{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T12:10:57Z","timestamp":1754395857255,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031416842"},{"type":"electronic","value":"9783031416859"}],"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\/978-3-031-41685-9_7","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T14:04:59Z","timestamp":1692367499000},"page":"101-115","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["OCR Language Models with\u00a0Custom Vocabularies"],"prefix":"10.1007","author":[{"given":"Peter","family":"Garst","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reeve","family":"Ingle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhisa","family":"Fujii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"issue":"43","key":"7_CR1","first-page":"1","volume":"180","author":"AS Agbemenu","year":"2018","unstructured":"Agbemenu, A.S., Yankey, J., Addo, E.O.: An automatic number plate recognition system using OPENCV and tesseract OCR engine. Int. J. Comput. Appl. 180(43), 1\u20135 (2018)","journal-title":"Int. J. Comput. Appl."},{"issue":"6","key":"7_CR2","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1145\/360825.360855","volume":"18","author":"AV Aho","year":"1975","unstructured":"Aho, A.V., Corasick, M.J.: Efficient string matching: an aid to bibliographic search. Commun. ACM 18(6), 333\u2013340 (1975)","journal-title":"Commun. ACM"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-540-76336-9_3","volume-title":"Implementation and Application of Automata","author":"C Allauzen","year":"2007","unstructured":"Allauzen, C., Riley, M., Schalkwyk, J., Skut, W., Mohri, M.: OpenFst: A General and Efficient Weighted Finite-State Transducer Library. In: Holub, J., \u017d\u010f\u00e1rek, J. (eds.) CIAA 2007. LNCS, vol. 4783, pp. 11\u201323. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-76336-9_3"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Bissacco, A., Cummins, M., Netzer, Y., Neven, H.: Photoocr: reading text in uncontrolled conditions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 785\u2013792 (2013)","DOI":"10.1109\/ICCV.2013.102"},{"issue":"7","key":"7_CR5","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/5.156470","volume":"80","author":"M Bokser","year":"1992","unstructured":"Bokser, M.: Omni document technologies. Proc. IEEE 80(7), 1066\u20131078 (1992)","journal-title":"Proc. IEEE"},{"issue":"4","key":"7_CR6","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1109\/TSA.2005.860838","volume":"14","author":"D Caseiro","year":"2006","unstructured":"Caseiro, D., Trancoso, I.: A specialized on-the-fly algorithm for lexicon and language model composition. IEEE Trans. Audio Speech Lang. Process. 14(4), 1281\u20131291 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-696"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chin, F., Wu, F.: A microprocessor-based optical character recognition check reader. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 2, pp. 982\u2013985. IEEE (1995)","DOI":"10.1109\/ICDAR.1995.602066"},{"key":"7_CR9","unstructured":"Diaz, D.H., Qin, S., Ingle, R., Fujii, Y., Bissacco, A.: Rethinking text line recognition models. arXiv preprint arXiv:2104.07787 (2021)"},{"key":"7_CR10","unstructured":"Dodge, J., Ilharco, G., Schwartz, R., Farhadi, A., Hajishirzi, H., Smith, N.: Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv preprint arXiv:2002.06305 (2020)"},{"issue":"2","key":"7_CR11","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1109\/TCSVT.2012.2203741","volume":"23","author":"S Du","year":"2013","unstructured":"Du, S., Ibrahim, M., Shehata, M., Badawy, W.: Automatic license plate recognition (ALPR): a state-of-the-art review. IEEE Trans. Circuits Syst. Video Technol. 23(2), 311\u2013325 (2013). https:\/\/doi.org\/10.1109\/TCSVT.2012.2203741","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Fujii, Y., Genzel, D., Popat, A.C., Teunen, R.: Label transition and selection pruning and automatic decoding parameter optimization for time-synchronous Viterbi decoding. In: Proceedings of the 13th International Conference on Document Analysis and Recognition, pp. 756\u2013760. IEEE, August 2015","DOI":"10.1109\/ICDAR.2015.7333863"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Golovin, D., Solnik, B., Moitra, S., Kochanski, G., Karro, J.E., Sculley, D. (eds.): Google Vizier: A Service for Black-Box Optimization (2017). http:\/\/www.kdd.org\/kdd2017\/papers\/view\/google-vizier-a-service-for-black-box-optimization","DOI":"10.1145\/3097983.3098043"},{"key":"7_CR14","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: ICML (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"4","key":"7_CR15","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1002\/j.1538-7305.1995.tb00189.x","volume":"74","author":"LD Jackel","year":"1995","unstructured":"Jackel, L.D., Sharman, D., Stenard, C.E., Strom, B.I., Zuckert, D.: Optical character recognition for self-service banking. AT &T Techn. J. 74(4), 16\u201324 (1995). https:\/\/doi.org\/10.1002\/j.1538-7305.1995.tb00189.x","journal-title":"AT &T Techn. J."