Skip to Content

Publications




Teklia is involved in national and international research projects, and its researchers publish their findings in international and national journals and conferences.
This research enables us to improve our document processing solutions and offer our customers the best artificial intelligence algorithms.  For over 10 years, we have been working to promote the adoption of AI technologies in the fields of heritage, culture and humanities.
Peer-reviewed international journalsPeer-reviewed national journalsInternational conferences with peer reviewNational conferences with peer reviewBook chaptersInternational peer-reviewed communicationsGuest international communicationsGuest national communications

Peer-reviewed international journals

  • Saint-Ours, É.D. & Kermorvant, C. (In press) The HikarIA Project: Using artificial intelligence to research and promote Japanese photographic heritage. Journal of Data Mining & Digital Humanities.

  • Tarride, S., Maarand, M., Boillet, M., McGrath, J., Capel, E., Vézina, H., & Kermorvant, C. (2023) Large-Scale Genealogical Information Extraction from Handwritten Quebec Parish Records. International Journal on Document Analysis and Recognition, 26(3), 255–272. [PDF]

  • Boillet, M., Kermorvant, C., & Paquet, T. (2023) Confidence Estimation for Object Detection in Document Images. Pattern Recognition Letters, 166(C), 31–37. [PDF]

  • Boillet, M., Kermorvant, C., & Paquet, T. (2022) Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods. International Journal on Document Analysis and Recognition, 25(2), 95–114. [PDF]

  • Walton, S., Livermore, L., Bánki, O., Cubey, R.W.N., Drinkwater, R., Englund, M., Goble, C., Groom, Q., Kermorvant, C., Rey, I., Santos, C.M., Scott, B., Williams, A.R., & Wu, Z. (2020) Landscape Analysis for the Specimen Data Refinery. Research Ideas and Outcomes, 6, e57602. [PDF]

  • Moysset, B., Kermorvant, C., & Wolf, C. (2018) Learning to detect, localize and recognize many text objects in document images from few examples. International Journal on Document Analysis and Recognition.
  • Renton, G., Soullard, Y., Chatelain, C., Adam, S., Kermorvant, C., & Paquet, T. (2018) Fully Convolutional Network with Dilated Convolutions for Handwritten Text Line Segmentation. International Journal on Document Analysis and Recognition, 21(3), 177–186. [PDF]

Peer-reviewed national journals

  • Daille, B., Hazem, A., Kermorvant, C., Maarand, M., Bonhomme, M.L., Stutzmann, D., Currie, J., & Jacquin, C. (2019) Transcription automatique et segmentation thématique de livres d'heures manuscrits. Traitement Automatique des Langues, 60(3), 13--36.

International conferences with peer review

  • Périssier, L., Rebolledo-Dhuin, V., Petiot, M.T., Schneider, Y., & Kermorvant, C. (2024) PRET19: Automatic Recognition and Indexing of Handwritten Loan Registers from 19th Century Parisian Universities. In International Conference on Theory and Practice of Digital Libraries (pp. 360–378). Springer-Verlag. [PDF]

  • Villanova-Aparisi, D., Tarride, S., Martínez-Hinarejos, C.D., Romero, V., Kermorvant, C., & Pastor-Gadea, M. (2024) Reading Order Independent Metrics for Information Extraction in Handwritten Documents. In International Conference on Document Analysis and Recognition (pp. 191--215). Springer Nature Switzerland.

  • Boillet, M., Tarride, S., Schneider, Y., Abadie, B., Kesztenbaum, L., & Kermorvant, C. (2024) The Socface Project: Large-Scale Collection, Processing, and Analysis of a Century of French Censuses. In International Conference on Document Analysis and Recognition (pp. 57--73). Springer Nature Switzerland.

  • Bottaioli, N., Tarride, S., Anger, J., Mowlavi, S., Gardella, M., Tadros, A., Facciolo, G., von Gioi, R.G., Kermorvant, C., Morel, J.M., & Preciozzi, J. (2024) Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates. In Document Analysis and Recognition -- ICDAR 2024 Workshops (pp. 40--54). Springer Nature Switzerland.

  • Tarride, S. & Kermorvant, C. (2024) Revisiting N-Gram Models: Their Impact in Modern Neural Networks for Handwritten Text Recognition. In International Conference on Document Analysis and Recognition (pp. 167--182). Springer Nature Switzerland.

