{"id":"https://openalex.org/W2263909771","doi":null,"title":"Probabilistic random field based method for annotated machine printed documents preprocessing","display_name":"Probabilistic random field based method for annotated machine printed documents preprocessing","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2263909771","mag":"2263909771"},"language":"en","primary_location":{"id":"mag:2263909771","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2126201&coll=DL&dl=GUIDE","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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","observed_orcids":["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":false,"raw_author_name":"Venu Govindaraju","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":"https://orcid.org/0000-0002-5318-7409","affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102329211","display_name":"Xujun Peng","orcid":"https://orcid.org/0000-0001-9373-7092","observed_orcids":["https://orcid.org/0000-0001-9373-7092"]},"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":"Xujun Peng","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":"https://orcid.org/0000-0001-9373-7092","affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/handwritten-text-segmentation","display_name":"handwritten text segmentation","score":0.824999988079071},{"id":"https://openalex.org/keywords/document-image-binarization","display_name":"document image binarization","score":0.8289999961853027},{"id":"https://openalex.org/keywords/markov-random-fields","display_name":"Markov random fields","score":0.8410000205039978},{"id":"https://openalex.org/keywords/authorship-attribution","display_name":"authorship attribution","score":0.5249999761581421},{"id":"https://openalex.org/keywords/document-restoration","display_name":"document restoration","score":0.6610000133514404},{"id":"https://openalex.org/keywords/document-image-preprocessing","display_name":"document preprocessing","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461964130401611},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.6197212338447571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607452392578125},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.5507432818412781},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.5472001433372498},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.53956139087677},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4705142080783844},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46514713764190674},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4524567723274231},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.44601088762283325},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44079554080963135},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.43348023295402527},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4255439341068268},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42079252004623413},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4057299494743347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3680059313774109},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3549495339393616},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28373855352401733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22265177965164185},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14898046851158142},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14820218086242676},{"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/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":"mag:2263909771","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2126201&coll=DL&dl=GUIDE","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W79315950","https://openalex.org/W172100085","https://openalex.org/W195353558","https://openalex.org/W1540371141","https://openalex.org/W1600276254","https://openalex.org/W1647671624","https://openalex.org/W1651266332","https://openalex.org/W1878940107","https://openalex.org/W1982374960","https://openalex.org/W1988790447","https://openalex.org/W1994221780","https://openalex.org/W2003180120","https://openalex.org/W2020999234","https://openalex.org/W2024046085","https://openalex.org/W2024060531","https://openalex.org/W2030837774","https://openalex.org/W2032210760","https://openalex.org/W2048448061","https://openalex.org/W2052881412","https://openalex.org/W2056760934","https://openalex.org/W2057175746","https://openalex.org/W2059128991","https://openalex.org/W2066221198","https://openalex.org/W2072610689","https://openalex.org/W2075211019","https://openalex.org/W2077079264","https://openalex.org/W2083931206","https://openalex.org/W2096127742","https://openalex.org/W2097074225","https://openalex.org/W2099212718","https://openalex.org/W2100176260","https://openalex.org/W2105408040","https://openalex.org/W2106321936","https://openalex.org/W2106666564","https://openalex.org/W2110212011","https://openalex.org/W2111522305","https://openalex.org/W2112525419","https://openalex.org/W2113137767","https://openalex.org/W2114864744","https://openalex.org/W2116862786","https://openalex.org/W2117203466","https://openalex.org/W2117671208","https://openalex.org/W2120689934","https://openalex.org/W2122023903","https://openalex.org/W2122929638","https://openalex.org/W2125378844","https://openalex.org/W2126447465","https://openalex.org/W2128060444","https://openalex.org/W2128647679","https://openalex.org/W2130475102","https://openalex.org/W2133059825","https://openalex.org/W2134427664","https://openalex.org/W2135164809","https://openalex.org/W2135249422","https://openalex.org/W2135493362","https://