{"id":"https://openalex.org/W4242234918","doi":"https://doi.org/10.1109/jcdl.2003.1204889","title":"Correcting broken characters in the recognition of historical printed documents","display_name":"Correcting broken characters in the recognition of historical printed documents","publication_year":2004,"publication_date":"2004-01-24","ids":{"openalex":"https://openalex.org/W4242234918","doi":"https://doi.org/10.1109/jcdl.2003.1204889"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2003.1204889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2003.1204889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 Joint Conference on Digital Libraries, 2003. Proceedings.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050177768","display_name":"M. Droettboom","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Droettboom","raw_affiliation_strings":["Digital Knowledge Center, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Digital Knowledge Center, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050177768"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.0932,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.81095709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"364","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12923","display_name":"Digital Image Processing Techniques","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12549","display_name":"Image and Object Detection Techniques","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8649337291717529},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6875336766242981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6646759510040283},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.6356927752494812},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5068593621253967},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.48396041989326477},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4645405113697052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4494372308254242},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4296457767486572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36701279878616333},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21940401196479797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1323266625404358},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12224212288856506},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07265207171440125}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8649337291717529},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6875336766242981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646759510040283},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.6356927752494812},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5068593621253967},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.48396041989326477},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4645405113697052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4494372308254242},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4296457767486572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36701279878616333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21940401196479797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1323266625404358},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12224212288856506},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07265207171440125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2003.1204889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2003.1204889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 Joint Conference on Digital Libraries, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W385325703","https://openalex.org/W1501437810","https://openalex.org/W2104095591","https://openalex.org/W2122111042","https://openalex.org/W2148539800","https://openalex.org/W2172063020","https://openalex.org/W6613125434","https://openalex.org/W6629966167","https://openalex.org/W6675770446"],"related_works":["https://openalex.org/W1991513203","https://openalex.org/W2892704491","https://openalex.org/W2218402054","https://openalex.org/W4312612713","https://openalex.org/W2085262576","https://openalex.org/W4383748232","https://openalex.org/W2510702936","https://openalex.org/W2902204561","https://openalex.org/W2386858327","https://openalex.org/W2964911286"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2],"new":[3],"technique":[4,27],"for":[5],"dealing":[6],"with":[7,47],"broken":[8],"characters,":[9],"one":[10],"of":[11,21],"the":[12,16,36],"major":[13],"challenges":[14],"in":[15],"optical":[17],"character":[18],"recognition":[19],"(OCR)":[20],"degraded":[22],"historical":[23],"printed":[24],"documents.":[25],"A":[26],"based":[28],"on":[29],"graph":[30],"combinatorics":[31],"is":[32],"used":[33],"to":[34,44],"rejoin":[35],"appropriate":[37],"connected":[38],"components.":[39],"It":[40],"has":[41],"been":[42],"applied":[43],"real":[45],"data":[46],"successful":[48],"results.":[49]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
