{"id":"https://openalex.org/W2143307633","doi":"https://doi.org/10.1109/dial.2004.1263246","title":"A general system for the retrieval of document images from digital libraries","display_name":"A general system for the retrieval of document images from digital libraries","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2143307633","doi":"https://doi.org/10.1109/dial.2004.1263246","mag":"2143307633"},"language":"en","primary_location":{"id":"doi:10.1109/dial.2004.1263246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. 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":["Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","Dipt. di Sistemi e Informatica, Florence Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Dipt. di Sistemi e Informatica, 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":["Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","Dipt. di Sistemi e Informatica, Florence Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Dipt. di Sistemi e Informatica, Florence Univ., Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000145862","display_name":"F. Cesarini","orcid":null},"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":"F. Cesarini","raw_affiliation_strings":["Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","Dipt. di Sistemi e Informatica, Florence Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Dipt. di Sistemi e Informatica, 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":["Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","Dipt. di Sistemi e Informatica, Florence Univ., Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Sistemi e Informatica, University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]},{"raw_affiliation_string":"Dipt. di Sistemi e Informatica, Florence Univ., Italy","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8675,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.942214,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8664391040802002},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8236631751060486},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6879944801330566},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.5547623634338379},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5531776547431946},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5199397802352905},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5042961835861206},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.47376683354377747},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43134605884552},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.430780291557312},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4243600368499756},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4223778247833252},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.339325875043869},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2498863935470581},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2167830765247345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18437138199806213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664391040802002},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8236631751060486},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6879944801330566},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.5547623634338379},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5531776547431946},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5199397802352905},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5042961835861206},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.47376683354377747},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43134605884552},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.430780291557312},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4243600368499756},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4223778247833252},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.339325875043869},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2498863935470581},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2167830765247345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18437138199806213},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/dial.2004.1263246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263246","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4515","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4515","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/DIAL04.pdf","raw_type":"text"},{"id":"pmh:oai:flore.unifi.it:2158/20851","is_oa":false,"landing_page_url":"http://hdl.handle.net/2158/20851","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"},{"id":"pmh:oai:flore.unifi.it:2158/260788","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1263246&tag=1","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":[{"display_name":"Quality Education","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W8079469","https://openalex.org/W71495007","https://openalex.org/W1504337617","https://openalex.org/W1516711901","https://openalex.org/W1527672561","https://openalex.org/W1528781420","https://openalex.org/W1660390307","https://openalex.org/W1679913846","https://openalex.org/W1952936656","https://openalex.org/W1990517717","https://openalex.org/W1999156958","https://openalex.org/W2001496424","https://openalex.org/W2046079134","https://openalex.org/W2085413885","https://openalex.org/W2093168600","https://openalex.org/W2116013009","https://openalex.org/W2118269922","https://openalex.org/W2120259239","https://openalex.org/W2125318232","https://openalex.org/W2128119911","https://openalex.org/W2130660124","https://openalex.org/W2132368650","https://openalex.org/W2135815319","https://openalex.org/W2139057240","https://openalex.org/W2149470434","https://openalex.org/W2163534337","https://openalex.org/W2169950950","https://openalex.org/W2238624099","https://openalex.org/W2546055497","https://openalex.org/W4245176872","https://openalex.org/W6600316486","https://openalex.org/W6630648726","https://openalex.org/W6631387376","https://openalex.org/W6683992317","https://openalex.org/W7062905887"],"related_works":["https://openalex.org/W86079546","https://openalex.org/W217802","https://openalex.org/W67877050","https://openalex.org/W118995706","https://openalex.org/W2154208237","https://openalex.org/W2396760013","https://openalex.org/W2152781138","https://openalex.org/W2019565280","https://openalex.org/W2356293009","https://openalex.org/W1496011054"],"abstract_inverted_index":{"Large":[0],"collections":[1,24],"of":[2,45,77,90,92,110,113,158,164,212,248,267],"scanned":[3],"documents":[4],"(books":[5],"and":[6,57,149,245,263],"journals)":[7],"are":[8,258],"now":[9],"available":[10,96],"in":[11,58,141,170,195,200,236],"digital":[12,153],"libraries.":[13,154],"The":[14,43,155,173,190,210,255],"most":[15],"common":[16],"method":[17],"for":[18,34,251],"retrieving":[19],"relevant":[20],"information":[21,115,145],"from":[22,146],"these":[23,213,249],"is":[25,31,95,125,161,193],"image":[26,131],"browsing,":[27],"but":[28],"this":[29,59],"approach":[30,105,124],"not":[32],"feasible":[33],"books":[35,148],"with":[36,97,182,222],"more":[37],"than":[38],"a":[39,61,136,183,187,204,223],"few":[40],"dozen":[41],"pages.":[42,102],"recognition":[44],"printed":[46],"text":[47],"can":[48,66,83],"be":[49,67,84,117],"made":[50,259],"on":[51,74,107,260],"the":[52,70,75,93,100,108,111,120,159,162,201,227,232,237,246,265,268],"images":[53],"by":[54,63,129],"OCR":[55],"systems,":[56],"case":[60],"retrieval":[62,132,168],"textual":[64],"content":[65],"performed.":[68],"However,":[69],"results":[71,257],"heavily":[72],"depend":[73],"quality":[76],"original":[78],"documents.":[79],"More":[80],"sophisticated":[81],"navigation":[82],"performed":[85],"when":[86],"an":[87,177],"electronic":[88],"table":[89],"contents":[91],"book":[94],"links":[98],"to":[99,116,143,152,179,186,197,218],"corresponding":[101],"An":[103],"opposite":[104],"relies":[106],"reduction":[109],"amount":[112],"symbolic":[114],"extracted":[118],"at":[119],"storage":[121],"time.":[122],"This":[123],"taken":[126],"into":[127],"account":[128],"document":[130],"systems.":[133],"We":[134,230],"describe":[135,231],"system":[137,160,238],"that":[138],"we":[139],"developed":[140],"order":[142,196],"retrieve":[144,198,219],"digitized":[147],"journals":[150],"belonging":[151],"main":[156],"feature":[157],"ability":[163],"combining":[165],"two":[166],"principal":[167],"strategies":[169,215],"several":[171],"ways.":[172],"first":[174],"strategy":[175,192],"allows":[176,216],"user":[178],"find":[180],"pages":[181,221,262],"layout":[184,241],"similar":[185],"query":[188],"page.":[189],"second":[191],"used":[194,235],"words":[199],"collection":[202],"matching":[203],"user-defined":[205],"query,":[206],"without":[207],"performing":[208],"OCR.":[209],"combination":[211],"basic":[214,233],"users":[217],"meaningful":[220],"low":[224],"effort":[225],"during":[226],"indexing":[228],"phase.":[229],"tools":[234,250],"(layout":[239],"analysis,":[240],"retrieval,":[242],"word":[243],"retrieval)":[244],"integration":[247],"answering":[252],"complex":[253],"queries.":[254],"experimental":[256],"1287":[261],"show":[264],"effectiveness":[266],"integrated":[269],"retrieval.":[270]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