openalex.org/W2137827331","https://openalex.org/W2138714160","https://openalex.org/W2139565439","https://openalex.org/W2141272333","https://openalex.org/W2143363968","https://openalex.org/W2145073242","https://openalex.org/W2146514558","https://openalex.org/W2146914716","https://openalex.org/W2149454242","https://openalex.org/W2149760002","https://openalex.org/W2150753219","https://openalex.org/W2156175024","https://openalex.org/W2156930033","https://openalex.org/W2158271210","https://openalex.org/W2159080219","https://openalex.org/W2159680539","https://openalex.org/W2165463593","https://openalex.org/W2166103567","https://openalex.org/W2166978545","https://openalex.org/W2169696215","https://openalex.org/W2994982620","https://openalex.org/W3097096317","https://openalex.org/W4253186002"],"related_works":["https://openalex.org/W7097727071","https://openalex.org/W1968525573","https://openalex.org/W7099556484","https://openalex.org/W2099212718","https://openalex.org/W2052881412","https://openalex.org/W7095926142","https://openalex.org/W2095428880","https://openalex.org/W7099211234","https://openalex.org/W2165463593","https://openalex.org/W2106666564"],"abstract_inverted_index":{"Today,":[0],"the":[1,7,14,27,38,68,85,90,101,148,162,194,211,227,261,276,280,323,328,337,341,350,367,375],"convenience":[2],"of":[3,26,30,43,93,113,133,150,161,164,174,196,317,340,369],"search,":[4],"both":[5],"on":[6,13,171,200,231,306,383],"personal":[8],"computer":[9],"hard":[10],"disk":[11],"and":[12,23,159,177,269,335,388],"web,":[15],"is":[16,131,189,215,354],"essentially":[17],"limited":[18],"to":[19,146,209,225,274,325,331,343],"machine-printed":[20,50,377],"text":[21,286],"documents":[22,51],"images":[24,198],"because":[25],"poor":[28],"accuracy":[29],"handwriting":[31],"recognizers.":[32],"The":[33,238,255,284],"proposed":[34,86,130],"research":[35,128],"will":[36,47,107,242,258,287,301,359],"advance":[37],"state-of-the-art":[39],"in":[40,61,104,117],"realizing":[41],"search":[42],"hand-annotated":[44],"documents.":[45],"We":[46,98,183,320],"primarily":[48,155],"target":[49],"which":[52,120,214],"have":[53,184,321,380],"been":[54],"annotated":[55],"by":[56,58,191,217,362],"hand":[57],"multiple":[59],"writers":[60],"an":[62,94,345],"office/collaborative":[63],"environment.":[64],"In":[65],"applications":[66],"where":[67],"annotations":[69,329],"are":[70,178],"action":[71],"instructions":[72],"(such":[73],"as,":[74],"\u201cmake":[75],"4":[76],"copies\u201d,":[77],"\u201cremove":[78],"Figure":[79],"X\u201d":[80],"etc.)":[81],"we":[82],"can":[83],"envision":[84],"system":[87,187,342],"serving":[88],"as":[89,147,313],"front":[91],"end":[92,338],"OCR-based":[95],"NLP":[96],"module.":[97],"expect":[99],"that":[100,132,188],"techniques":[102,154],"developed":[103,185],"this":[105],"dissertation":[106],"be":[108,288,302,360],"also":[109],"useful":[110],"for":[111,119,249],"retrieval":[112],"pages":[114],"from":[115],"material":[116],"languages":[118],"accurate":[121],"OCRs":[122],"do":[123],"not":[124,179,373],"exist.":[125],"\r\nThe":[126,296],"main":[127],"task":[129,149],"segmenting":[134],"handwritten":[135,298],"text,":[136,139,143],"machine":[137],"printed":[138],"noise":[140],"or":[141],"overlapped":[142,285],"sometimes":[144],"referred":[145],"\u201dink":[151],"separation\u201d.":[152],"Prior":[153],"use":[156,270],"histogram":[157],"thresholding":[158],"analysis":[160],"connectivity":[163],"strokes.":[165],"These":[166],"algorithms,":[167],"although":[168],"effective,":[169],"rely":[170],"heuristic":[172],"rules":[173],"spatial":[175],"constraints,":[176],"scalable":[180],"across":[181],"applications.":[182],"a":[186,205,218,236,244,271,292,332,384],"composed":[190],"three":[192],"parts:":[193],"binariztion":[195],"document":[197,247,347,352,364,386],"(focus":[199],"hand-held":[201],"devices":[202],"captured":[203],"documents),":[204],"boosted":[206],"tree":[207,257],"classifier":[208,273],"perform":[210],"initial":[212,228,277],"classification":[213],"followed":[216],"Markov":[219],"random":[220],"field":[221],"(MRF)":[222],"based":[223,230,240,294,305],"approach":[224],"re-label":[226],"segments":[229],"their":[232],"statistical":[233],"dependencies":[234],"within":[235],"neighborhood.":[237],"MRF":[239,293],"binarization":[241],"provide":[243],"reliable":[245],"binarized":[246],"image":[248,353],"segmentation":[250],"even":[251,348],"with":[252],"bad":[253],"illumination.":[254],"boost":[256],"allow":[259,336],"dividing":[260],"training":[262],"data":[263],"set":[264],"into":[265],"several":[266],"small":[267],"clusters":[268],"simple":[272],"solve":[275],"labeling":[278],"at":[279],"cluster":[281],"(homogeneous)":[282],"levels.":[283],"further":[289],"separated":[290],"using":[291],"method.":[295],"isolated":[297],"textual":[299],"blocks":[300],"indexed":[303],"(unsupervised)":[304],"writing":[307],"instrument,":[308],"style,":[309],"ink":[310],"color,":[311],"etc.":[312],"being":[314],"possible":[315],"indicators":[316],"different":[318],"writers.":[319],"shown":[322],"ability":[324],"selectively":[326],"remove":[327],"belonging":[330],"particular":[333],"writer":[334],"user":[339],"view":[344],"unmarked":[346],"though":[349],"original":[351],"marked":[355],"up.":[356],"This":[357],"feature":[358],"accomplished":[361],"intelligent":[363],"restoration":[365],"whereby":[366],"removal":[368],"overlapping":[370],"strokes":[371],"does":[372],"damage":[374],"underlying":[376],"text.":[378],"\r\nWe":[379],"performed":[381],"experiments":[382],"large":[385],"dataset":[387],"report":[389],"results.":[390]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}