{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:29:12Z","timestamp":1757611752909,"version":"3.44.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030865481"},{"type":"electronic","value":"9783030865498"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86549-8_31","type":"book-chapter","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T02:05:57Z","timestamp":1630721157000},"page":"481-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Unknown-Box Approximation to Improve Optical Character Recognition Performance"],"prefix":"10.1007","author":[{"given":"Ayantha","family":"Randika","sequence":"first","affiliation":[]},{"given":"Nilanjan","family":"Ray","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Allegra","family":"Latimer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"31_CR1","doi-asserted-by":"publisher","unstructured":"Artaud, C., Sid\u00e8re, N., Doucet, A., Ogier, J., Yooz, V.P.D.: Find it! fraud detection contest report. In: ICPR, pp. 13\u201318 (2018). https:\/\/doi.org\/10.1109\/ICPR.2018.8545428","DOI":"10.1109\/ICPR.2018.8545428"},{"key":"31_CR2","doi-asserted-by":"publisher","unstructured":"Bieniecki, W., Grabowski, S., Rozenberg, W.: Image preprocessing for improving OCR accuracy. In: 2007 International Conference on Perspective Technologies and Methods in MEMS Design, pp. 75\u201380 (2007). https:\/\/doi.org\/10.1109\/MEMSTECH.2007.4283429","DOI":"10.1109\/MEMSTECH.2007.4283429"},{"key":"31_CR3","doi-asserted-by":"publisher","unstructured":"Buda, M., Saha, A., Mazurowski, M.A.: Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm. Comput. Biol. Med. 109, 218\u2013225 (2019). https:\/\/doi.org\/10.1016\/j.compbiomed.2019.05.002","DOI":"10.1016\/j.compbiomed.2019.05.002"},{"key":"31_CR4","doi-asserted-by":"publisher","unstructured":"Chen, Q., Sun, Q.S, Heng, P.A., Shen Xia, D.: A double-threshold image binarization method based on edge detector. Patt. Recogn. 41, 1254\u20131267 (2008). https:\/\/doi.org\/10.1016\/j.patcog.2007.09.007","DOI":"10.1016\/j.patcog.2007.09.007"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Shao, Y.: Scene text recognition based on deep learning: a brief survey. In: ICCSN (2019)","DOI":"10.1109\/ICCSN.2019.8905316"},{"key":"31_CR6","doi-asserted-by":"publisher","unstructured":"Garain, U., Jain, A., Maity, A., Chanda, B.: Machine reading of camera-held low quality text images: an ICA-based image enhancement approach for improving OCR accuracy. In: ICPR, pp. 1\u20134 (2008). https:\/\/doi.org\/10.1109\/ICPR.2008.4761840","DOI":"10.1109\/ICPR.2008.4761840"},{"key":"31_CR7","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ACM International Conference Proceeding Series, vol. 148, pp. 369\u2013376. ACM Press (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"31_CR8","doi-asserted-by":"publisher","unstructured":"Harraj, A.E., Raissouni, N.: OCR accuracy improvement on document images through a novel pre-processing approach. Signal Image Process. Int. J. 6, 01\u201318 (2015). https:\/\/doi.org\/10.5121\/sipij.2015.6401","DOI":"10.5121\/sipij.2015.6401"},{"key":"31_CR9","doi-asserted-by":"publisher","unstructured":"He, S., Schomaker, L.: DeepOtsu: document enhancement and binarization using iterative deep learning. Patt. Recogn. 91, 379\u2013390 (2019). https:\/\/doi.org\/10.1016\/j.patcog.2019.01.025","DOI":"10.1016\/j.patcog.2019.01.025"},{"key":"31_CR10","doi-asserted-by":"publisher","unstructured":"Hicks, J.R., Eby Jr, J.C.: Signal processing techniques in commercially available high-speed optical character reading equipment. In: Tao, T.F. (ed.) Real-Time Signal Processing II, vol. 0180, pp. 205\u2013216. SPIE (1979). https:\/\/doi.org\/10.1117\/12.957332","DOI":"10.1117\/12.957332"},{"key":"31_CR11","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/0893-6080(90)90005-6","volume":"3","author":"K Hornik","year":"1990","unstructured":"Hornik, K., Stinchcombe, M.B., White, H.: Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Netw. 3, 551\u2013560 (1990)","journal-title":"Neural Netw."},{"key":"31_CR12","doi-asserted-by":"publisher","unstructured":"Huang, Z., et al.: ICDAR 2019 competition on scanned receipt OCR and information extraction. In: ICDAR, pp. 1516\u20131520 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00244","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"31_CR13","unstructured":"Jacovi, A., et al.: Neural network gradient-based learning of black-box function interfaces. In: ICLR. arXiv (2019)"},{"key":"31_CR14","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. In: Workshop on Deep Learning, NIPS (2014)"},{"key":"31_CR15","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1109\/34.406659","volume":"17","author":"L Lam","year":"1995","unstructured":"Lam, L., Suen, C.Y.: An evaluation of parallel thinning algorithms for character recognition. IEEE Trans. Pattern Anal. Mach. Intell. 