{"id":"https://openalex.org/W2052918223","doi":"https://doi.org/10.1045/march2006-choudhury","title":"Document Recognition for a Million Books","display_name":"Document Recognition for a Million Books","publication_year":2006,"publication_date":"2006-03-01","ids":{"openalex":"https://openalex.org/W2052918223","doi":"https://doi.org/10.1045/march2006-choudhury","mag":"2052918223"},"language":"en","primary_location":{"id":"doi:10.1045/march2006-choudhury","is_oa":true,"landing_page_url":"https://doi.org/10.1045/march2006-choudhury","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1045/march2006-choudhury","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035606969","display_name":"Sayeed Choudhury","orcid":"https://orcid.org/0000-0003-2891-0543"},"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":"G. Sayeed Choudhury","raw_affiliation_strings":["Johns Hopkins University ("],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083723894","display_name":"Tim DiLauro","orcid":"https://orcid.org/0000-0002-9997-3464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim DiLauro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022919593","display_name":"Robert Ferguson","orcid":"https://orcid.org/0000-0002-8071-0998"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Robert Ferguson","raw_affiliation_strings":["McGill University"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035044633","display_name":"Michael Droettboom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Droettboom","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020424604","display_name":"Ichiro Fujinaga","orcid":"https://orcid.org/0000-0003-2524-8582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ichiro Fujinaga","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035606969"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.845,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91170482,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"12","issue":"3","first_page":null,"last_page":null},"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/T14339","display_name":"Image Processing and 3D Reconstruction","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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.995199978351593,"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":0.7436230182647705},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6198088526725769},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48954471945762634},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44570696353912354},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4433193802833557},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.43070918321609497},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4119192063808441},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1341533064842224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08043491840362549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436230182647705},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6198088526725769},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48954471945762634},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44570696353912354},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4433193802833557},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.43070918321609497},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4119192063808441},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1341533064842224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08043491840362549},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1045/march2006-choudhury","is_oa":true,"landing_page_url":"https://doi.org/10.1045/march2006-choudhury","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},{"id":"pmh:oai:hispana.mcu.es:231854","is_oa":false,"landing_page_url":"http://dialnet.unirioja.es/servlet/oaiart?codigo=1457127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"D-Lib Magazine, ISSN 1082-9873, Vol. 12, N\u00ba. 3, 2006","raw_type":"text (article)"}],"best_oa_location":{"id":"doi:10.1045/march2006-choudhury","is_oa":true,"landing_page_url":"https://doi.org/10.1045/march2006-choudhury","pdf_url":null,"source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W108602857","https://openalex.org/W1482381211","https://openalex.org/W1531901927","https://openalex.org/W1584427380","https://openalex.org/W1827111577","https://openalex.org/W1833803359","https://openalex.org/W1982012519","https://openalex.org/W2054944928","https://openalex.org/W2114021129","https://openalex.org/W2136529249","https://openalex.org/W2150486441","https://openalex.org/W2172063020"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"As":[0],"initiatives":[1],"such":[2],"as":[3],"Google":[4],"Book":[5],"Search":[6],"(http://books.google.com/)":[7],"and":[8,57,69,95],"the":[9,44,55,61,93],"Open":[10],"Content":[11],"Alliance":[12],"(http://www.opencontentalliance.org/)":[13],"advance":[14],"efforts":[15],"to":[16,25,42,49,79,103],"digitize":[17],"millions":[18],"of":[19,30,64,72,98],"books,":[20],"there":[21],"is":[22],"great":[23],"potential":[24],"make":[26],"available":[27],"vast":[28,62],"amounts":[29],"information.":[31],"To":[32],"truly":[33],"unlock":[34],"this":[35],"knowledge,":[36],"however,":[37],"it":[38,75],"will":[39,76],"be":[40,77],"necessary":[41,78],"process":[43],"resulting":[45],"digital":[46],"page":[47],"images":[48,94],"recognize":[50],"important":[51],"content,":[52],"including":[53],"both":[54],"semantic":[56],"structural":[58],"aspects.":[59],"Given":[60],"diversity":[63],"fonts,":[65],"symbols,":[66],"tables,":[67],"languages":[68],"a":[70],"host":[71],"other":[73,99],"elements,":[74],"create":[80],"flexible,":[81],"modular,":[82],"scalable":[83],"document":[84],"recognition":[85,88],"systems.":[86],"Document":[87],"involves":[89],"extracting":[90],"features":[91],"from":[92],"even":[96],"transcriptions":[97],"documents":[100],"in":[101],"order":[102],"group":[104],"diverse":[105],"content.":[106]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
