{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T07:12:01Z","timestamp":1766301121026,"version":"build-2065373602"},"reference-count":30,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,1,25]],"date-time":"2025-01-25T00:00:00Z","timestamp":1737763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"iForal project","doi-asserted-by":"publisher","award":["PTDC\/HAR-HIS\/5065\/2020","FCT\/MCTE"],"award-info":[{"award-number":["PTDC\/HAR-HIS\/5065\/2020","FCT\/MCTE"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"national funds","award":["PTDC\/HAR-HIS\/5065\/2020","FCT\/MCTE"],"award-info":[{"award-number":["PTDC\/HAR-HIS\/5065\/2020","FCT\/MCTE"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>The transcription of historical manuscripts aims at making our cultural heritage more accessible to experts and also to the larger public, but it is a challenging and time-intensive task. This paper contributes an automated solution for text layout recognition, segmentation, and recognition to speed up the transcription process of historical manuscripts. The focus is on transcribing Portuguese municipal documents from the Middle Ages in the context of the iForal project, including the contribution of an annotated dataset containing Portuguese medieval documents, notably a corpus of 67 Portuguese royal charter data. The proposed system can accurately identify document layouts, isolate the text, segment, and transcribe it. Results for the layout recognition model achieved 0.98 mAP@0.50 and 0.98 precision, while the text segmentation model achieved 0.91 mAP@0.50, detecting 95% of the lines. The text recognition model achieved 8.1% character error rate (CER) and 25.5% word error rate (WER) on the test set. These results can then be validated by palaeographers with less effort, contributing to achieving high-quality transcriptions faster. Moreover, the automatic models developed can be utilized as a basis for the creation of models that perform well for other historical handwriting styles, notably using transfer learning techniques. The contributed dataset has been made available on the HTR United catalogue, which includes training datasets to be used for automatic transcription or segmentation models. The models developed can be used, for instance, on the eSriptorium platform, which is used by a vast community of experts.<\/jats:p>","DOI":"10.3390\/jimaging11020036","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T07:46:29Z","timestamp":1737963989000},"page":"36","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["iForal: Automated Handwritten Text Transcription for Historical Medieval Manuscripts"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4781-3294","authenticated-orcid":false,"given":"Alexandre","family":"Matos","sequence":"first","affiliation":[{"name":"Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9005-6688","authenticated-orcid":false,"given":"Pedro","family":"Almeida","sequence":"additional","affiliation":[{"name":"Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6525-9572","authenticated-orcid":false,"given":"Paulo","family":"Correia","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunica\u00e7\u00f5es (IT), Instituto Superior Tecnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3098-7163","authenticated-orcid":false,"given":"Osvaldo","family":"Pacheco","sequence":"additional","affiliation":[{"name":"Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Reul, C., Christ, D., Hartelt, A., Balbach, N., Wehner, M., Springmann, U., Wick, C., Grundig, C., B\u00fcttner, A., and Puppe, F. (2019). OCR4all\u2014An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings. Appl. Sci., 9.","DOI":"10.20944\/preprints201909.0101.v1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102606","DOI":"10.1016\/j.ipm.2021.102606","article-title":"In Codice Ratio: A crowd-enabled solution for low resource machine transcription of the Vatican Registers","volume":"58","author":"Nieddu","year":"2021","journal-title":"Inf. Process. Manag."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Philips, J., and Tabrizi, N. (2020, January 2\u20134). Historical Document Processing: Historical Document Processing: A Survey of Techniques, Tools, and Trends. Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, Virtual.","DOI":"10.5220\/0010177403350343"},{"key":"ref_4","unstructured":"(2024, November 07). iForal. Available online: https:\/\/iforal.hypotheses.org\/."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"130","DOI":"10.21814\/diacritica.5602","article-title":"A edi\u00e7\u00e3o digital de forais medievais portugueses com o suporte de um sistema de edi\u00e7\u00e3o colaborativa em base de dados","volume":"38","author":"Silvestre","year":"2024","journal-title":"Diacr\u00edtica"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Al-Taee, M., Neji, S., and Frikha, M. (2020, January 9\u201311). Handwritten Recognition: A survey. Proceedings of the 2020 IEEE 4th International Conference On Image Processing, Applications And Systems (IPAS), Genova, Italy.","DOI":"10.1109\/IPAS50080.2020.9334936"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-36107-5_1","article-title":"An Overview of Handwritten Character Recognition Systems for Historical Documents","volume":"859","author":"Bugeja","year":"2020","journal-title":"Stud. Comput. