{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:21:34Z","timestamp":1774484494524,"version":"3.50.1"},"reference-count":34,"publisher":"Walter de Gruyter GmbH","issue":"1","funder":[{"DOI":"10.13039\/100005156","name":"Alexander von Humboldt Foundation","doi-asserted-by":"crossref","award":["Sofja Kovalevskaja Award 2017"],"award-info":[{"award-number":["Sofja Kovalevskaja Award 2017"]}],"id":[{"id":"10.13039\/100005156","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007306","name":"Bayerische Akademie der Wissenschaften","doi-asserted-by":"crossref","award":["Cuneiform Artefacts of Iraq in Context"],"award-info":[{"award-number":["Cuneiform Artefacts of Iraq in Context"]}],"id":[{"id":"10.13039\/501100007306","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,2,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p xml:lang=\"en\">Among the many excavated cuneiform tablets, only a small portion has been analyzed by Assyriologists. Learning how to read cuneiform is a lengthy and challenging process that can take years to complete. This work aims to improve the automatic detection of cuneiform signs from 2D images of cuneiform tablets. The results can later be used for NLP tasks such as semantic annotation, word alignment and machine translation to assist Assyriologists in their research. We introduce the largest publicly available annotated dataset of cuneiform signs to date. It comprises of 52,102 signs from 315 fully annotated tablets, equating to 512 distinct images. In addition, we have preprocessed and refined four existing datasets, resulting in a comprehensive collection of 88,536 signs. Since some signs are not localized on fully annotated tablets, the total dataset encompasses 593 fully annotated cuneiform tablets, resulting in 654 images. Our efforts to expand this dataset are ongoing. Furthermore, we evaluate two state-of-the-art methods to establish benchmarks in the field. The first is a two-stage supervised sign\u202fdetection approach that involves: (1) the identification of bounding boxes, and (2) the classification of each sign\u202fwithin these boxes. The second method employs an object detection model. Given the numerous classes and their varied distribution, the task of cuneiform sign\u202fdetection poses a significant challenge in machine learning. This paper aims to lay a groundwork for future research, offering both a substantial dataset and initial methodologies for sign\u202fdetection on cuneiform tablets.<\/jats:p>","DOI":"10.1515\/itit-2024-0028","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T16:31:12Z","timestamp":1717173072000},"page":"28-38","source":"Crossref","is-referenced-by-count":4,"title":["Sign detection for cuneiform tablets"],"prefix":"10.1515","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5715-9979","authenticated-orcid":false,"given":"Yunus","family":"Cobanoglu","sequence":"first","affiliation":[{"name":"Institut f\u00fcr Assyriologie und Hethitologie , Ludwig-Maximilian University of Munich , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9107-6574","authenticated-orcid":false,"given":"Luis","family":"S\u00e1enz","sequence":"additional","affiliation":[{"name":"Seminar f\u00fcr Sprachen und Kulturen des Vorderen Orients , Heidelberg University , Heidelberg , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0520-7014","authenticated-orcid":false,"given":"Ilya","family":"Khait","sequence":"additional","affiliation":[{"name":"Institut f\u00fcr Assyriologie und Hethitologie , Ludwig-Maximilian University of Munich , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0093-528X","authenticated-orcid":false,"given":"Enrique","family":"Jim\u00e9nez","sequence":"additional","affiliation":[{"name":"Institut