{"id":"https://openalex.org/W2149470434","doi":"https://doi.org/10.1109/tpami.2002.1008389","title":"Imaged document text retrieval without OCR","display_name":"Imaged document text retrieval without OCR","publication_year":2002,"publication_date":"2002-06-01","ids":{"openalex":"https://openalex.org/W2149470434","doi":"https://doi.org/10.1109/tpami.2002.1008389","mag":"2149470434"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2002.1008389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2002.1008389","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-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/A5111664929","display_name":"Chew Lim Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chew Lim Tan","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput., Univ. of Singapore, Kent Ridge, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Singapore, Kent Ridge, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641403","display_name":"Weihua Huang","orcid":"https://orcid.org/0000-0002-2208-7464"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weihua Huang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput., Univ. of Singapore, Kent Ridge, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Singapore, Kent Ridge, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007584","display_name":"Zhaohui Yu","orcid":"https://orcid.org/0000-0002-8230-1899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaohui Yu","raw_affiliation_strings":["Toronto, Ontario, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toronto, Ontario, Canada#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076450290","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0003-4215-1993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Agilent Technologies Singapore Private Limited, Singapore, Singapore","Agilent Technologies Singapore Pte Ltd., Alexandra Road, Singapore#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agilent Technologies Singapore Private Limited, Singapore, Singapore","institution_ids":[]},{"raw_affiliation_string":"Agilent Technologies Singapore Pte Ltd., Alexandra Road, Singapore#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1907,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.95090007,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"24","issue":"6","first_page":"838","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"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":0.7411913275718689},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.6911454796791077},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6546444296836853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6182379126548767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6085740327835083},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5975145101547241},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.4863656163215637},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4682259261608124},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.46522849798202515},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.45918673276901245},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.440490186214447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4334338307380676},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.42790746688842773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4174787998199463},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34336841106414795},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.2918907403945923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11601448059082031},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.1101662814617157},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08614552021026611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411913275718689},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.6911454796791077},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6546444296836853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182379126548767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6085740327835083},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5975145101547241},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.4863656163215637},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4682259261608124},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.46522849798202515},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.45918673276901245},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.440490186214447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4334338307380676},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.42790746688842773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4174787998199463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34336841106414795},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2918907403945923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11601448059082031},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.1101662814617157},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08614552021026611},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2002.1008389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2002.1008389","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/39184","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/39184","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.7021","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.7021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~tancl/Papers/Earlier Papers/PAMI-Tan-Huang.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.98.7701","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.98.7701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/labs/chime/da/paperdownload/tan02tpamia.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6000000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332265","display_name":"National Science Board","ror":"https://ror.org/00apvva27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W184723446","https://openalex.org/W1480297560","https://openalex.org/W1501437810","https://openalex.org/W1541376310","https://openalex.org/W1936443983","https://openalex.org/W2044092664","https://openalex.org/W2060588231","https://openalex.org/W2063743738","https://openalex.org/W2078396547","https://openalex.org/W2091626300","https://openalex.org/W2093951781","https://openalex.org/W2121979056","https://openalex.org/W2135950423","https://openalex.org/W4236428962","https://openalex.org/W6632372736"],"related_works":["https://openalex.org/W2131730163","https://openalex.org/W2573990671","https://openalex.org/W2037668370","https://openalex.org/W2000372441","https://openalex.org/W2051072213","https://openalex.org/W4377927354","https://openalex.org/W3021512437","https://openalex.org/W2888746867","https://openalex.org/W2154208237","https://openalex.org/W2356293009"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"method":[3],"for":[4,42],"text":[5],"retrieval":[6],"from":[7,81],"document":[8,38,44,63],"images":[9,80],"without":[10],"the":[11,24,58,62,82,90,93],"use":[12],"of":[13,61,69,85,92],"OCR.":[14],"Documents":[15],"are":[16,34],"segmented":[17],"into":[18],"character":[19],"objects.":[20],"Image":[21],"features,":[22],"namely":[23],"vertical":[25],"traverse":[26,31],"density":[27,32],"(VTD)":[28],"and":[29,75],"horizontal":[30],"(HTD),":[33],"extracted.":[35],"An":[36],"n-gram-based":[37],"vector":[39],"is":[40,53],"constructed":[41],"each":[43],"based":[45],"on":[46],"these":[47],"features.":[48],"Text":[49],"similarity":[50],"between":[51],"documents":[52,72],"then":[54],"measured":[55],"by":[56],"calculating":[57],"dot":[59],"product":[60],"vectors.":[64],"Testing":[65],"with":[66],"seven":[67],"corpora":[68],"imaged":[70],"textual":[71],"in":[73],"English":[74],"Chinese":[76],"as":[77,79],"well":[78],"UW1":[83],"(University":[84],"Washington":[86],"1)":[87],"database":[88],"confirms":[89],"validity":[91],"proposed":[94],"method.":[95]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}