17, 914\u2013919 (1995). https:\/\/doi.org\/10.1109\/34.406659","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR16","doi-asserted-by":"publisher","unstructured":"Lat, A., Jawahar, C.V.: Enhancing OCR accuracy with super resolution. In: ICPR, pp. 3162\u20133167 (2018). https:\/\/doi.org\/10.1109\/ICPR.2018.8545609","DOI":"10.1109\/ICPR.2018.8545609"},{"key":"31_CR17","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet Physics. Doklady, vol. 10, pp. 707\u2013710 (1965)"},{"key":"31_CR18","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"31_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Y., Feinrich, R., Srihari, S.N.: An object attribute thresholding algorithm for document image binarization. In: ICDAR, pp. 278\u2013281 (1993). https:\/\/doi.org\/10.1109\/ICDAR.1993.395732","DOI":"10.1109\/ICDAR.1993.395732"},{"key":"31_CR20","unstructured":"Mohamed, S., Rosca, M., Figurnov, M., Mnih, A.: Monte Carlo gradient estimation in machine learning. J. Mach. Learn. Res. 21, 1\u201363 (2019). http:\/\/arxiv.org\/abs\/1906.10652"},{"key":"31_CR21","doi-asserted-by":"publisher","unstructured":"Chang, M.S., Kang, S.M., Rho, W.S., Kim, H.G., Kim, D.J.: Improved binarization algorithm for document image by histogram and edge detection. In: ICDAR, vol. 2, pp. 636\u2013639 (1995). https:\/\/doi.org\/10.1109\/ICDAR.1995.601976","DOI":"10.1109\/ICDAR.1995.601976"},{"key":"31_CR22","unstructured":"Nguyen, N.M., Ray, N.: End-to-end learning of convolutional neural net and dynamic programming for left ventricle segmentation. In: Proceedings of Machine Learning Research, vol. 121, pp. 555\u2013569. PMLR (2020)"},{"key":"31_CR23","doi-asserted-by":"publisher","unstructured":"Ogorman, L.: Binarization and multithresholding of document images using connectivity. CVGIP: Graph. Mod. Image Process. 56, 494\u2013506 (1994). https:\/\/doi.org\/10.1006\/cgip.1994.1044","DOI":"10.1006\/cgip.1994.1044"},{"key":"31_CR24","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62\u201366 (1979)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"31_CR25","unstructured":"Park, S., et al.: CORD: a consolidated receipt dataset for post-OCR parsing. In: Workshop on Document Intelligence at NeurIPS 2019 (2019). https:\/\/openreview.net\/forum?id=SJl3z659UH"},{"key":"31_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-030-57058-3_11","volume-title":"Document Analysis Systems","author":"X Peng","year":"2020","unstructured":"Peng, X., Wang, C.: Building super-resolution image generator for OCR accuracy improvement. In: Bai, X., Karatzas, D., Lopresti, D. (eds.) DAS 2020. LNCS, vol. 12116, pp. 145\u2013160. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57058-3_11"},{"key":"31_CR27","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: 2018 13th IAPR International Workshop on Document Analysis Systems, pp. 423\u2013428 (2018).https:\/\/doi.org\/10.1109\/DAS.2018.30","DOI":"10.1109\/DAS.2018.30"},{"key":"31_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"31_CR29","doi-asserted-by":"publisher","unstructured":"Saha, P.K., Borgefors, G., di Baja, G.S.: Chapter 1 - skeletonization and its applications - a review. In: Saha, P.K., Borgefors, G., di Baja, G.S. (eds.) Skeletonization, pp. 3\u201342. Academic Press (2017). https:\/\/doi.org\/10.1016\/B978-0-08-101291-8.00002-X","DOI":"10.1016\/B978-0-08-101291-8.00002-X"},{"key":"31_CR30","unstructured":"Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning (2017)"},{"key":"31_CR31","doi-asserted-by":"publisher","unstructured":"Sauvola, J., Pietik\u00e4inen, M.: Adaptive document image binarization. Patt. Recogn. 33, 225\u2013236 (2000). https:\/\/doi.org\/10.1016\/S0031-3203(99)00055-2","DOI":"10.1016\/S0031-3203(99)00055-2"},{"key":"31_CR32","doi-asserted-by":"publisher","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Patt. Anal. Mach. Intell. 39, 2298\u20132304 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2646371","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"31_CR33","doi-asserted-by":"publisher","unstructured":"Sporici, D., Cu\u015fnir, E., Boiangiu, C.A.: Improving the accuracy of tesseract 4.0 OCR engine using convolution-based preprocessing. Symmetry 12, 715 (2020). https:\/\/doi.org\/10.3390\/SYM12050715","DOI":"10.3390\/SYM12050715"},{"key":"31_CR34","doi-asserted-by":"publisher","unstructured":"Thompson, P., McNaught, J., Ananiadou, S.: Customised OCR correction for historical medical text. In: 2015 Digital Heritage, vol. 1, pp. 35\u201342 (2015). https:\/\/doi.org\/10.1109\/DigitalHeritage.2015.7413829","DOI":"10.1109\/DigitalHeritage.2015.7413829"},{"key":"31_CR35","doi-asserted-by":"publisher","unstructured":"Vo, Q.N., Kim, S.H., Yang, H.J., Lee, G.: Binarization of degraded document images based on hierarchical deep supervised network. Patt. Recogn. 74, 568\u2013586 (2018).https:\/\/doi.org\/10.1016\/j.patcog.2017.08.025","DOI":"10.1016\/j.patcog.2017.08.025"},{"key":"31_CR36","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1147\/rd.274.0400","volume":"27","author":"JM White","year":"1983","unstructured":"White, J.M., Rohrer, G.D.: Image thresholding for optical character recognition and other applications requiring character image extraction. IBM J. Res. Dev. 27, 400\u2013411 (1983). https:\/\/doi.org\/10.1147\/rd.274.0400","journal-title":"IBM J. Res. Dev."},{"key":"31_CR37","doi-asserted-by":"publisher","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992). https:\/\/doi.org\/10.1007\/bf00992696","DOI":"10.1007\/bf00992696"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86549-8_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T22:02:43Z","timestamp":1756936963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86549-8_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865481","9783030865498"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86549-8_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","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":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"Additionally, 13 competition reports are included.","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)"}}]}}