{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T16:41:40Z","timestamp":1771260100675,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030878016","type":"print"},{"value":"9783030878023","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_21","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"226-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["OCR Improvements for Images of Multi-page Historical Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2333-433X","authenticated-orcid":false,"given":"Ivan","family":"Gruber","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7851-9879","authenticated-orcid":false,"given":"Marek","family":"Hr\u00faz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6967-1687","authenticated-orcid":false,"given":"Pavel","family":"Ircing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5788-604X","authenticated-orcid":false,"given":"Petr","family":"Neduchal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6798-1494","authenticated-orcid":false,"given":"Tom\u00e1\u0161","family":"Z\u00edtka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-930X","authenticated-orcid":false,"given":"Miroslav","family":"Hlav\u00e1\u010d","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4153-6560","authenticated-orcid":false,"given":"Zbyn\u011bk","family":"Zaj\u00edc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8362-5927","authenticated-orcid":false,"given":"Jan","family":"\u0160vec","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0276-3143","authenticated-orcid":false,"given":"Martin","family":"Bul\u00edn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Bure\u0161, L., Gruber, I., Neduchal, P., Hlav\u00e1\u010d, M., Hr\u00faz, M.: Semantic text segmentation from synthetic images of full-text documents (2019)","DOI":"10.15622\/sp.2019.18.6.1381-1406"},{"key":"21_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-030-60276-5_9","volume-title":"Speech and Computer","author":"L Bure\u0161","year":"2020","unstructured":"Bure\u0161, L., Neduchal, P., M\u00fcller, L.: Automatic information extraction from scanned documents. In: Karpov, A., Potapova, R. (eds.) SPECOM 2020. LNCS (LNAI), vol. 12335, pp. 87\u201396. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60276-5_9"},{"key":"21_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1007\/978-3-030-60276-5_17","volume-title":"Speech and Computer","author":"I Gruber","year":"2020","unstructured":"Gruber, I., et al.: An automated pipeline for robust image processing and optical character recognition of historical documents. In: Karpov, A., Potapova, R. (eds.) SPECOM 2020. LNCS (LNAI), vol. 12335, pp. 166\u2013175. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60276-5_17"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"21_CR5","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."},{"key":"21_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"21_CR7","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Kodym, O., Hradi\u0161, M.: Page layout analysis system for unconstrained historic documents. arXiv preprint arXiv:2102.11838 (2021)","DOI":"10.1007\/978-3-030-86331-9_32"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Koh\u00fat, J., Hradi\u0161, M.: TS-Net: OCR trained to switch between text transcription styles. arXiv preprint arXiv:2103.05489 (2021)","DOI":"10.1007\/978-3-030-86337-1_32"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Lee, B.C.G., et al.: The newspaper navigator dataset: extracting and analyzing visual content from 16 million historic newspaper pages in chronicling America. arXiv preprint arXiv:2005.01583 (2020)","DOI":"10.1145\/3340531.3412767"},{"key":"21_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-030-54956-5_17","volume-title":"Digital Libraries for Open Knowledge","author":"C Lehenmeier","year":"2020","unstructured":"Lehenmeier, C., Burghardt, M., Mischka, B.: Layout detection and table recognition \u2013 recent challenges in digitizing historical documents and handwritten tabular data. In: Hall, M., Mer\u010dun, T., Risse, T., Duchateau, F. (eds.) TPDL 2020. LNCS, vol. 12246, pp. 229\u2013242. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-54956-5_17"},{"issue":"1","key":"21_CR12","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s12530-020-09343-4","volume":"12","author":"L Lenc","year":"2020","unstructured":"Lenc, L., Mart\u00ednek, J., Kr\u00e1l, P., Nicolao, A., Christlein, V.: HDPA: historical document processing and analysis framework. Evol. Syst. 12(1), 177\u2013190 (2020). https:\/\/doi.org\/10.1007\/s12530-020-09343-4","journal-title":"Evol. Syst."},{"key":"21_CR13","unstructured":"Poncelas, A., Aboomar, M., Buts, J., Hadley, J., Way, A.: A tool for facilitating OCR postediting in historical documents. arXiv preprint arXiv:2004.11471 (2020)"},{"issue":"6","key":"21_CR14","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Shen, Z., Zhang, R., Dell, M., Lee, B.C.G., Carlson, J., Li, W.: Layout-parser: a unified toolkit for deep learning based document image analysis. arXiv preprint arXiv:2103.15348 (2021)","DOI":"10.1007\/978-3-030-86549-8_9"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol 2, pp. 629\u2013633. IEEE, Curitiba, September 2007. iSSN: 1520\u20135363","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Smith, R., Antonova, D., Lee, D.S.: Adapting the tesseract open source OCR engine for multilingual OCR. In: Proceedings of the International Workshop on Multilingual OCR, pp. 1\u20138 (2009)","DOI":"10.1145\/1577802.1577804"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"V\u00f6gtlin, L., Drazyk, M., Pondenkandath, V., Alberti, M., Ingold, R.: Generating synthetic handwritten historical documents with OCR constrained GANs. arXiv preprint arXiv:2103.08236 (2021)","DOI":"10.1007\/978-3-030-86334-0_40"},{"key":"21_CR19","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"21_CR20","unstructured":"Zaj\u00edc, Z., et al.: Towards processing of the oral history interviews and related printed documents. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:43:10Z","timestamp":1632267790000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","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)"}}]}}