  • Tarride, S., Schneider, Y., Generali-Lince, M., Boillet, M., Abadie, B., & Kermorvant, C. (2024) Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library. In International Conference on Document Analysis and Recognition (pp. 387--404). Springer Nature Switzerland.

  • Kermorvant, C., Bardou, E., Blanco, M., & Abadie, B. (2024) Callico: A Versatile Open-Source Document Image Annotation Platform. In International Conference on Document Analysis and Recognition (pp. 338–353). Springer-Verlag. [PDF]

  • Pippi, V., Cascianelli, S., Kermorvant, C., & Cucchiara, R. (2023) How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning. In International Conference on Document Analysis and Recognition. Springer-Verlag.

  • Tarride, S., Boillet, M., Moufflet, J.F., & Kermorvant, C. (2023) SIMARA: a database for key-value information extraction from full-page handwritten documents. In International Conference on Document Analysis and Recognition (pp. 185–204). Springer-Verlag.

  • Tarride, S., Boillet, M., & Kermorvant, C. (2023) Key-Value Information Extraction From Full Handwritten Pages. In Document Analysis and Recognition - ICDAR 2023: 17th International Conference, San José, CA, USA, August 21–26, 2023, Proceedings, Part II (pp. 185–204). Springer-Verlag. [PDF]

  • Tarride, S., Faine, T., Boillet, M., Mouchère, H., & Kermorvant, C. (2023) Handwritten Text Recognition from Crowdsourced Annotations. In International Workshop on Historical Document Imaging and Processing (HIP2023).

  • Cascianelli, S., Pippi, V., Maarand, M., Cornia, M., Baraldi, L., Kermorvant, C., & Cucchiara, R. (2022) The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition. In International Conference on Pattern Recognition (ICPR) (pp. 1506-1513). [PDF]

  • Maarand, M., Beyer, Y., Kasen, A., Fosseide, K.T., & Kermorvant, A.C. (2022) A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Norwegian. In Document Analysis Systems.

  • Monroc, C.B., Miret, B., Bonhomme, M.L., & Kermorvant, C. (2022) A Comprehensive Study of Open-source Libraries for Named Entity Recognition on Handwritten Historical Documents. In Document Analysis Systems.

  • Debezia, J.L., Boillet, M., Kermorvant, C., & Barral, Q. (2021) Drilling a large corpus of document images of geological information extraction. In 1st Workshop on Machine Learning for Buildings Energy Management.

  • Boillet, M., Maarand, M., Paquet, T., & Kermorvant, C. (2021) Including Keyword Position in Image-based Models for Act Segmentation of Historical Registers. In International Workshop on Historical Document Imaging and Processing.

  • Hazem, A., Daille, B., Stutzmann, D., Kermorvant, C., & Chevalier, L. (2020) Hierarchical Text Segmentation for Medieval Manuscripts. In Proceedings of the 28th International Conference on Computational Linguistics (pp. 6240--6251). International Committee on Computational Linguistics. [PDF]

  • Boillet, M., Kermorvant, C., & Paquet, T. (2020) Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks. In International Conference on Pattern Recognition.

  • Boros, E., Romero, V., Maarand, M., Zenklová, K., Křečková, J., Vidal, E., Stutzmann, D., & Kermorvant, C. (2020) A comparison of sequential and combined approaches for named entity recognition in a corpus of handwritten medieval charters. In International Conference on Frontiers in Handwriting Recognition .

  • Hazem, A., Bonhomme, M.L., Maarand, M., Kermorvant, C., & Stutzmann, D. (2020) Books of Hours : the First Liturgical Corpus for Text Segmentation. In Proceedings of The 12th Language Resources and Evaluation Conference (pp. 776--784).

  • Boillet, M., Bonhomme, M.L., Stutzmann, D., & Kermorvant, C. (2019) HORAE: an annotated dataset of books of hours. In International Workshop on Historical Document Imaging and Processing.

  • Boros, E., Toumi, A., Rouchet, E., Abadie, B., Stutzmann, D., & Kermorvant, C. (2019) Automatic page classification in a large collection of manuscripts based on the International Image Interoperability Framework. In International Conference on Document Analysis and Recognition.

  • Bluche, T., Hamel, S., Kermorvant, C., Puigcerver, J., Stutzmann, D., Toselli, A., & Vidal, E. (2017) Preparatory KWS Experiments for Large-Scale Indexing of a Vast Medieval Manuscript Collection in the HIMANIS Project. In International Conference on Document Analysis and Recognition.

