{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:42:01Z","timestamp":1767339721437,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031417337"},{"type":"electronic","value":"9783031417344"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41734-4_21","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T07:02:59Z","timestamp":1692342179000},"page":"342-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Combining OCR Models for\u00a0Reading Early Modern Books"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9153-1031","authenticated-orcid":false,"given":"Mathias","family":"Seuret","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7486-669X","authenticated-orcid":false,"given":"Janne","family":"van der Loop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8065-0390","authenticated-orcid":false,"given":"Nikolaus","family":"Weichselbaumer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3706-285X","authenticated-orcid":false,"given":"Martin","family":"Mayr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4729-0933","authenticated-orcid":false,"given":"Janina","family":"Molnar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1254-3403","authenticated-orcid":false,"given":"Tatjana","family":"Hass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0455-3799","authenticated-orcid":false,"given":"Vincent","family":"Christlein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Bjerring-Hansen, J., Kristensen-McLachlan, R.D., Diderichsen, P., Hansen, D.H.: Mending Fractured Texts. A Heuristic Procedure for Correcting OCR Data. CEUR-WS (2022)","key":"21_CR1","DOI":"10.5617\/dhnbpub.11285"},{"doi-asserted-by":"publisher","unstructured":"Bluche, T., Messina, R.: Gated convolutional recurrent neural networks for multilingual handwriting recognition. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 646\u2013651 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.111","key":"21_CR2","DOI":"10.1109\/ICDAR.2017.111"},{"unstructured":"Breul, T.: ocrodeg: document image degradation - github.com (2020). https:\/\/github.com\/NVlabs\/ocrodeg. Accessed 10 Feb 2023","key":"21_CR3"},{"doi-asserted-by":"crossref","unstructured":"Chen, J., Mu, S., Xu, S., Ding, Y.: HENet: forcing a network to think more for font recognition. In: 3rd International Conference on Advanced Information Science and System (AISS), pp. 1\u20135 (2021)","key":"21_CR4","DOI":"10.1145\/3503047.3503055"},{"key":"21_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/978-3-030-86334-0_5","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"D Coquenet","year":"2021","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: SPAN: a simple predict & align network for handwritten paragraph recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12823, pp. 70\u201384. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_5"},{"key":"21_CR6","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TPAMI.2022.3144899","volume":"45","author":"D Coquenet","year":"2022","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. 45, 508\u2013524 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2022.3144899","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"publisher","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network. In: 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 19\u201324 (2020). https:\/\/doi.org\/10.1109\/ICFHR2020.2020.00015","key":"21_CR7","DOI":"10.1109\/ICFHR2020.2020.00015"},{"doi-asserted-by":"publisher","unstructured":"Diaz, D.H., Qin, S., Ingle, R., Fujii, Y., Bissacco, A.: Rethinking text line recognition models (2021). https:\/\/doi.org\/10.48550\/ARXIV.2104.07787. https:\/\/arxiv.org\/abs\/2104.07787","key":"21_CR8","DOI":"10.48550\/ARXIV.2104.07787"},{"unstructured":"Fossey, R., Baird, H.: A 100 font classifier. In: 1st IAPR International Conference on Document Analysis and Recognition (ICDAR) (1991)","key":"21_CR9"},{"issue":"10","key":"21_CR10","first-page":"658","volume":"62","author":"K Fukushima","year":"1979","unstructured":"Fukushima, K.: Neural network model for a mechanism of pattern recognition unaffected by shift in position - neocognitron. IEICE Tech. Rep. A 62(10), 658\u2013665 (1979)","journal-title":"IEICE Tech. Rep. A"},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","key":"21_CR11","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"publisher","unstructured":"Grosicki, E., El-Abed, H.: ICDAR 2011 - French handwriting recognition competition. In: 11th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 1459\u20131463 (2011). https:\/\/doi.org\/10.1109\/ICDAR.2011.290","key":"21_CR12","DOI":"10.1109\/ICDAR.2011.290"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"21_CR13","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"21_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","key":"21_CR15","DOI":"10.1109\/CVPR.2017.243"},{"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","key":"21_CR16","DOI":"10.1016\/j.patcog.2022.108766"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"21_CR17"},{"key":"21_CR18","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I., et al.: Binary codes capable of correcting deletions, insertions, and reversals. Sov. Phys. Dokl. 10, 707\u2013710 (1966)","journal-title":"Sov. Phys. Dokl."},{"doi-asserted-by":"publisher","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models (2021). https:\/\/doi.org\/10.48550\/ARXIV.2109.10282. https:\/\/arxiv.org\/abs\/2109.10282","key":"21_CR19","DOI":"10.48550\/ARXIV.2109.10282"},{"doi-asserted-by":"publisher","unstructured":"Lyu, P., et al.: MaskOCR: text recognition with masked encoder-decoder pretraining (2022). https:\/\/doi.org\/10.48550\/ARXIV.2206.00311. https:\/\/arxiv.org\/abs\/2206.00311","key":"21_CR20","DOI":"10.48550\/ARXIV.2206.00311"},{"issue":"1","key":"21_CR21","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). https:\/\/doi.org\/10.1007\/s100320200071","journal-title":"Int. J. Doc. Anal. Recogn."