{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T04:38:13Z","timestamp":1758083893545,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"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_14","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:08:24Z","timestamp":1757988504000},"page":"244-260","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving OCR Using Internal Document Redundancy"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0535-7246","authenticated-orcid":false,"given":"Diego","family":"Belzarena","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7774-9217","authenticated-orcid":false,"given":"Seginus","family":"Mowlavi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aitor","family":"Artola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7094-9371","authenticated-orcid":false,"given":"Camilo","family":"Mari\u00f1o","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2465-2014","authenticated-orcid":false,"given":"Marina","family":"Gardella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2954-9040","authenticated-orcid":false,"given":"Ignacio","family":"Ram\u00edrez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7885-903X","authenticated-orcid":false,"given":"Antoine","family":"Tadros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4690-4007","authenticated-orcid":false,"given":"Roy","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3606-908X","authenticated-orcid":false,"given":"Natalia","family":"Bottaioli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0969-0389","authenticated-orcid":false,"given":"Boshra","family":"Rajaei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7911-2977","authenticated-orcid":false,"given":"Gregory","family":"Randall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6108-897X","authenticated-orcid":false,"given":"Jean-Michel","family":"Morel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: CVPR, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Baker, S., Matthews, I.: Equivalence and efficiency of image alignment algorithms. In: CVPR, vol.\u00a01, p.\u00a0I. IEEE (2001)","DOI":"10.1109\/CVPR.2001.990652"},{"key":"14_CR3","unstructured":"Berg-Kirkpatrick, T., Durrett, G., Klein, D.: Unsupervised transcription of historical documents. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 207\u2013217 (2013)"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Bluche, T., Messina, R.: Gated convolutional recurrent neural networks for multilingual handwriting recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 646\u2013651. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.111"},{"key":"14_CR5","doi-asserted-by":"publisher","unstructured":"Bottaioli, N., et al.: Normalized vs diplomatic annotation: a case study of automatic information extraction from handwritten Uruguayan birth certificates. In: Mouch\u00e8re, H., Zhu, A. (eds.) ICDAR 2024. LNCS, vol. 14935. pp. 40\u201354. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70645-5_4","DOI":"10.1007\/978-3-031-70645-5_4"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Briand, T., Facciolo, G., S\u00e1nchez, J.: Improvements of the inverse compositional algorithm for parametric motion estimation. Image Process. Line (2018)","DOI":"10.5201\/ipol.2018.222"},{"issue":"10","key":"14_CR7","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.1109\/TSP.2010.2053029","volume":"58","author":"Y Chen","year":"2010","unstructured":"Chen, Y., Wiesel, A., Eldar, Y.C., Hero, A.O.: Shrinkage algorithms for MMSE covariance estimation. IEEE Trans. Signal Process. 58(10), 5016\u20135029 (2010)","journal-title":"IEEE Trans. Signal Process."},{"key":"14_CR8","doi-asserted-by":"publisher","unstructured":"Constum, T., Preel, L., Larcher, T., Paquet, T., Tranouez, P., Br\u00e9e, S.: End-to-end information extraction in handwritten documents: Understanding paris marriage records from 1880 to 1940. In: In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds) ICDAR 2024. LNCS, vol. 14806, pp. 195\u2013214. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70543-4_12","DOI":"10.1007\/978-3-031-70543-4_12"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: DAN: a segmentation-free document attention network for handwritten document recognition. IEEE TPAMI (2023)","DOI":"10.1109\/TPAMI.2023.3235826"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Dijkstra, E.W.: A note on two problems in connexion with graphs. In: Edsger Wybe Dijkstra: His Life, Work, and Legacy, pp. 287\u2013290. Association for Computing Machinery (2022)","DOI":"10.1145\/3544585.3544600"},{"key":"14_CR11","doi-asserted-by":"publisher","unstructured":"Dutta, A., Zisserman, A.: The VIA annotation software for images, audio and video. In: ACM MM, MM 2019. ACM, New York (2019). https:\/\/doi.org\/10.1145\/3343031.3350535","DOI":"10.1145\/3343031.3350535"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"D\u2019Agostino, R.B.: Tests for the normal distribution. In: Goodness-of-Fit-Techniques, pp. 367\u2013420. Routledge (2017)","DOI":"10.1201\/9780203753064-9"},{"issue":"8","key":"14_CR13","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1109\/34.784288","volume":"21","author":"A El-Yacoubi","year":"1999","unstructured":"El-Yacoubi, A., Gilloux, M., Sabourin, R., Suen, C.Y.: An HMM-based approach for off-line unconstrained handwritten word modeling and recognition. IEEE TPAMI 21(8), 752\u2013760 (1999)","journal-title":"IEEE TPAMI"},{"key":"14_CR14","unstructured":"Google LLC: Google Cloud Vision Document OCR, python client library. https:\/\/cloud.google.com\/vision\/docs\/ocr#optical_character_recognition_ocr"},{"issue":"5","key":"14_CR15","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1109\/TPAMI.2008.137","volume":"31","author":"A Graves","year":"2008","unstructured":"Graves, A., Liwicki, M., Fern\u00e1ndez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE TPAMI 31(5), 855\u2013868 (2008)","journal-title":"IEEE TPAMI"},{"key":"14_CR16","unstructured":"Hudson, R., Meditz, S., of\u00a0Congress. Federal Research\u00a0Division, L.: Uruguay: a country study. Area Handbook Uruguay: A Country Study, Federal Research Division, Library of Congress (1992). https:\/\/books.google.fr\/books?id=vm17AAAAMAAJ"},{"issue":"12","key":"14_CR17","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1109\/34.643891","volume":"19","author":"GE Kopec","year":"1997","unstructured":"Kopec, G.E., Lomelin, M.: Supervised template estimation for document image decoding. IEEE TPAMI 19(12), 1313\u20131324 (1997)","journal-title":"IEEE TPAMI"},{"key":"14_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NeurIPS, vol. 25 (2012)"},{"issue":"4","key":"14_CR19","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: AAAI, vol. 37, no. 11, pp. 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"issue":"1","key":"14_CR21","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. IJCV 129(1), 161\u2013184 (2021)","journal-title":"IJCV"},{"issue":"6","key":"14_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3453476","volume":"54","author":"TTH Nguyen","year":"2021","unstructured":"Nguyen, T.T.H., Jatowt, A., Coustaty, M., Doucet, A.: Survey of post-OCR processing approaches. ACM Comput. Surv. (CSUR) 54(6), 1\u201337 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"3","key":"14_CR23","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1145\/882262.882269","volume":"22","author":"P P\u00e9rez","year":"2003","unstructured":"P\u00e9rez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM TOG 22(3), 313\u2013318 (2003)","journal-title":"ACM TOG"},{"key":"14_CR24","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.3758\/s13423-014-0585-6","volume":"21","author":"ST Piantadosi","year":"2014","unstructured":"Piantadosi, S.T.: Zipf\u2019s word frequency law in natural language: a critical review and future directions. Psychon. Bull. Rev. 21, 1112\u20131130 (2014)","journal-title":"Psychon. Bull. Rev."},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Doucet, A., Coustaty, M., Moreux, J.P.: ICDAR 2019 competition on post-OCR text correction. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1588\u20131593. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00255"},{"key":"14_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"14_CR27","doi-asserted-by":"publisher","unstructured":"Siglidis, I., Gonthier, N., Gaubil, J., Monnier, T., Aubry, M.: The learnable typewriter: a generative approach to text analysis. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds.) ICDAR 2024. LNCS, vol. 14805, pp. 297\u2013314. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-70536-6_18","DOI":"10.1007\/978-3-031-70536-6_18"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth international conference on document analysis and recognition (ICDAR 2007), vol.\u00a02, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"14_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) NeurIPS, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"14_CR30","unstructured":"Volpi, R., Namkoong, H., Sener, O., Duchi, J.C., Murino, V., Savarese, S.: Generalizing to unseen domains via adversarial data augmentation. In: NeurIPS, vol. 31 (2018)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Xing, L., Tian, Z., Huang, W., Scott, M.R.: Convolutional character networks. In: ICCV, pp. 9126\u20139136 (2019)","DOI":"10.1109\/ICCV.2019.00922"}],"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_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T02:08:32Z","timestamp":1757988512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04627-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046260","9783032046277"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04627-7_14","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":"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"}}]}}