  • Moysset, B., Kermorvant, C., & Wolf, C. (2017) Full-Page Text Recognition: Learning Where to Start and When to Stop. In International Conference on Document Analysis and Recognition.

  • Bluche, T., Kermorvant, C., Touzet, C., & Glotin, H. (2017) Cortical-Inspired Open-Bigram Representation for Handwritten Word Recognition. In International Conference on Document Analysis and Recognition.

  • Renton, G., Chatelain, C., Adam, S., Kermorvant, C., & Paquet, T. (2017) Handwritten text line segmentation using Fully Convolutional Network. In International Workshop on Historical Document Imaging and Processing.

  • Moysset, B., Louradour, J., Kermorvant, C., & Wolf, C. (2016) Learning text-line localization with shared and local regression neural networks. In International Conference on Frontiers in Handwriting Recognition.

  • Bluche, T., Stutzmann, D., & Kermorvant, C. (2016) Automatic Handwritten Character Segmentation for Paleographical Character Shape Analysis. In Document Analysis Systems.

  • Stutzmann, D., Bluche, T., Kermorvant, C., Englin, V., Vincent, N., Leydier, Y., & Cloppet, F. (2016) Text-Image Alignment and Automated Letter-form Classification: Reading vs. Looking at. In Second International Conference on Natural Sciences and Technology in Manuscript Analysis.

  • Benzeghiba, M.F., Louradour, J., & Kermorvant, C. (2015) Hybrid Word / Part-of-Arabic-Word Language Models for Arabic Text Document Recognition. In International Conference of Document Analysis and Recognition.

  • Bluche, T., Kermorvant, C., & Louradour, J. (2015) Where to Apply Dropout in Recurrent Neural Networks for Handwriting Recognition ?. In International Conference of Document Analysis and Recognition.

  • Bluche, T., Ney, H., & Kermorvant, C. (2015) The LIMSI Handwriting Recognition System for the HTRtS 2014 Contest. In International Conference of Document Analysis and Recognition.

  • Bluche, T., Ney, H., & Kermorvant, C. (2015) Framewise and CTC Training of Neural Networks for Handwriting Recognition. In International Conference of Document Analysis and Recognition.

  • Moysset, B., Kermorvant, C., Wolf, C., & Louradour, J. (2015) Paragraph text segmentation into lines with Recurrent Neural Networks. In International Conference of Document Analysis and Recognition.

National conferences with peer review

  • Bluche, T., Kermorvant, C., Ney, H., & Louradour, J. (2016) La CTC et son intrigant label. In Colloque International Francophone sur l'Écrit et le Document (CIFED 2016).

Book chapters

  • Kermorvant, C. (2025) La reconnaissance d’écriture manuscrite : du caractère aux documents. In Alix Chagué and Thibault Clérice and Ariane Pinche (Eds.), Apprendre à Lire aux Machines.

  • Bluche, T., Kermorvant, C., & Ney, H. (2017) How to Design Deep Neural Networks for Handwriting Recognition.

International peer-reviewed communications

  • Kermorvant, C., Kesztenbaum, L., & Restif, M. (2025) Massive Access, Imperfect Data: Rethinking Archival Value in the Age of AI. Lightning talk at the International Archives Week 2025, organised by the International Council on Archives (ICA), online event, 9 June 2025.

  • Stutzmann, D. & Kermorvant, C. (2025) HORAE -- Book of Hours: A Thematic, Dual Portal. Presentation at the Biblissima+ International Conference "Written Cultures without Borders: International Forum of Portals", Centre de Colloques, Campus Condorcet, Aubervilliers, France, 21--22 May 2025.

  • Kermorvant, C., Boillet, M., Ciezar, P., Szabados, A.V., & Schuh, J. (2025) Arkindex, an Open-Source Platform for Document Image Recognition Applied to Archaeology. Presentation at the 52nd CAA International Conference, University of West Attica, Athens, Greece, 5--9 May 2025.|

  • Larcher, C. & Kermorvant, C. (2025) From Field Notes to Digital Archive: AI-Assisted Indexing of Bernard Bruyère's Excavation Journals of Deir el-Medina (1922--1955). Presentation at the 52nd CAA International Conference, University of West Attica, Athens, Greece, 5--9 May 2025.

