{"id":"https://openalex.org/W2143373361","doi":"https://doi.org/10.1109/icdar.2003.1227663","title":"Indexing and retrieval of words in old documents","display_name":"Indexing and retrieval of words in old documents","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2143373361","doi":"https://doi.org/10.1109/icdar.2003.1227663","mag":"2143373361"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2003.1227663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 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/A5011511343","display_name":"Simone Marinai","orcid":"https://orcid.org/0000-0002-6702-2277"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"S. Marinai","raw_affiliation_strings":["DSI-University of Florence, Italy","Florence, Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DSI-University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Florence, Univ., Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044448928","display_name":"Emanuele Marino","orcid":"https://orcid.org/0000-0002-0887-1201"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"E. Marino","raw_affiliation_strings":["DSI-University of Florence, Italy","Florence, Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DSI-University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Florence, Univ., Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072297116","display_name":"G. Soda","orcid":"https://orcid.org/0000-0003-1807-1539"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"G. Soda","raw_affiliation_strings":["DSI-University of Florence, Italy","Florence, Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DSI-University of Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Florence, Univ., Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.315,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92922159,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"223","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9979000091552734,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9965000152587891,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.897676944732666},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.849628210067749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6736838817596436},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6686670780181885},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6566765308380127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6090426445007324},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.5986657738685608},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5813652873039246},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5476944446563721},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5378621816635132},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.508621335029602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50672847032547},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46824824810028076},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4646757245063782},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4502774775028229},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4458584487438202},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.41957247257232666},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.39919254183769226}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.897676944732666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849628210067749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6736838817596436},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6686670780181885},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6566765308380127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6090426445007324},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.5986657738685608},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5813652873039246},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5476944446563721},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5378621816635132},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.508621335029602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50672847032547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46824824810028076},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4646757245063782},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4502774775028229},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4458584487438202},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.41957247257232666},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.39919254183769226},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icdar.2003.1227663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.109.6668","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.6668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.salford.ac.uk/prima/ICDAR2003/Papers/0039_673_marinai_s.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.8222","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.8222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dsi.unifi.it/~simone/Papers/ICDAR03a.pdf","raw_type":"text"},{"id":"pmh:oai:flore.unifi.it:2158/260789","is_oa":false,"landing_page_url":"http://hdl.handle.net/2158/260789","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1679913846","https://openalex.org/W1952936656","https://openalex.org/W2128119911","https://openalex.org/W2149470434","https://openalex.org/W2160484851","https://openalex.org/W2169950950","https://openalex.org/W2238624099","https://openalex.org/W2546055497","https://openalex.org/W4230511558","https://openalex.org/W4245176872","https://openalex.org/W6607690945","https://openalex.org/W7062905887"],"related_works":["https://openalex.org/W2054173104","https://openalex.org/W2257399947","https://openalex.org/W2051764263","https://openalex.org/W2935705348","https://openalex.org/W2358632292","https://openalex.org/W2069035364","https://openalex.org/W2111239386","https://openalex.org/W2502807948","https://openalex.org/W52396946","https://openalex.org/W4238415164"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,38,55,80,98],"system":[4,102],"for":[5,32,118,145],"efficient":[6,33],"indexing":[7],"and":[8,29,77,110,125],"retrieval":[9],"of":[10,14,57,121,143],"words":[11,69,94],"in":[12,54,70,88,95],"collections":[13],"document":[15],"images.":[16],"The":[17,101,113],"proposed":[18],"method":[19],"is":[20,43],"based":[21],"on":[22],"two":[23],"main":[24],"principles:":[25],"unsupervised":[26],"prototype":[27],"clustering,":[28],"string":[30,34],"encoding":[31],"matching.":[35],"During":[36],"indexing,":[37],"self":[39],"organizing":[40],"map":[41],"(SOM)":[42],"trained":[44,66],"so":[45],"as":[46],"to":[47,60,90,97,107],"cluster":[48],"together":[49],"similar":[50,93],"symbols":[51],"(character-like":[52],"objects)":[53],"sub-set":[56],"the":[58,65,68,71,119],"documents":[59,123],"be":[61,75,85,104],"stored.":[62],"By":[63],"using":[64],"SOM":[67],"whole":[72],"collection":[73],"can":[74,84,103],"stored":[76],"represented":[78],"with":[79],"fixed-length":[81],"description":[82],"that":[83],"easily":[86],"compared":[87],"order":[89],"score":[91],"most":[92,114],"response":[96],"user":[99],"query.":[100],"automatically":[105],"adapted":[106],"different":[108],"languages":[109],"font":[111],"styles.":[112],"appropriate":[115],"applications":[116],"are":[117],"processing":[120],"old":[122],"(18th":[124],"19th":[126],"Centuries)":[127],"where":[128],"current":[129,146],"OCRs":[130],"have":[131],"more":[132],"difficulties.":[133],"Experimental":[134],"results":[135],"describe":[136],"three":[137],"application":[138],"scenarios":[139],"having":[140],"various":[141],"levels":[142],"difficulty":[144],"OCR":[147],"systems.":[148]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}