field segmentation for id documents using dynamic squeezeboxes packing. Multimed. Tools Appl. 1\u201315 (2024). https:\/\/doi.org\/10.1007\/s11042-024-20162-6","DOI":"10.1007\/s11042-024-20162-6"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04627-7_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:08:08Z","timestamp":1757988488000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}