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Teslya, N., and Mohammed, S. (2022, January 27\u201329). Deep Learning for Handwriting Text Recognition: Existing Approaches and Challenges. Proceedings of the 2022 31st Conference of Open Innovations Association (FRUCT), Helsinki, Finland.","DOI":"10.23919\/FRUCT54823.2022.9770912"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Breuel, T. (2017, January 9\u201315). High Performance Text Recognition Using a Hybrid Convolutional-LSTM Implementation. Proceedings of the 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.12"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Puigcerver, J. (2017, January 9\u201315). Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?. Proceedings of the 2017 14th IAPR International Conference On Document Analysis and Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.20"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Li, M., Lv, T., Chen, J., Cui, L., Lu, Y., Florencio, D., Zhang, C., Li, Z., and Wei, F. (2023, January 7\u201314). TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models. Proceedings of the 37th AAAI Conference on Artificial Intelligence AAAI 2023, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Str\u00f6bel, P., Hodel, T., Boente, W., and Volk, M. (2023, January 21\u201326). The Adaptability of a Transformer-Based OCR Model for Historical Documents. Proceedings of the 17th International Conference on Document Analysis and Recognition, San Jos\u00e9, CA, USA.","DOI":"10.1007\/978-3-031-41498-5_3"},{"key":"ref_13","unstructured":"(2024, November 06). Kraken. Available online: https:\/\/kraken.re\/main\/index.html."},{"key":"ref_14","unstructured":"(2024, October 01). eScriptorium. Available online: https:\/\/gitlab.com\/scripta\/escriptorium."},{"key":"ref_15","unstructured":"Wick, C., Reul, C., and Puppe, F. (2020). Calamari\u2014A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition. Digit. Humanit. Q., 14."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kahle, P., Colutto, S., Hackl, G., and M\u00fchlberger, G. (2017, January 9\u201315). Transkribus\u2014A Service Platform for Transcription, Recognition and Retrieval of Historical Documents. Proceedings of the 2017 14th IAPR International Conference On Document Analysis And Recognition (ICDAR), Kyoto, Japan.","DOI":"10.1109\/ICDAR.2017.307"},{"key":"ref_17","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"535","DOI":"10.3390\/signals3030032","article-title":"Text Line Extraction in Historical Documents Using Mask R-CNN","volume":"3","author":"Droby","year":"2022","journal-title":"Signals"},{"key":"ref_19","unstructured":"Alexandre, M., Rui, N., Gon\u00e7alo, M., Catarina, C., and Pedro, B. (2024, December 19). iForal-Dataset. (HTR United). Available online: https:\/\/github.com\/Arch-W\/iForal-Dataset."},{"key":"ref_20","unstructured":"(2024, November 07). PAGE XML. Available online: https:\/\/github.com\/PRImA-Research-Lab\/PAGE-XML."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Pletschacher, S., and Antonacopoulos, A. (2010, January 23\u201326). The PAGE (Page Analysis and Ground-Truth Elements) Format Framework. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.","DOI":"10.1109\/ICPR.2010.72"},{"key":"ref_22","unstructured":"iForal Platform (2024, October 09). Source of the Medieval Documents. Available online: https:\/\/deti-iforal.ua.pt\/documents\/."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wick, C., and Puppe, F. (2018, January 24\u201327). Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images. Proceedings of the 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), Vienna, Austria.","DOI":"10.1109\/DAS.2018.39"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ares Oliveira, S., Seguin, B., and Kaplan, F. (2018, January 5\u20138). dhSegment: A Generic Deep-Learning Approach for Document Segmentation. Proceedings of the 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, NY, USA.","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cl\u00e9rice, T. (2023). You Actually Look Twice at it (YALTAi): Using an object detection approach instead of region segmentation within the Kraken engine. J. Data Min. Digit. Humanit., 1\u201313.","DOI":"10.46298\/jdmdh.9806"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","article-title":"Beyond document object detection: Instance-level segmentation of complex layouts","volume":"24","author":"Biswas","year":"2021","journal-title":"Int. J. Doc. Anal. Recognit. IJDAR"},{"key":"ref_27","unstructured":"(2024, September 02). Ultralytics. Available online: https:\/\/docs.ultralytics.com\/."},{"key":"ref_28","unstructured":"(2024, October 09). Calamari OCR Documentation. Available online: https:\/\/calamari-ocr.readthedocs.io\/en\/latest\/."},{"key":"ref_29","unstructured":"Cl\u00e9rice, T., Pinche, A., and Vlachou-Efstathiou, M. (2023). Generic CREMMA Model for Medieval Manuscripts (Latin and Old French), 8\u201315th century. Zenodo, 2."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.patcog.2019.05.025","article-title":"A set of benchmarks for Handwritten Text Recognition on historical documents","volume":"94","author":"Romero","year":"2019","journal-title":"Pattern Recognit."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/2\/36\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:36:03Z","timestamp":1759919763000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/2\/36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,25]]},"references-count":30,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["jimaging11020036"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11020036","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2025,1,25]]}}}