f\u00fcr Assyriologie und Hethitologie , Ludwig-Maximilian University of Munich , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"2024110207213604054_j_itit-2024-0028_ref_036","unstructured":"M. Krebernik, \u201cZur Struktur und Geschichte des \u00e4lteren sumerischen Onomastikons,\u201d in Altorientalische und semitische Onomastik, M. P. Streck and S. Weninger, Eds., M\u00fcnster, Ugarit-Verlag, 2002, pp. 1\u201374. Available at: https:\/\/archiv.ub.uni-heidelberg.de\/propylaeumdok\/1452\/ Accessed: Nov. 7, 2023."},{"key":"2024110207213604054_j_itit-2024-0028_ref_016","unstructured":"A. J. Sachs, \u201cThe latest datable cuneiform tablets,\u201d in Kramer Aniversary Volume. Cuneiform Studies in Honor of Samuel Noah Kramer, B. L. Eichler, Ed., Kevelaer, Neukirchen-Vluyn, Ugarit-Verlag, 1976, pp. 379\u2013398."},{"key":"2024110207213604054_j_itit-2024-0028_ref_029","unstructured":"M. P. Streck, Sprachen des alten Orients, Darmstadt, Wissenschaftliche Buchgesellschaft, 2007."},{"key":"2024110207213604054_j_itit-2024-0028_ref_031","unstructured":"M. P. Streck, \u201cGro\u00dfes Fach Altorientalistik: Der Umfang des keilschriftlichen Textkorpus,\u201d Mitt. Dtsch. Orient Ges. Berl., vol. 142, no. 1, pp. 35\u201358, 2010."},{"key":"2024110207213604054_j_itit-2024-0028_ref_034","doi-asserted-by":"crossref","unstructured":"S. Gordin, G. Gutherz, A. Elazary, A. Romach, E. Jim\u00e9nez, J. Berant, and Y. Cohen, \u201cReading Akkadian cuneiform using natural language processing,\u201d PLoS One, vol. 15, no. 10, p. e0240511, 2020. https:\/\/doi.org\/10.1371\/journal.pone.0240511.","DOI":"10.1371\/journal.pone.0240511"},{"key":"2024110207213604054_j_itit-2024-0028_ref_033","doi-asserted-by":"crossref","unstructured":"E. Fetaya, Y. Lifshitz, E. Aaron, and S. Gordin, \u201cRestoration of fragmentary Babylonian texts using recurrent neural networks,\u201d Proc. Natl. Acad. Sci., vol. 117, no. 37, pp. 22743\u201322751, 2020. https:\/\/doi.org\/10.1073\/pnas.2003794117.","DOI":"10.1073\/pnas.2003794117"},{"key":"2024110207213604054_j_itit-2024-0028_ref_035","doi-asserted-by":"crossref","unstructured":"G. Gutherz, S. Gordin, L. S\u00e1enz, O. Levy, and J. Berant, \u201cTranslating Akkadian to English with neural machine translation,\u201d PNAS Nexus, vol. 2, no. 5, p. pgad096, 2023. https:\/\/doi.org\/10.1093\/pnasnexus\/pgad096.","DOI":"10.1093\/pnasnexus\/pgad096"},{"key":"2024110207213604054_j_itit-2024-0028_ref_009","doi-asserted-by":"crossref","unstructured":"B. Bogacz and H. Mara, \u201cDigital assyriology \u2013 advances in visual cuneiform analysis,\u201d ACM J. Comput. Cult. Herit., vol. 15, no. 2, pp. 1\u201322, 2022. https:\/\/doi.org\/10.1145\/3491239.","DOI":"10.1145\/3491239"},{"key":"2024110207213604054_j_itit-2024-0028_ref_025","unstructured":"A. Sahala, \u201cContributions to computational assyriology,\u201d 2021, https:\/\/doi.org\/10.13140\/RG.2.2.15525.17127."},{"key":"2024110207213604054_j_itit-2024-0028_ref_038","unstructured":"F. Simonjetz, J. Laasonen, Y. Cobanoglu, A. Fraser, and E. Jim\u00e9nez. Reconstruction of cuneiform literary texts as text matching. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), 2024, pp. 13712\u201313721, Torino, Italia. ELRA and ICCL. Available at: https:\/\/aclanthology.org\/2024.lrec-main.1197."},{"key":"2024110207213604054_j_itit-2024-0028_ref_026","doi-asserted-by":"crossref","unstructured":"T. Dencker, P. Klinkisch, S. M. Maul, and B. Ommer, \u201cDeep learning of cuneiform sign\u202fdetection with weak supervision using transliteration alignment,\u201d PLoS One, vol.\u00a015, no.\u00a012, p.