{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T16:03:59Z","timestamp":1751299439287,"version":"3.41.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"22","license":[{"start":{"date-parts":[[2016,12,7]],"date-time":"2016-12-07T00:00:00Z","timestamp":1481068800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005357","name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","doi-asserted-by":"publisher","award":["APVV-15-0517"],"award-info":[{"award-number":["APVV-15-0517"]}],"id":[{"id":"10.13039\/501100005357","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Kult\u00farna a Edukacn\u00e1 Grantov\u00e1 Agent\u00fara M\u0160VVa\u0160 SR (SK)","award":["055-TUKE-4\/2016"],"award-info":[{"award-number":["055-TUKE-4\/2016"]}]},{"name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja (SK)","award":["SK-HU-2013-0015"],"award-info":[{"award-number":["SK-HU-2013-0015"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s11042-016-4185-5","type":"journal-article","created":{"date-parts":[[2016,12,7]],"date-time":"2016-12-07T08:05:40Z","timestamp":1481097940000},"page":"24549-24567","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning string distance with smoothing for OCR spelling correction"],"prefix":"10.1007","volume":"76","author":[{"given":"Daniel","family":"Hl\u00e1dek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00e1n","family":"Sta\u0161","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanislav","family":"Ond\u00e1\u0161","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jozef","family":"Juh\u00e1r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L\u00e1szlo","family":"Kov\u00e1cs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,12,7]]},"reference":[{"key":"4185_CR1","doi-asserted-by":"publisher","unstructured":"Ahmad F, Kondrak G (2005) Learning a spelling error model from search query logs. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT \u201905, pp. 955\u2013962. Association for Computational Linguistics, Stroudsburg, PA, USA. doi: 10.3115\/1220575.1220695","DOI":"10.3115\/1220575.1220695"},{"issue":"1-2","key":"4185_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10994-012-5293-8","volume":"89","author":"A Bellet","year":"2012","unstructured":"Bellet A, Habrard A, Sebban M (2012) Good edit similarity learning by loss minimization. Mach Learn 89(1-2):5\u201335. doi: 10.1007\/s10994-012-5293-8","journal-title":"Mach Learn"},{"key":"4185_CR3","doi-asserted-by":"publisher","unstructured":"Bilenko M, Mooney R (2003) Adaptive duplicate detection using learnable string similarity measures:39\u201348. doi: 10.1145\/956750.956759","DOI":"10.1145\/956750.956759"},{"issue":"4","key":"4185_CR4","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1006\/ csla.1999.0128","volume":"13","author":"SF Chen","year":"1999","unstructured":"Chen SF, Goodman J (1999) An empirical study of smoothing techniques for language modeling. Comput Speech Lang 13(4):359\u2013394. doi: 10.1006\/csla.1999.0128","journal-title":"Comput Speech Lang"},{"issue":"6","key":"4185_CR5","doi-asserted-by":"crossref","first-page":"1458","DOI":"10.11591\/ijece.v5i6.pp1458-1467","volume":"5","author":"A Eutamene","year":"2015","unstructured":"Eutamene A, Kholladi M, Belhadef H (2015) Ontologies and bigram-based approach for isolated non-word errors correction in OCR system. International Journal of Electrical and Computer Engineering 5(6):1458\u20131467","journal-title":"International Journal of Electrical and Computer Engineering"},{"key":"4185_CR6","doi-asserted-by":"publisher","unstructured":"Evershed J, Fitch K (2014) Correcting Noisy OCR: Context Beats Confusion. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, DATeCH \u201914, pp. 45\u201351. ACM, New York, NY, USA. doi: 10.1145\/2595188.2595200","DOI":"10.1145\/2595188.2595200"},{"key":"4185_CR7","doi-asserted-by":"publisher","unstructured":"Gerdjikov S, Mihov S, Nenchev V (2013) Extraction of spelling variations from language structure for noisy text correction. doi: 10.1109\/ICDAR.2013.72","DOI":"10.1109\/ICDAR.2013.72"},{"key":"4185_CR8","doi-asserted-by":"publisher","unstructured":"Ghosh K, Chakraborty A, Parui SK, Majumder P (2016) Improving Information Retrieval Performance on OCRed Text in the Absence of Clean Text Ground Truth. Inf Process Manag. doi: 10.1016\/j.ipm.2016.03.006 . Artice in press","DOI":"10.1016\/j.ipm.2016.03.006"},{"issue":"5","key":"4185_CR9","doi-asserted-by":"publisher","first-page":"392","DOI":"10.15598\/aeee.v11i5.898","volume":"11","author":"D Hl\u00e1dek","year":"2013","unstructured":"Hl\u00e1dek D, Sta\u0161 J, Juh\u00e1r J (2013) Unsupervised spelling correction for Slovak. Adv Electr Electron Eng Ser 11(5):392\u2013397. doi: 10.15598\/aeee.v11i5.898","journal-title":"Adv Electr Electron Eng