{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:09:50Z","timestamp":1758089390205,"version":"3.44.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046239"},{"type":"electronic","value":"9783032046246"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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\/978-3-032-04624-6_26","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:33:20Z","timestamp":1758000800000},"page":"443-458","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Version 5 of\u00a0the\u00a0Kraken ATR Engine for\u00a0the\u00a0Humanities"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-7827","authenticated-orcid":false,"given":"Benjamin","family":"Kiessling","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Ares\u00a0Oliveira, S., Seguin, B., Kaplan, F.: dhsegment: a generic deep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7\u201312 (2018). https:\/\/doi.org\/10.1109\/ICFHR-2018.2018.00011","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"26_CR2","unstructured":"Baierer, K.: hOCR - OCR Workflow and Output embedded in HTML (2020). https:\/\/kba.github.io\/hocr-spec\/1.2\/"},{"key":"26_CR3","doi-asserted-by":"publisher","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.\u00a001, pp. 646\u2013651 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.111","DOI":"10.1109\/ICDAR.2017.111"},{"key":"26_CR4","doi-asserted-by":"publisher","unstructured":"Brisson, C., Constant, F., Bui, M.: Chinese historical documents automatic transcription (chat) models (Sep 2023). https:\/\/doi.org\/10.5281\/zenodo.8383732. https:\/\/doi.org\/10.5281\/zenodo.8383732","DOI":"10.5281\/zenodo.8383732"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Castro, D., Bezerra, B.L.D., Zanchettin, C.: An end-to-end approach for handwriting recognition: From handwritten text lines to complete pages. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 264\u2013273 (6 2024)","DOI":"10.1109\/CVPRW63382.2024.00031"},{"key":"26_CR6","unstructured":"Chagu\u00e9, A., Cl\u00e9rice, T.: \u201dI\u2019m here to fight for ground truth\u201d: HTR-United, a solution towards a common for HTR training data. In: Digital Humanities 2023: Collaboration as Opportunity. Alliance of Digital Humanities Organizations and University of Graz, Graz, Austria (Jul 2023). https:\/\/inria.hal.science\/hal-04094233"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Cl\u00e9rice, T., et al.: CATMuS Medieval: A large scale cross-century dataset in latin scripts for handwritten text recognition and beyond. In: ICDAR 2024: International Conference on Document Analysis and Recognition, Athens, Greece, September 6-11, 2024 (2024), under review","DOI":"10.1007\/978-3-031-70543-4_11"},{"issue":"7","key":"26_CR8","doi-asserted-by":"publisher","first-page":"8227","DOI":"10.1109\/TPAMI.2023.3235826","volume":"45","author":"D Coquenet","year":"2023","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: Dan: a segmentation-free document attention network for handwritten document recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8227\u20138243 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3235826","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR9","doi-asserted-by":"publisher","unstructured":"Fujitake, M.: Dtrocr: Decoder-only transformer for optical character recognition. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 8010\u20138020 (2024). https:\/\/doi.org\/10.1109\/WACV57701.2024.00784","DOI":"10.1109\/WACV57701.2024.00784"},{"key":"26_CR10","doi-asserted-by":"publisher","unstructured":"Gabay, S.: Fondue-gd (Dec 2024). https:\/\/doi.org\/10.5281\/zenodo.14399779","DOI":"10.5281\/zenodo.14399779"},{"key":"26_CR11","unstructured":"Gabay, S., Pinche, Christensen, K., Camps, J.B., Carboni, N.: SegmOnto, A Controlled Vocabulary to Describe the Layout of Pages (2023). https:\/\/segmonto.github.io\/"},{"key":"26_CR12","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ICML \u201906, Association for Computing Machinery, New York, NY, USA (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"26_CR13","doi-asserted-by":"publisher","unstructured":"Gruning, T., Labahn, R., Diem, M., Kleber, F., Fiel, S.: READ-BAD: a new dataset and evaluation scheme for baseline detection in archival documents . In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 351\u2013356. IEEE Computer Society, Los Alamitos, CA, USA (Apr 2018). https:\/\/doi.org\/10.1109\/DAS.2018.38, https:\/\/doi.ieeecomputersociety.org\/10.1109\/DAS.2018.38","DOI":"10.1109\/DAS.2018.38"},{"key":"26_CR14","doi-asserted-by":"publisher","unstructured":"Gr\u00fcning, T., Leifert, G., Strau\u00df, T., Michael, J., Labahn, R.: A two-stage method for text line detection in historical documents. Int. J. Document Analysis Recogn. (IJDAR) 22(3), 285\u2013302 (9 2019). https:\/\/doi.org\/10.1007\/s10032-019-00332-1","DOI":"10.1007\/s10032-019-00332-1"},{"key":"26_CR15","doi-asserted-by":"publisher","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Pay attention to what you read: non-recurrent handwritten text-line recognition. Pattern Recogn. 