\u00a0e0243039, 2020. https:\/\/doi.org\/10.1371\/journal.pone.0243039.","DOI":"10.1371\/journal.pone.0243039"},{"key":"2024110207213604054_j_itit-2024-0028_ref_024","unstructured":"W. Liu, et al.., \u201cSSD: single shot MultiBox detector,\u201d CoRR. abs\/1512.02325, 2015, http:\/\/arxiv.org\/abs\/1512.02325."},{"key":"2024110207213604054_j_itit-2024-0028_ref_027","unstructured":"E. Williams, G. Su, S. Schloen, M. Prosser, S. Paulus, and S. Krishnan, \u201cDeepScribe: localization and classification of elamite cuneiform signs via deep learning,\u201d CoRR. abs\/2306.01268, 2023, https:\/\/doi.org\/10.48550\/arXiv.2306.01268."},{"key":"2024110207213604054_j_itit-2024-0028_ref_022","doi-asserted-by":"crossref","unstructured":"E. Rusakov, T. Somel, G. Fink, and G. M\u00fcller, \u201cTowards query-by-eXpression retrieval of cuneiform signs,\u201d in 2020 17th International Conference on Frontiers In Handwriting Recognition (ICFHR), 2020, pp.\u00a043\u201348.","DOI":"10.1109\/ICFHR2020.2020.00019"},{"key":"2024110207213604054_j_itit-2024-0028_ref_023","unstructured":"M. Jursa, R. Pirngruber, Y. Levavi, and D. Schopper (2014\u20132017). Late Babylonian Signs (LaBaSi). https:\/\/labasi.acdh.oeaw.ac.at\/"},{"key":"2024110207213604054_j_itit-2024-0028_ref_012","unstructured":"Stephan H\u00fcgel (2014). Cuneiform Digital Palaeography Project (CDPP) v0.2. ZENODO.10.5281\/zenodo.11647"},{"key":"2024110207213604054_j_itit-2024-0028_ref_007","unstructured":"Electronic Babylonian Library Github. Available at: https:\/\/github.com\/ElectronicBabylonianLiterature Accessed: Nov. 7, 2023."},{"key":"2024110207213604054_j_itit-2024-0028_ref_001","doi-asserted-by":"crossref","unstructured":"Y. Cobanoglu, et al.., \u201cTransliterated cuneiform tablets of the electronic Babylonian Library platform,\u201d J. Open Humanit. Data, vol. 10, no. 1, p. 19, 2024. https:\/\/doi.org\/10.5334\/johd.148.","DOI":"10.5334\/johd.148"},{"key":"2024110207213604054_j_itit-2024-0028_ref_037","doi-asserted-by":"crossref","unstructured":"V. Yugay, K. Paliwal, Y. Cobanoglu, L. S\u00e1enz, E. Gogokhia, S. Gordin, and E. Jim\u00e9nez, \u201cStylistic classification of cuneiform signs using convolutional neural networks,\u201d IT - Information Technology, vol. 66, no. 1, pp. 12\u201324, 2024.","DOI":"10.1515\/itit-2023-0114"},{"key":"2024110207213604054_j_itit-2024-0028_ref_013","doi-asserted-by":"crossref","unstructured":"S. Suzuki and K. Be, \u201cTopological structural analysis of digitized binary images by border following,\u201d Comput. Vis. Graph Image Process., vol. 30, no. 1, pp. 32\u201346, 1985. https:\/\/doi.org\/10.1016\/0734-189X(85)90016-7.","DOI":"10.1016\/0734-189X(85)90016-7"},{"key":"2024110207213604054_j_itit-2024-0028_ref_006","unstructured":"OpenCV. Available at: https:\/\/docs.opencv.org\/3.4\/d4\/d73\/tutorial_py_contours_begin.html Accessed: Nov. 7, 2023."},{"key":"2024110207213604054_j_itit-2024-0028_ref_030","unstructured":"M. Studt, \u201cA practical and critical guide to the unicode blocks \u00bbcuneiform\u00ab and \u00bbcuneiform numbers\u00ab of unicode standard version 5.0,\u201d 2007. Available at: http:\/\/www.sumerisches-glossar.de\/download\/SignListNeoAssyrian.pdf."},{"key":"2024110207213604054_j_itit-2024-0028_ref_032","unstructured":"R. Borger, Assyrisch-babylonische Zeichenliste, Neukirchen-Vluyn, Ugarit-Verlag, 1988."},{"key":"2024110207213604054_j_itit-2024-0028_ref_008","doi-asserted-by":"crossref","unstructured":"J. Johnson and T. Khoshgoftaar, \u201cSurvey on deep learning with class imbalance,\u201d J. Big Data, vol. 6, no. 1, 2019. https:\/\/doi.org\/10.1186\/s40537-019-0192-5.","DOI":"10.1186\/s40537-019-0192-5"},{"key":"2024110207213604054_j_itit-2024-0028_ref_010","unstructured":"Y. Zhu, J. Chen, L. Liang, Z. Kuang, L. Jin, and W. Zhang, \u201cFourier contour embedding for arbitrary-shaped text detection,\u201d CoRR. abs\/2104.10442, 2021, https:\/\/arxiv.org\/abs\/2104.10442."