},{"doi-asserted-by":"publisher","unstructured":"Michael, J., Labahn, R., Gr\u00fcning, T., Z\u00f6llner, J.: Evaluating sequence-to-sequence models for handwritten text recognition. In: 15th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 1286\u20131293 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00208","key":"21_CR22","DOI":"10.1109\/ICDAR.2019.00208"},{"doi-asserted-by":"crossref","unstructured":"Nicolaou, A., Slimane, F., Maergner, V., Liwicki, M.: Local binary patterns for Arabic optical font recognition. In: 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 76\u201380. IEEE (2014)","key":"21_CR23","DOI":"10.1109\/DAS.2014.71"},{"issue":"7","key":"21_CR24","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","volume":"24","author":"T Ojala","year":"2002","unstructured":"Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971\u2013987 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"publisher","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 67\u201372 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.20","key":"21_CR25","DOI":"10.1109\/ICDAR.2017.20"},{"doi-asserted-by":"publisher","unstructured":"Reul, C., Springmann, U., Wick, C., Puppe, F.: Improving OCR accuracy on early printed books by utilizing cross fold training and voting. In: 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 423\u2013428 (2018). https:\/\/doi.org\/10.1109\/DAS.2018.30","key":"21_CR26","DOI":"10.1109\/DAS.2018.30"},{"doi-asserted-by":"crossref","unstructured":"Seuret, M., Limbach, S., Weichselbaumer, N., Maier, A., Christlein, V.: Dataset of pages from early printed books with multiple font groups. In: 15th International Workshop on Historical Document Imaging and Processing (HIP), pp. 1\u20136 (2019)","key":"21_CR27","DOI":"10.1145\/3352631.3352640"},{"doi-asserted-by":"crossref","unstructured":"Springmann, U., Reul, C., Dipper, S., Baiter, J.: Ground truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin. arXiv preprint arXiv:1809.05501 (2018)","key":"21_CR28","DOI":"10.21248\/jlcl.33.2018.220"},{"doi-asserted-by":"crossref","unstructured":"Tensmeyer, C., Saunders, D., Martinez, T.: Convolutional neural networks for font classification. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 985\u2013990. IEEE (2017)","key":"21_CR29","DOI":"10.1109\/ICDAR.2017.164"},{"unstructured":"TorchVision maintainers and contributors: TorchVision: PyTorch\u2019s Computer Vision library (2016). https:\/\/github.com\/pytorch\/vision","key":"21_CR30"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf","key":"21_CR31"},{"key":"21_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-030-86549-8_25","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"C Wick","year":"2021","unstructured":"Wick, C., Reul, C.: One-model ensemble-learning for text recognition of historical printings. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 385\u2013399. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_25"},{"key":"21_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/978-3-030-86334-0_8","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"C Wick","year":"2021","unstructured":"Wick, C., Z\u00f6llner, J., Gr\u00fcning, T.: Transformer for handwritten text recognition using bidirectional post-decoding. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12823, pp. 112\u2013126. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86334-0_8"},{"key":"21_CR34","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/978-3-031-06555-2_18","volume-title":"15th IAPR International Workshop on Document Analysis Systems (DAS)","author":"C Wick","year":"2022","unstructured":"Wick, C., Z\u00f6llner, J., Gr\u00fcning, T.: Rescoring sequence-to-sequence models for text line recognition with CTC-prefixes. In: Uchida, S., Barney, E., Eglin, V. (eds.) 15th IAPR International Workshop on Document Analysis Systems (DAS), pp. 260\u2013274. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_18"},{"key":"21_CR35","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10032-019-00337-w","volume":"22","author":"J Yang","year":"2019","unstructured":"Yang, J., Kim, H., Kwak, H., Kim, I.: HanFont: large-scale adaptive hangul font recognizer using CNN and font clustering. Int. J. Doc. Anal. Recogn. (IJDAR) 22, 407\u2013416 (2019)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"21_CR36","doi-asserted-by":"publisher","first-page":"107482","DOI":"10.1016\/j.patcog.2020.107482","volume":"108","author":"M Yousef","year":"2020","unstructured":"Yousef, M., Hussain, K.F., Mohammed, U.S.: Accurate, data-efficient, unconstrained text recognition with convolutional neural networks. Pattern Recogn. 108, 107482 (2020). https:\/\/doi.org\/10.1016\/j.patcog.2020.107482","journal-title":"Pattern Recogn."}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41734-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T09:39:07Z","timestamp":1729935547000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41734-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417337","9783031417344"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41734-4_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","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":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}