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Jelinek, F., Merialdo, B., Roukos, S., Strauss, M.: A dynamic language model for speech recognition. In: Speech and Natural Language: Proceedings of a Workshop Held at Pacific Grove, California, February 19\u201322, 1991 (1991)","DOI":"10.3115\/112405.112464"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Lee, T.H.: Generalized aho-corasick algorithm for signature based anti-virus applications. In: 16th International Conference on Computer Communications and Networks, pp. 792\u2013797. IEEE (2007)","DOI":"10.1109\/ICCCN.2007.4317914"},{"issue":"1","key":"7_CR18","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy, G.: Twenty years of document image analysis in pami. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 38\u201362 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Neat, L., Peng, R., Qin, S., Manduchi, R.: Scene text access: a comparison of mobile OCR modalities for blind users. In: Proceedings of the 24th International Conference on Intelligent User Interfaces, pp. 197\u2013207 (2019)","DOI":"10.1145\/3301275.3302271"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Sabir, E., Rawls, S., Natarajan, P.: Implicit language model in LSTM for OCR. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 7, pp. 27\u201331. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.361"},{"issue":"D1","key":"7_CR21","doi-asserted-by":"publisher","first-page":"D10","DOI":"10.1093\/nar\/gkaa892","volume":"49","author":"EW Sayers","year":"2021","unstructured":"Sayers, E.W., et al.: Database resources of the national center for biotechnology information. Nucleic Acids Res. 49(D1), D10 (2021)","journal-title":"Nucleic Acids Res."},{"issue":"7383","key":"7_CR22","first-page":"41","volume":"2","author":"H Shen","year":"2012","unstructured":"Shen, H., Coughlan, J.M.: Towards a real-time system for finding and reading signs for visually impaired users. ICCHP 2(7383), 41\u201347 (2012)","journal-title":"ICCHP"},{"key":"7_CR23","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":"7_CR24","doi-asserted-by":"crossref","unstructured":"Smith, R.: Limits on the application of frequency-based language models to OCR. In: 2011 International Conference on Document Analysis and Recognition, pp. 538\u2013542. IEEE (2011)","DOI":"10.1109\/ICDAR.2011.114"},{"key":"7_CR25","unstructured":"Taylor, O.: Pango, an open-source unicode text layout engine (2004)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Thakare, S., Kamble, A., Thengne, V., Kamble, U.: Document segmentation and language translation using tesseract-OCR. In: 2018 IEEE 13th International Conference on Industrial and Information Systems (ICIIS), pp. 148\u2013151. IEEE (2018)","DOI":"10.1109\/ICIINFS.2018.8721372"},{"key":"7_CR27","unstructured":"Walker, J., Fujii, Y., Popat, A.C.: A web-based OCR service for documents. In: Proceedings of the 13th IAPR International Workshop on Document Analysis Systems (DAS), Vienna, Austria, vol. 1 (2018)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"White, J.: Pubmed 2.0. Medical reference services quarterly 39(4), 382\u2013387 (2020)","DOI":"10.1080\/02763869.2020.1826228"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Yan, A., McAuley, J., Lu, X., Du, J., Chang, E.Y., Gentili, A., Hsu, C.N.: Radbert: adapting transformer-based language models to radiology. Radiol. Artif. Intell. 4(4), e210258 (2022)","DOI":"10.1148\/ryai.210258"},{"key":"7_CR30","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: recent advances and future trends. Front. Comp. Sci. 10, 19\u201336 (2016)","journal-title":"Front. Comp. Sci."}],"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\/978-3-031-41685-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T10:35:41Z","timestamp":1729938941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41685-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416842","9783031416859"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41685-9_7","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)"}}]}}