129, 108766 (2022). https:\/\/doi.org\/10.1016\/j.patcog.2022.108766, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320322002473","DOI":"10.1016\/j.patcog.2022.108766"},{"key":"26_CR16","doi-asserted-by":"publisher","unstructured":"Kiessling, B.: A modular region and text line layout analysis system. In: 17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020, Dortmund, Germany, September 8-10, 2020, pp. 313\u2013318. IEEE (2020). https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00064, https:\/\/hal.science\/hal-04442992","DOI":"10.1109\/ICFHR2020.2020.00064"},{"key":"26_CR17","doi-asserted-by":"publisher","unstructured":"Kiessling, B.: CurT: end-to-end text line detection in\u00a0historical documents with\u00a0transformers. In: Frontiers in Handwriting Recognition: 18th International Conference, ICFHR 2022, Hyderabad, India, December 4\u20137, 2022. Lecture Notes in Computer Science, vol. 13639, pp. 34\u201348. Springer International Publishing, Hyderabad, India (Dec 2022). https:\/\/doi.org\/10.1007\/978-3-031-21648-0_3, https:\/\/hal.science\/hal-04036249","DOI":"10.1007\/978-3-031-21648-0_3"},{"key":"26_CR18","unstructured":"Kiessling, B.: The HTRMoPo schema for repositories of HTR\/OCR models (2025). https:\/\/github.com\/mittagessen\/htrmopo"},{"key":"26_CR19","doi-asserted-by":"publisher","unstructured":"Kiessling, B., Tissot, R., Stokes, P.A., Ezra, D.S.B.: eScriptorium: An open source platform for historical document analysis. In: 2nd International Workshop on Open Services and Tools for Document Analysis, OST@ICDAR 2019, Sydney, Australia, September 22-25, 2019, p.\u00a019. IEEE (2019). https:\/\/doi.org\/10.1109\/ICDARW.2019.10032","DOI":"10.1109\/ICDARW.2019.10032"},{"key":"26_CR20","doi-asserted-by":"publisher","unstructured":"Klut, S., van Koert, R., Sluijter, R.: Laypa: A novel framework for applying segmentation networks to historical documents. In: Proceedings of the 7th International Workshop on Historical Document Imaging and Processing, pp. 67\u201372. HIP \u201923, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3604951.3605520","DOI":"10.1145\/3604951.3605520"},{"key":"26_CR21","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-3-030-86331-9_32","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"O Kodym","year":"2021","unstructured":"Kodym, O., Hradi\u0161, M.: Page layout analysis system for unconstrained historic documents. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition - ICDAR 2021, pp. 492\u2013506. Springer International Publishing, Cham (2021)"},{"key":"26_CR22","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: Trocr: Transformer-based optical character recognition with pre-trained models. In: Proceedings of the AAAI Conference on Artificial Intelligence 37(11), 13094\u201313102 (6 2023). https:\/\/doi.org\/10.1609\/aaai.v37i11.26538, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/26538","DOI":"10.1609\/aaai.v37i11.26538"},{"issue":"1","key":"26_CR23","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s100320200071","volume":"5","author":"UV Marti","year":"2002","unstructured":"Marti, U.V., Bunke, H.: The iam-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recogn. 5(1), 39\u201346 (2002)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"26_CR24","doi-asserted-by":"publisher","unstructured":"Neudecker, C., et al.: OCR-d: An end-to-end open source OCR framework for historical printed documents. In: Proceedings of the 3rd International Conference on Digital Access to Textual Cultural Heritage, pp. 53\u201358. DATeCH2019, Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3322905.3322917","DOI":"10.1145\/3322905.3322917"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Pinche, A.: Generic HTR Models for Medieval Manuscripts. The CREMMALab Project. J. Data Mining Digital Humanities Historical Documents and automatic text recognition (Jun 2023). https:\/\/hal.science\/hal-03837519","DOI":"10.46298\/jdmdh.10252"},{"key":"26_CR26","doi-asserted-by":"publisher","unstructured":"Pinche, A., et al.: Catmus medieval (Jul 