{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:33:40Z","timestamp":1743129220543,"version":"3.40.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602758"},{"type":"electronic","value":"9783030602765"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60276-5_17","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"166-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Automated Pipeline for Robust Image Processing and Optical Character Recognition of Historical Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2333-433X","authenticated-orcid":false,"given":"Ivan","family":"Gruber","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6967-1687","authenticated-orcid":false,"given":"Pavel","family":"Ircing","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5788-604X","authenticated-orcid":false,"given":"Petr","family":"Neduchal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7851-9879","authenticated-orcid":false,"given":"Marek","family":"Hr\u00faz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-930X","authenticated-orcid":false,"given":"Miroslav","family":"Hlav\u00e1\u010d","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4153-6560","authenticated-orcid":false,"given":"Zbyn\u011bk","family":"Zaj\u00edc","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8362-5927","authenticated-orcid":false,"given":"Jan","family":"\u0160vec","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0276-3143","authenticated-orcid":false,"given":"Martin","family":"Bul\u00edn","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"issue":"6","key":"17_CR1","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.15622\/sp.2019.18.6.1381-1406","volume":"18","author":"L Bure\u0161","year":"2019","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. SPIIRAS Proc. 18(6), 1381\u20131406 (2019)","journal-title":"SPIIRAS Proc."},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-26061-3_15","volume-title":"Speech and Computer","author":"I Gruber","year":"2019","unstructured":"Gruber, I., Hlav\u00e1\u010d, M., Hr\u00faz, M., \u017delezn\u00fd, M.: Semantic segmentation of historical documents via fully-convolutional neural network. In: Salah, A.A., Karpov, A., Potapova, R. (eds.) SPECOM 2019. LNCS (LNAI), vol. 11658, pp. 142\u2013149. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-26061-3_15"},{"key":"17_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"},{"key":"17_CR5","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 (2020)","DOI":"10.1145\/3340531.3412767"},{"key":"17_CR6","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.1007\/978-0-387-39940-9_3032","volume-title":"Encyclopedia of Database Systems","author":"L Liu","year":"2009","unstructured":"Liu, L., \u00d6zsu, M.T.: Mean average precision. In: Liu, L., \u00d6zsu, M.T. (eds.) Encyclopedia of Database Systems, p. 1703. Springer, Boston (2009). https:\/\/doi.org\/10.1007\/978-0-387-39940-9_3032"},{"issue":"1","key":"17_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/1687-4722-2011-10","volume":"2011","author":"J Psutka","year":"2011","unstructured":"Psutka, J., et al.: System for fast lexical and phonetic spoken term detection in a Czech cultural heritage archive. EURASIP J. Audio Speech Music Process. 2011(1), 10 (2011)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"17_CR8","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 (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"17_CR9","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"17_CR10","unstructured":"Zaj\u00edc, Z., et al.: Towards processing of the oral history interviews and related printed documents. In: Proceedings of LREC 2018, pp. 2099\u20132104 (2018)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE, September 2019","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T02:07:19Z","timestamp":1617674839000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","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":"160","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":"65","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":"41% - 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","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","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":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","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)"}}]}}