{"id":"https://openalex.org/W1999067635","doi":"https://doi.org/10.1145/1815330.1815356","title":"Analysis of whole-book recognition","display_name":"Analysis of whole-book recognition","publication_year":2010,"publication_date":"2010-06-09","ids":{"openalex":"https://openalex.org/W1999067635","doi":"https://doi.org/10.1145/1815330.1815356","mag":"1999067635"},"language":"en","primary_location":{"id":"doi:10.1145/1815330.1815356","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","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/A5004532741","display_name":"Pingping Xiu","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pingping Xiu","raw_affiliation_strings":["Lehigh Univ., Bethlehem, PA","Lehigh University Bethlehem PA"],"affiliations":[{"raw_affiliation_string":"Lehigh Univ., Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University Bethlehem PA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011850885","display_name":"Henry S. Baird","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry S. Baird","raw_affiliation_strings":["Lehigh Univ., Bethlehem, PA","Lehigh University Bethlehem PA"],"affiliations":[{"raw_affiliation_string":"Lehigh Univ., Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]},{"raw_affiliation_string":"Lehigh University Bethlehem PA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004532741"],"corresponding_institution_ids":["https://openalex.org/I186143895"],"apc_list":null,"apc_paid":null,"fwci":1.2749,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8052468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9943000078201294,"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":0.9890000224113464,"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":0.6661257147789001},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5870493650436401},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5738407373428345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5644619464874268},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.555264949798584},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5520666837692261},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.49666935205459595},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4816257357597351},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4485899806022644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44735726714134216},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.43304795026779175},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4316885471343994},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.42244020104408264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40087831020355225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3433438539505005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3414529860019684},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2022598683834076},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14020854234695435},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08264520764350891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661257147789001},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5870493650436401},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5738407373428345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644619464874268},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.555264949798584},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5520666837692261},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.49666935205459595},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4816257357597351},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4485899806022644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44735726714134216},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.43304795026779175},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4316885471343994},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.42244020104408264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40087831020355225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3433438539505005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3414529860019684},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2022598683834076},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14020854234695435},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08264520764350891},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1815330.1815356","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W27981834","https://openalex.org/W1593368611","https://openalex.org/W1980079039","https://openalex.org/W2021795960","https://openalex.org/W2036265926","https://openalex.org/W2051454481","https://openalex.org/W2074557738","https://openalex.org/W2106125148","https://openalex.org/W2119015427","https://openalex.org/W2152114086","https://openalex.org/W2167404062","https://openalex.org/W2168733012","https://openalex.org/W4244934065"],"related_works":["https://openalex.org/W3190162935","https://openalex.org/W2013767392","https://openalex.org/W2892857623","https://openalex.org/W2595338207","https://openalex.org/W2997809463","https://openalex.org/W1973075426","https://openalex.org/W2145230572","https://openalex.org/W338678865","https://openalex.org/W3002261956","https://openalex.org/W4230848040"],"abstract_inverted_index":{"Whole-book":[0],"recognition":[1,102,118,153,192,204],"is":[2],"a":[3,15,180],"document":[4],"image":[5,105,121],"analysis":[6],"strategy":[7,205],"that":[8,68],"operates":[9],"on":[10,130],"the":[11,54,57,60,78,85,94,110,164,166,168,170,202,209,213],"complete":[12],"set":[13,87],"of":[14,98,114,160],"book's":[16,181],"page":[17],"images,":[18],"attempting":[19],"to":[20,30,53,134,206],"improve":[21],"accuracy":[22],"by":[23,50,88,156],"automatic":[24],"unsupervised":[25],"adaptation.":[26],"Our":[27],"algorithm":[28,58,149],"expects":[29],"be":[31,82],"given":[32],"initial":[33],"iconic":[34,184],"and":[35,43,108,141,162,185,188],"linguistic":[36,125,186],"models---derived":[37],"from":[38,104,120],"(generally":[39,44],"errorful)":[40],"OCR":[41],"results":[42,103,119],"incomplete)":[45],"dictionaries---and":[46],"then,":[47],"guided":[48],"entirely":[49],"evidence":[51],"internal":[52],"test":[55,86],"set,":[56],"corrects":[59],"models":[61,79,178],"yielding":[62],"improved":[63],"accuracy.":[64],"We":[65,127,174],"have":[66],"found":[67],"successful":[69],"corrections":[70],"are":[71,144],"often":[72],"closely":[73],"associated":[74],"with":[75,124],"\"disagreements\"":[76],"between":[77,92],"which":[80],"can":[81,150],"detected":[83],"within":[84],"measuring":[89],"cross":[90],"entropy":[91],"(a)":[93],"posterior":[95,111],"probability":[96,112],"distribution":[97,113],"character":[99],"classes":[100,116],"(the":[101,117],"classification":[106,122],"alone),":[107],"(b)":[109],"word":[115],"combined":[123],"constraints).":[126],"report":[128],"experiments":[129],"long":[131],"passages":[132],"(up":[133],"180":[135],"pages)":[136],"revealing":[137],"that:":[138],"(1)":[139],"disagreements":[140],"error":[142,154,171],"rates":[143,155],"strongly":[145],"correlated;":[146],"(2)":[147],"our":[148,190],"drive":[151],"down":[152],"nearly":[157],"an":[158],"order":[159],"magnitude;":[161],"(3)":[163],"longer":[165],"passage,":[167],"lower":[169],"rate":[172],"achievable.":[173],"also":[175],"propose":[176],"formal":[177],"for":[179,183,189,201],"text,":[182],"constraints,":[187],"whole-book":[191,203],"algorithm---and,":[193],"using":[194],"these,":[195],"we":[196],"rigorously":[197],"prove":[198],"sufficient":[199],"conditions":[200],"succeed":[207],"in":[208,212],"ways":[210],"illustrated":[211],"experiments.":[214]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}