{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:40:04Z","timestamp":1756852804692,"version":"3.44.0"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863364"},{"type":"electronic","value":"9783030863371"}],"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\/978-3-030-86337-1_12","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"171-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FEDS - Filtered Edit Distance Surrogate"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9373-529X","authenticated-orcid":false,"given":"Yash","family":"Patel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0863-4844","authenticated-orcid":false,"given":"Ji\u0159\u00ed","family":"Matas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"12_CR2","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.24792","volume":"11","author":"FL Bookstein","year":"1989","unstructured":"Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. TPAMI 11, 567\u2013585 (1989)","journal-title":"TPAMI"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Busta, M., Neumann, L., Matas, J.: Deep textspotter: an end-to-end trainable scene text localization and recognition framework. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.242"},{"key":"12_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-030-21074-8_11","volume-title":"Computer Vision \u2013 ACCV 2018 Workshops","author":"M Bu\u0161ta","year":"2019","unstructured":"Bu\u0161ta, M., Patel, Y., Matas, J.: E2E-MLT - an unconstrained end-to-end method for multi-language scene text. In: Carneiro, G., You, S. (eds.) ACCV 2018. LNCS, vol. 11367, pp. 127\u2013143. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21074-8_11"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"G\u00f3mez, L., Rusinol, M., Karatzas, D.: LSDE: levenshtein space deep embedding for query-by-string word spotting. In: ICDAR (2017)","DOI":"10.1109\/ICDAR.2017.88"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Gomez, R., Biten, A.F., Gomez, L., Gibert, J., Karatzas, D., Rusi\u00f1ol, M.: Selective style transfer for text. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00134"},{"key":"12_CR7","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"},{"key":"12_CR8","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. In: NeurIPS (2017)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., Qiao, Y., Loy, C., Tang, X.: Reading scene text in deep convolutional sequences. In: AAAI (2016)","DOI":"10.1609\/aaai.v30i1.10465"},{"key":"12_CR12","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Reading text in the wild with convolutional neural networks. IJCV 116, 1\u201320 (2016)","journal-title":"IJCV"},{"key":"12_CR14","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: NeurIPS (2015)"},{"key":"12_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/978-3-319-10593-2_34","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Jaderberg","year":"2014","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 512\u2013528. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10593-2_34"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Janou\u0161kov\u00e1, K., Matas, J., Gomez, L., Karatzas, D.: Text recognition - real world data and where to find them. In: ICPR (2021)","DOI":"10.1109\/ICPR48806.2021.9412868"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Lapin, M., Hein, M., Schiele, B.: Loss functions for top-k error: analysis and insights. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.163"},{"key":"12_CR20","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018610"},{"key":"12_CR22","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. TPAMI (2019)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Liao, M., et al.: Scene text recognition from two-dimensional perspective. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018714"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Litman, R., Anschel, O., Tsiper, S., Litman, R., Mazor, S., Manmatha, R.: Scatter: selective context attentional scene text recognizer. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01198"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Chen, C., Wong, K.Y.K.: Char-net: a character-aware neural network for distorted scene text recognition. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12246"},{"key":"12_CR26","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2020","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. IJCV 129, 161\u2013184 (2020)","journal-title":"IJCV"},{"key":"12_CR27","unstructured":"Long, S., Yao, C.: UnrealText: synthesizing realistic scene text images from the unreal world. In: CVPR (2020)"},{"key":"12_CR28","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. In: ICDAR (2003)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC (2012)","DOI":"10.5244\/C.26.127"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR 2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019. In: ICDAR (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"12_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-319-46604-0_29","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Y Patel","year":"2016","unstructured":"Patel, Y., Gomez, L., Rusi\u00f1ol, M., Karatzas, D.: Dynamic lexicon generation for natural scene images. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 395\u2013410. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_29"},{"key":"12_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-030-58577-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Patel","year":"2020","unstructured":"Patel, Y., Hoda\u0148, T., Matas, J.: Learning surrogates via deep embedding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 205\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_13"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Patel, Y., Bu\u0161ta, M., Matas, J.: E2E-MLT-an unconstrained end-to-end method for multi-language scene text (2018)","DOI":"10.1007\/978-3-030-21074-8_11"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: SEED: semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01354"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Quy Phan, T., Shivakumara, P., Tian, S., Lim Tan, C.: Recognizing text with perspective distortion in natural scenes. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"12_CR36","doi-asserted-by":"publisher","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Syst. Appl. 41, 8027\u20138048 (2014)","journal-title":"Expert Syst. Appl."},{"key":"12_CR37","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533\u2013536 (1986)","journal-title":"Nature"},{"key":"12_CR38","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","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. TPAMI 39, 2298\u20132304 (2016)","journal-title":"TPAMI"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.452"},{"key":"12_CR40","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: ASTER: an attentional scene text recognizer with flexible rectification. PAMI 41, 2035\u20132048 (2018)","journal-title":"PAMI"},{"key":"12_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"12_CR42","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NeurIPS (2014)"},{"key":"12_CR43","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV (2011)"},{"key":"12_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1007\/978-3-642-15549-9_43","volume-title":"Computer Vision \u2013 ECCV 2010","author":"K Wang","year":"2010","unstructured":"Wang, K., Belongie, S.: Word spotting in the wild. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 591\u2013604. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_43"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Decoupled attention network for text recognition. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6903"},{"key":"12_CR46","unstructured":"Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. In: CoRR (2015)"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: Symmetry-constrained rectification network for scene text recognition. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00924"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Yao, C., Bai, X., Shi, B., Liu, W.: Strokelets: a learned multi-scale representation for scene text recognition. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.515"},{"key":"12_CR49","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. TPAMI 37, 1480\u20131500 (2014)","journal-title":"TPAMI"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"12_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58529-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Yue","year":"2020","unstructured":"Yue, X., Kuang, Z., Lin, C., Sun, H., Zhang, W.: RobustScanner: dynamically enhancing positional clues for robust text recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 135\u2013151. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_9"},{"key":"12_CR52","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. In: CoRR (2012)"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Zhan, F., Lu, S.: ESIR: end-to-end scene text recognition via iterative image rectification. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00216"},{"key":"12_CR54","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: NeurIPS (2015)"},{"key":"12_CR55","unstructured":"Zhang, Y., Gueguen, L., Zharkov, I., Zhang, P., Seifert, K., Kadlec, B.: Uber-text: a large-scale dataset for optical character recognition from street-level imagery. In: CVPR Workshop (2017)"}],"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\/978-3-030-86337-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:15:33Z","timestamp":1756851333000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_12","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)"}}]}}