{"id":"https://openalex.org/W1996759799","doi":"https://doi.org/10.1145/1568296.1568300","title":"Handwritten document retrieval strategies","display_name":"Handwritten document retrieval strategies","publication_year":2009,"publication_date":"2009-07-23","ids":{"openalex":"https://openalex.org/W1996759799","doi":"https://doi.org/10.1145/1568296.1568300","mag":"1996759799"},"language":"en","primary_location":{"id":"doi:10.1145/1568296.1568300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data","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/A5020354604","display_name":"Venu Govindaraju","orcid":"https://orcid.org/0000-0002-5318-7409"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Venu Govindaraju","raw_affiliation_strings":["University at Buffalo - SUNY, Amherst, NY","University at Buffalo - SUNY, Amherst, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"University at Buffalo - SUNY, Amherst, NY","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"University at Buffalo - SUNY, Amherst, NY#TAB#","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108504544","display_name":"Huaigu Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaigu Cao","raw_affiliation_strings":["BBN Technologies, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, Cambridge, MA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102494018","display_name":"Anurag Bhardwaj","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Bhardwaj","raw_affiliation_strings":["University at Buffalo - SUNY, Amherst, NY","University at Buffalo - SUNY, Amherst, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"University at Buffalo - SUNY, Amherst, NY","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"University at Buffalo - SUNY, Amherst, NY#TAB#","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020354604"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":2.265,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89005677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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/T10601","display_name":"Handwritten Text Recognition 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":0.9993000030517578,"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":0.9987999796867371,"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":0.892693817615509},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5857982635498047},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5852046012878418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749693512916565},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5602916479110718},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.5404371619224548},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5331816673278809},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.47880324721336365},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4763917326927185},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"Text retrieval","score":0.43194708228111267},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4212639629840851},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4136790931224823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3700975775718689},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2892773747444153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.892693817615509},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5857982635498047},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5852046012878418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749693512916565},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5602916479110718},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.5404371619224548},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5331816673278809},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.47880324721336365},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4763917326927185},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.43194708228111267},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4212639629840851},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4136790931224823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3700975775718689},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2892773747444153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1568296.1568300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1568296.1568300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data","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":15,"referenced_works":["https://openalex.org/W10112829","https://openalex.org/W1541376310","https://openalex.org/W1660390307","https://openalex.org/W1826921238","https://openalex.org/W2041823554","https://openalex.org/W2044506065","https://openalex.org/W2058931781","https://openalex.org/W2098761739","https://openalex.org/W2112489058","https://openalex.org/W2115167129","https://openalex.org/W2126888240","https://openalex.org/W2131994350","https://openalex.org/W2147782381","https://openalex.org/W2163374925","https://openalex.org/W2167929403"],"related_works":["https://openalex.org/W2083605078","https://openalex.org/W2169718841","https://openalex.org/W1502028000","https://openalex.org/W200631787","https://openalex.org/W204509384","https://openalex.org/W2367995618","https://openalex.org/W2350106110","https://openalex.org/W2036614928","https://openalex.org/W2393777710","https://openalex.org/W2360192068"],"abstract_inverted_index":{"With":[0],"the":[1,5,62,103,118,123,132,140,159],"continuous":[2],"growth":[3],"of":[4,64,162],"World":[6],"Wide":[7],"Web,":[8],"there":[9],"is":[10],"an":[11,15],"urgent":[12],"need":[13],"for":[14,101,126,145],"efficient":[16],"information":[17,78],"retrieval":[18,79,106],"system":[19],"which":[20],"can":[21],"search":[22,59],"and":[23,121,173],"retrieve":[24],"handwritten":[25,65,89],"documents":[26,160],"when":[27],"presented":[28],"with":[29,42,75],"user":[30],"queries.":[31],"However,":[32],"unconstrained":[33],"handwriting":[34],"recognition":[35],"remains":[36],"to":[37,50,88,116,157],"be":[38,51],"a":[39,52,57,98,112],"challenging":[40],"task":[41],"inadequate":[43],"performance":[44,177],"(around":[45],"30%,":[46],"accuracy)":[47],"thus":[48],"proving":[49],"major":[53],"hurdle":[54],"in":[55,61,171],"providing":[56],"robust":[58,154],"experience":[60],"domain":[63],"documents.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"describe":[71,93,168],"our":[72],"recent":[73],"research":[74],"focus":[76],"on":[77],"from":[80],"noisy":[81,104,147,164],"text":[82,105,120,125,137,148],"output":[83],"by":[84],"imperfect":[85],"recognizers":[86],"applied":[87],"document":[90],"images.":[91],"We":[92,167],"three":[94],"techniques":[95],"each":[96],"exploring":[97],"different":[99],"approach":[100],"solving":[102],"task.":[107],"The":[108,128,150],"first":[109],"method":[110,130,152],"uses":[111,122,131],"novel":[113],"bootstrapping":[114],"mechanism":[115],"refine":[117],"OCR'ed":[119,136,165],"cleaned":[124],"retrieval.":[127],"second":[129],"uncorrected":[133],"or":[134],"raw":[135],"but":[138],"modifies":[139],"standard":[141,179],"vector":[142],"space":[143],"model":[144],"handling":[146],"issues.":[149],"third":[151],"employs":[153],"image":[155],"features":[156],"index":[158],"instead":[161],"using":[163,178],"text.":[166],"these":[169],"approaches":[170],"detail":[172],"also":[174],"present":[175],"their":[176],"IR":[180],"evaluation":[181],"metrics.":[182]},"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}