},{"key":"2024110207213604054_j_itit-2024-0028_ref_020","doi-asserted-by":"crossref","unstructured":"D. Karatzas, et al.., \u201cICDAR 2015 competition on robust reading,\u201d in Proceedings Of The 2015 13th International Conference on Document Analysis And Recognition (ICDAR), 2015, pp.\u00a01156\u20131160.","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"2024110207213604054_j_itit-2024-0028_ref_015","unstructured":"Y. Liu, L. Jin, S. Zhang, and S. Zhang, \u201cDetecting curve text in the wild: new dataset and new solution,\u201d CoRR. abs\/1712.02170, 2017, http:\/\/arxiv.org\/abs\/1712.02170."},{"key":"2024110207213604054_j_itit-2024-0028_ref_019","unstructured":"C. Chng and C. Chan, \u201cTotal-text: a comprehensive dataset for scene text detection and recognition,\u201d CoRR. abs\/1710.10400, 2017, http:\/\/arxiv.org\/abs\/1710.10400."},{"key":"2024110207213604054_j_itit-2024-0028_ref_003","unstructured":"MMOCR FceNet Implementation. Available at: https:\/\/github.com\/open-mmlab\/mmocr\/tree\/main\/configs\/textdet\/fcenet Accessed: Nov. 7, 2023."},{"key":"2024110207213604054_j_itit-2024-0028_ref_011","unstructured":"M. Tan and Q. Le, \u201cEfficientNet: rethinking model scaling for convolutional neural networks,\u201d in Proceedings of The 36th International Conference on Machine Learning, ICML 2019, 9\u201315 June 2019, Long Beach, California, USA, vol.\u00a097, 2019, pp.\u00a06105\u20136114. Available at: http:\/\/proceedings.mlr.press\/v97\/tan19a.html."},{"key":"2024110207213604054_j_itit-2024-0028_ref_004","unstructured":"MMCLS EfficientNet Implementation. Available at: https:\/\/github.com\/open-mmlab\/mmpretrain\/tree\/mmcls-1.x\/configs\/efficientnet Accessed: Nov. 7, 2023."},{"key":"2024110207213604054_j_itit-2024-0028_ref_005","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, \u201cDeformable DETR: deformable transformers for end-to-end object detection,\u201d in International Conference On Learning Representations, 2021. Available at: https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke."},{"key":"2024110207213604054_j_itit-2024-0028_ref_002","doi-asserted-by":"crossref","unstructured":"N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, \u201cEnd-to-end object detection with transformers,\u201d in Computer Vision \u2013 ECCV 2020 \u2013 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I. 12346, 2020, pp.\u00a0213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2024110207213604054_j_itit-2024-0028_ref_039","unstructured":"MMDetection Object Detection Toolbox. Available at: https:\/\/github.com\/open-mmlab\/mmdetection Accessed: May 27, 2024."}],"container-title":["it - Information Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/itit-2024-0028\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/itit-2024-0028\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T07:21:55Z","timestamp":1730532115000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/itit-2024-0028\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,1]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,10,30]]},"published-print":{"date-parts":[[2024,2,26]]}},"alternative-id":["10.1515\/itit-2024-0028"],"URL":"https:\/\/doi.org\/10.1515\/itit-2024-0028","relation":{},"ISSN":["1611-2776","2196-7032"],"issn-type":[{"value":"1611-2776","type":"print"},{"value":"2196-7032","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,1]]}}}