Ser"},{"issue":"2-3","key":"4185_CR10","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1023\/A:1009902609570","volume":"2","author":"P Kantor","year":"2000","unstructured":"Kantor P, Voorhees E (2000) The TREC-5 confusion track: Comparing retrieval methods for scanned text. Inf Retr 2(2-3):165\u2013176","journal-title":"Inf Retr"},{"issue":"4","key":"4185_CR11","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1145\/146370.146380","volume":"24","author":"K Kukich","year":"1992","unstructured":"Kukich K (1992) Techniques for automatically correcting words in text. ACM Comput Surv 24(4):377\u2013439","journal-title":"ACM Comput Surv"},{"key":"4185_CR12","doi-asserted-by":"publisher","unstructured":"Lin Y, Song Y, Li Y, Wang F, He K (2015) Multilingual corpus construction based on printed and handwritten character separation. Multimedia Tools and Applications:1\u201317. doi: 10.1007\/s11042-015-2995-5","DOI":"10.1007\/s11042-015-2995-5"},{"key":"4185_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.3233\/978-1-61499-619-4-32","volume":"281","author":"YY Lv","year":"2016","unstructured":"Lv YY, Deng YI, Liu ML, Lu QY (2016) Automatic error checking and correction of electronic medical records. Frontiers in Artificial Intelligence and Applications 281:32\u201340. doi: 10.3233\/978-1-61499-619-4-32","journal-title":"Frontiers in Artificial Intelligence and Applications"},{"key":"4185_CR14","doi-asserted-by":"publisher","unstructured":"M\u00fchlberger G., Zelger J, Sagmeister D (2014) User-driven correction of OCR errors. Combing crowdsourcing and information retrieval technology:53\u201356. doi: 10.1145\/2595188.2595212","DOI":"10.1145\/2595188.2595212"},{"key":"4185_CR15","doi-asserted-by":"publisher","unstructured":"Mitankin P, Gerdjikov S, Mihov S (2014) An Approach to Unsupervised Historical Text Normalisation. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, DATeCH \u201914, pp. 29\u201334. ACM, New York, NY, USA. doi: 10.1145\/2595188.2595191","DOI":"10.1145\/2595188.2595191"},{"key":"4185_CR16","doi-asserted-by":"crossref","unstructured":"Mohri M (2004) Weighted Finite-State Transducer Algorithms. An Overview. In: D.C. Mart\u00edn-Vide, D.V. Mitrana, D.G. P\u0103un (eds.) Formal Languages and Applications, no. 148 in Studies in Fuzziness and Soft Computing, pp. 551\u2013563. Springer Berlin Heidelberg","DOI":"10.1007\/978-3-540-39886-8_29"},{"issue":"3","key":"4185_CR17","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"SB Needleman","year":"1970","unstructured":"Needleman SB, Wunsch CD (1970) A general method applicable to the search for similarities in the amino acid sequence of two proteins. J Mol Biol 48(3):443\u2013453. doi: 10.1016\/0022-2836(70)90057-4","journal-title":"J Mol Biol"},{"issue":"4","key":"4185_CR18","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s10506-010-9093-9","volume":"18","author":"DW Oard","year":"2010","unstructured":"Oard DW, Baron JR, Hedin B, Lewis DD, Tomlinson S (2010) Evaluation of information retrieval for E-discovery. Artif Intell Law 18(4):347\u2013386. doi: 10.1007\/s10506-010-9093-9","journal-title":"Artif Intell Law"},{"issue":"7","key":"4185_CR19","doi-asserted-by":"publisher","first-page":"2359","DOI":"10.1007\/s11042-014-1971-9","volume":"74","author":"JH Park","year":"2014","unstructured":"Park JH, Park HH, Kwon YB (2014) Error correction of reference indexing system including multimedia journals. Multimedia Tools and Applications 74(7):2359\u20132370. doi: 10.1007\/s11042-014-1971-9","journal-title":"Multimedia Tools and Applications"},{"issue":"17","key":"4185_CR20","doi-asserted-by":"publisher","first-page":"7221","DOI":"10.1007\/s11042-014-1969-3","volume":"74","author":"G Pengcheng","year":"2014","unstructured":"Pengcheng G, Jiangqin W, Yuan L, Yang X, Tianjiao M (2014) Fast Chinese calligraphic character recognition with large-scale data. Multimedia Tools and Applications 74(17):7221\u20137238. doi: 10.1007\/s11042-014-1969-3","journal-title":"Multimedia Tools and Applications"},{"key":"4185_CR21","doi-asserted-by":"publisher","unstructured":"Perez-Cortes JC, Llobet R, Navarro-Cerdan J, Arlandis J (2010) Using field interdependence to improve correction performance in a transducer-based OCR post-processing system. doi: 10.1109\/ICFHR.2010.99","DOI":"10.1109\/ICFHR.2010.99"},{"key":"4185_CR22","doi-asserted-by":"publisher","unstructured":"Ramanan M, Ramanan A, Charles E (2015) A performance comparison and post-processing error correction technique to OCRs for printed Tamil texts. doi: 10.1109\/ICIINFS.2014.7036474","DOI":"10.1109\/ICIINFS.2014.7036474"},{"issue":"5","key":"4185_CR23","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1016\/j.patcog.2012.10.002","volume":"46","author":"U Reffle","year":"2013","unstructured":"Reffle U, Ringlstetter C (2013) Unsupervised profiling of OCRed historical documents. Pattern Recog 46(5):1346\u20131357. doi: 10.1016\/j.patcog.2012.10.002","journal-title":"Pattern Recog"},{"issue":"5","key":"4185_CR24","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/34.682181","volume":"20","author":"E Ristad","year":"1998","unstructured":"Ristad E, Yianilos P (1998) Learning string-edit distance. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(5):522\u2013532","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"4185_CR25","doi-asserted-by":"publisher","unstructured":"Sariev A, Nenchev V, Gerdjikov S, Mitankin P, Ganchev H, Mihov S, Tinchev T (2014) Flexible Noisy Text Correction. In: 2014 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 31\u201335. doi: 10.1109\/DAS.2014.12","DOI":"10.1109\/DAS.2014.12"},{"key":"4185_CR26","doi-asserted-by":"publisher","unstructured":"Sawant A, Chougule D (2015) Script independent text pre-processing and segmentation for OCR. doi: 10.1109\/EESCO.2015.7253643","DOI":"10.1109\/EESCO.2015.7253643"},{"issue":"1","key":"4185_CR27","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10032-002-0082-8","volume":"5","author":"KU Schulz","year":"2002","unstructured":"Schulz KU, Mihov S (2002) Fast string correction with Levenshtein automata. Int J Doc Anal Recognit 5(1):67\u201385. doi: 10.1007\/s10032-002-0082-8","journal-title":"Int J Doc Anal Recognit"},{"key":"4185_CR28","doi-asserted-by":"publisher","unstructured":"Springmann U, Najock D, Morgenroth H, Schmid H, Gotscharek A, Fink F (2014) OCR of Historical Printings of Latin Texts: Problems, Prospects, Progress. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, DATeCH \u201914. ACM, New York, NY, USA, pp 71\u201375. doi: 10.1145\/2595188.2595205","DOI":"10.1145\/2595188.2595205"},{"issue":"1","key":"4185_CR29","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/1687-4722-2014-14","volume":"2014","author":"J Sta\u0161","year":"2014","unstructured":"Sta\u0161 J, Juh\u00e1r J, Hl\u00e1dek D (2014) Classification of heterogeneous text data for robust domain-specific language modeling. EURASIP Journal on Audio, Speech, and Music Processing 2014(1):14. doi: 10.1186\/1687-4722-2014-14","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"4185_CR30","doi-asserted-by":"publisher","unstructured":"Taghva K, Agarwal S (2013) Utilizing web data in identification and correction of OCR errors. In: Proc. SPIE 9021, Document Recognition and Retrieval XXI, 902109. doi: 10.1117\/12.2006500","DOI":"10.1117\/12.2006500"},{"key":"4185_CR31","doi-asserted-by":"publisher","unstructured":"Takasu A (2009) Bayesian similarity model estimation for approximate recognized text search. doi: 10.1109\/ICDAR.2009.193","DOI":"10.1109\/ICDAR.2009.193"},{"issue":"1","key":"4185_CR32","doi-asserted-by":"publisher","first-page":"42","DOI":"10.5281\/zenodo.16303","volume":"36","author":"O Tange","year":"2011","unstructured":"Tange O (2011) Gnu parallel - the command-line power tool. ;login: The USENIX Magazine 36(1):42\u201347. doi: 10.5281\/zenodo.16303","journal-title":";login: The USENIX Magazine"},{"key":"4185_CR33","doi-asserted-by":"publisher","unstructured":"Vobl T, Gotscharek A, Reffle U, Ringlstetter C, Schulz KU (2014) PoCoTo - an Open Source System for Efficient Interactive Postcorrection of OCRed Historical Texts. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, DATeCH \u201914. ACM, New York, NY, USA, pp 57\u201361. doi: 10.1145\/2595188.2595197","DOI":"10.1145\/2595188.2595197"},{"issue":"1","key":"4185_CR34","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1145\/321796.321811","volume":"21","author":"RA Wagner","year":"1974","unstructured":"Wagner RA, Fischer MJ (1974) The String-to-String Correction Problem. J ACM 21(1):168\u2013173. doi: 10.1145\/321796.321811","journal-title":"J ACM"},{"issue":"1","key":"4185_CR35","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s11042-012-1250-6","volume":"69","author":"H Yang","year":"2012","unstructured":"Yang H, Quehl B, Sack H (2012) A framework for improved video text detection and recognition. Multimedia Tools and Applications 69(1):217\u2013245. doi: 10.1007\/s11042-012-1250-6","journal-title":"Multimedia Tools and Applications"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-016-4185-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-4185-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-016-4185-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T06:59:24Z","timestamp":1749797964000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-016-4185-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12,7]]},"references-count":35,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["4185"],"URL":"https:\/\/doi.org\/10.1007\/s11042-016-4185-5","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2016,12,7]]}}}