  • Kermorvant, C. (2024) Semantic Content Description and Object Detection: How Contemporary Deep Learning Models Describe Early Japanese Photographs. Presentation at the conference "Artificial Intelligence in Archives and Collections: Practices, Potentials and Evidence Production in Dealing with Images and Multimodal Cultural Heritage", Herder Institute for Historical Research on East Central Europe, Marburg, Germany, 12--13 December 2024.

  • Vezina, H., Bournival, J.S., Kermorvant, C., & Bonhomme, M.L. (2019) I-Balsac: Completing Families with the Help of Automatic Text Recognition.

  • Stutzmann, D., Currie, J., Daille, B., Hazem, A., & Kermorvant, C. (2019) Integrated DH. Rationale of the HORAE Research Project.

  • Stutzmann, D., Bluche, T., Lavrentev, A., Leydier, Y., & Kermorvant, C. (2015) From Text and Image to Historical Resource : Text-Image Alignment for Digital Humanists.

Guest international communications

  • Kermorvant, C. (2025) Reading Albums with AI: Exploring the Content and Materiality of a Collection of Early Japanese Photographs. Invited talk at the conference organised by The Image Centre, Toronto Metropolitan University, Toronto, Canada, April 1, 2025.

  • Kermorvant, C. (2025) Open Source AI for Processing Heritage and Cultural Documents. Invited talk at the AI4Culture Final Conference: Exploring the Future of AI in Cultural Heritage, Netherlands Institute for Sound and Vision, Hilversum, Netherlands, March 10, 2025.

  • Kermorvant, C. (2025) NorHand-ATR: A Set of Open-Source Models for Recognizing Norwegian Handwritten Correspondence from the 18th and 19th Centuries. Invited talk at the Hugin-Munin Research Seminar, National Library of Norway, Oslo, Norway, January 20, 2025.

  • Kermorvant, C. (2024) Large Scale Industrial Processing of Historical Documents for Open Science: The Socface Project. Presentation at the Joint IAEA–French Ministry of Culture Advanced Workshop on the Sustainable Management of Ion Beam, C2RMF, Louvre Museum, Paris, France, 16--20 December 2024.

Guest national communications

  • Kermorvant, C. & Saint-Ours, É.D. (2025) Le projet HikarIA : analyse iconographique automatisée de photographies patrimoniales. Atelier numérique « Les lundis numériques de l’INHA », Institut National d'Histoire de l'Art (INHA), Paris, France, 16 juin 2025.

  • Kermorvant, C. (2025) Traitement automatique de documents numérisés par IA avec la plateforme open-source Arkindex. Communication invitée lors des journées imagIA2025 : Images & IA -- Faire dialoguer les communautés, Maison Méditerranéenne des Sciences de l'Homme, Aix-en-Provence, France, 13--14 mai 2025.

  • Kermorvant, C. (2025) L’intelligence artificielle au service des collections muséales. Intervention lors de la table ronde organisée par le ministère de la Culture dans le cadre du Salon SITEM 2025, Paris, France, 25 mars 2025.

  • Kermorvant, C. (2025) Le projet HikarIA : L’intelligence artificielle au service de l’étude et de la valorisation des photographies anciennes du Japon. Communication invitée lors de la conférence organisée par la Société des amis du musée Guimet, Paris, France, 12 mars 2025.

  • Kermorvant, C. (2025) Le projet Socface. Communication lors du Week-end culturel de l'IA, dans le cadre de la Semaine culturelle de l'IA, en ouverture du Sommet pour l'action sur l'intelligence artificielle. Paris, France, 9 février 2025.

  • Kermorvant, C. (2025) Indexation automatique du fichier de contrôle de la préfecture de police de Paris. Intervention lors de la table ronde « Premier accès sécurisé au fichier juif », organisée par les Archives nationales et le Mémorial de la Shoah à l’occasion du 80ème anniversaire de la découverte du camp d’Auschwitz. Archives Nationales, Paris, France, 27 janvier 2025.

  • Kermorvant, C. (2025) Présentation de la plateforme Arkindex. Communication invitée lors du séminaire « Annotation collaborative et IIIF », projet Mezanno, Bibliothèque nationale de France (BnF), Paris, France, 24 janvier 2025.

  • Kermorvant, C. (2024) Reconnaissance automatique et indexation des registres de prêts manuscrits du XIXe siècle des universités parisiennes. Communication lors de la journée de clôture du projet PRET19, organisée avec le soutien du GIS CollEx-Persée. Paris, France, 16 décembre 2024.