2024). https:\/\/doi.org\/10.5281\/zenodo.12743230","DOI":"10.5281\/zenodo.12743230"},{"key":"26_CR27","doi-asserted-by":"publisher","unstructured":"Pletschacher, S., Antonacopoulos, A.: The page (page analysis and ground-truth elements) format framework. In: 2010 20th International Conference on Pattern Recognition, pp. 257\u2013260 (2010). https:\/\/doi.org\/10.1109\/ICPR.2010.72","DOI":"10.1109\/ICPR.2010.72"},{"key":"26_CR28","unstructured":"Project PERO: (2021). https:\/\/pero-ocr.fit.vutbr.cz\/"},{"key":"26_CR29","doi-asserted-by":"publisher","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a001, pp. 67\u201372 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.20","DOI":"10.1109\/ICDAR.2017.20"},{"key":"26_CR30","doi-asserted-by":"publisher","unstructured":"Quir\u00f3s, L., Vidal, E.: Reading order detection on handwritten documents. Neural Comput. Appl. 34(12), 9593\u20139611 (Jun 2022). https:\/\/doi.org\/10.1007\/s00521-022-06948-5","DOI":"10.1007\/s00521-022-06948-5"},{"key":"26_CR31","unstructured":"Quir\u00f3s, L.: Multi-task handwritten document layout analysis (2018). https:\/\/arxiv.org\/abs\/1806.08852"},{"key":"26_CR32","unstructured":"READ-COOP: Transkribus (2025). https:\/\/transkribus.org"},{"key":"26_CR33","doi-asserted-by":"publisher","unstructured":"Reul, C., et al.: Ocr4all\u2014an open-source tool providing a (semi-)automatic ocr workflow for historical printings. Appl. Sci. 9(22) (2019). https:\/\/doi.org\/10.3390\/app9224853, https:\/\/www.mdpi.com\/2076-3417\/9\/22\/4853","DOI":"10.3390\/app9224853"},{"key":"26_CR34","doi-asserted-by":"publisher","unstructured":"Reul, C., Springmann, U., Puppe, F.: Larex: A semi-automatic open-source tool for layout analysis and region extraction on early printed books. In: Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage, pp. 137\u2013142. DATeCH2017, Association for Computing Machinery, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3078081.3078097","DOI":"10.1145\/3078081.3078097"},{"key":"26_CR35","first-page":"234","volume-title":"Medical Image Computing and Computer-Assisted Intervention - 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.) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, pp. 234\u2013241. Springer International Publishing, Cham (2015)"},{"key":"26_CR36","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-86334-0_4","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"SS Singh","year":"2021","unstructured":"Singh, S.S., Karayev, S.: Full page handwriting recognition via image to sequence extraction. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) Document Analysis and Recognition - ICDAR 2021, pp. 55\u201369. Springer International Publishing, Cham (2021)"},{"key":"26_CR37","doi-asserted-by":"publisher","unstructured":"Stoekl Ben\u00a0Ezra, D., Brown-DeVost, B., Jablonski, P., Lapin, H., Kiessling, B., Lolli, E.: Biblia - a general model for medieval hebrew manuscripts and an open annotated dataset. In: Proceedings of the 6th International Workshop on Historical Document Imaging and Processing, pp. 61\u201366. HIP \u201921, Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3476887.3476896","DOI":"10.1145\/3476887.3476896"},{"key":"26_CR38","unstructured":"The ALTO editorial board: ALTO Technical Metadata for Layout and Text Objects (2023). https:\/\/www.loc.gov\/standards\/alto\/"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Vogler, N., Allen, J.P., Miller, M.T., Berg-Kirkpatrick, T.: Lacuna reconstruction: Self-supervised pre-training for low-resource historical document transcription. arXiv preprint arXiv:2112.08692 (2021)","DOI":"10.18653\/v1\/2022.findings-naacl.15"},{"key":"26_CR40","unstructured":"Wick, C., Reul, C., Puppe, F.: Calamari - A high-performance tensorflow-based deep learning package for optical character recognition. Digital Human. Quart. 14(1) (2020)"},{"key":"26_CR41","doi-asserted-by":"publisher","unstructured":"W\u00f6dlinger, M., Sablatnig, R.: Text baseline recognition using a recurrent convolutional neural network. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 4673\u20134679 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412624","DOI":"10.1109\/ICPR48806.2021.9412624"}],"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\/978-3-032-04624-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:33:25Z","timestamp":1758000805000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04624-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032046239","9783032046246"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04624-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 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"}}]}}