{"id":"https://openalex.org/W4376479381","doi":"https://doi.org/10.1145/3571600.3571645","title":"Automatic Annotation of Handwritten Document Images at Word Level","display_name":"Automatic Annotation of Handwritten Document Images at Word Level","publication_year":2022,"publication_date":"2022-12-08","ids":{"openalex":"https://openalex.org/W4376479381","doi":"https://doi.org/10.1145/3571600.3571645"},"language":"en","primary_location":{"id":"doi:10.1145/3571600.3571645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3571600.3571645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing","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/A5052301812","display_name":"Ajoy Mondal","orcid":"https://orcid.org/0000-0002-4808-8860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ajoy Mondal","raw_affiliation_strings":["CVIT, International Institute of Information Technology, IN"],"raw_orcid":"https://orcid.org/0000-0002-4808-8860","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058942781","display_name":"Krishna Tulsyan","orcid":"https://orcid.org/0000-0003-0177-588X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna Tulsyan","raw_affiliation_strings":["CVIT, International Institute of Information Technology, IN"],"raw_orcid":"https://orcid.org/0000-0003-0177-588X","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, IN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C.V. Jawahar","raw_affiliation_strings":["CVIT, International Institute of Information Technology, IN"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"CVIT, International Institute of Information Technology, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2936,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55227001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9944999814033508,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8660435676574707},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8507207632064819},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7446612119674683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.715732991695404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.697964072227478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44255298376083374},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4359324872493744},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.4356307089328766},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41205137968063354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35027727484703064},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.08269843459129333},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07692384719848633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660435676574707},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8507207632064819},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7446612119674683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.715732991695404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.697964072227478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44255298376083374},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4359324872493744},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.4356307089328766},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41205137968063354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35027727484703064},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.08269843459129333},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07692384719848633},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3571600.3571645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3571600.3571645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1491083719","https://openalex.org/W2016829658","https://openalex.org/W2107645346","https://openalex.org/W2118013826","https://openalex.org/W2133098817","https://openalex.org/W2147510700","https://openalex.org/W2152928267","https://openalex.org/W2155450843","https://openalex.org/W2170472910","https://openalex.org/W2297788108","https://openalex.org/W2577429903","https://openalex.org/W2785820430","https://openalex.org/W2786429113","https://openalex.org/W2793404167","https://openalex.org/W2810296118","https://openalex.org/W2895359355","https://openalex.org/W2904970205","https://openalex.org/W2915106267","https://openalex.org/W2916222163","https://openalex.org/W2946921758","https://openalex.org/W2967615747","https://openalex.org/W3003428515","https://openalex.org/W3003915459","https://openalex.org/W3003967978","https://openalex.org/W3031548983","https://openalex.org/W3034904792","https://openalex.org/W3038203375","https://openalex.org/W3083907077","https://openalex.org/W3109563519","https://openalex.org/W3109645351","https://openalex.org/W3134182987","https://openalex.org/W3197061335","https://openalex.org/W3201139606","https://openalex.org/W4243521730","https://openalex.org/W4247264488","https://openalex.org/W4285167662"],"related_works":["https://openalex.org/W2140449480","https://openalex.org/W2112800125","https://openalex.org/W178422364","https://openalex.org/W2069374145","https://openalex.org/W2401522294","https://openalex.org/W1962828410","https://openalex.org/W2358212252","https://openalex.org/W3197877226","https://openalex.org/W2382772676","https://openalex.org/W2158882055"],"abstract_inverted_index":{"Recent":[0],"development":[1],"in":[2,101,115,122,136,194],"deep":[3],"learning-based":[4],"recognizers":[5],"needs":[6],"a":[7,17,30],"large":[8,18],"annotated":[9,149,202],"corpus":[10,19],"for":[11,32,39,168],"creating":[12],"the":[13,36,76,80,102,105,126,134,137,143,165,204,209],"model.":[14],"Manually":[15],"annotating":[16,169],"is":[20,96],"time-consuming,":[21],"costly,":[22],"and":[23,43,66,70,78,88,92,110,141,154,177],"tedious.":[24],"In":[25,160],"this":[26,161],"work,":[27,162],"we":[28,146,163],"propose":[29],"framework":[31,51],"automatic":[33,138,205],"annotation":[34,139,206],"at":[35],"word":[37,59,62,106,127,152],"level":[38],"given":[40],"handwritten":[41,183,191],"data":[42],"corresponding":[44,156,172],"text":[45,81,123],"sequences":[46],"(or":[47],"corpora).":[48],"The":[49,72,117,129],"proposed":[50,166],"consists":[52],"of":[53,113,190,198],"five":[54],"modules":[55,90],"(i)":[56],"pre-processing,":[57],"(ii)":[58],"detection,":[60],"(iii)":[61],"recognition,":[63],"(iv)":[64],"alignment,":[65],"(v)":[67],"manual":[68],"correction":[69],"verification.":[71],"pre-processing":[73],"module":[74,119],"cleans":[75],"image":[77],"crops":[79],"region":[82],"from":[83],"an":[84,148,187],"image.":[85],"Word":[86],"detection":[87,109],"recognition":[89,111],"localize":[91],"recognize":[93],"words.":[94],"It":[95],"necessary":[97],"to":[98,125,173],"align":[99],"words":[100,121,199],"sequence":[103,124],"with":[104],"images":[107,153,193],"during":[108],"because":[112],"errors":[114,135],"writing.":[116],"alignment":[118],"aligns":[120],"images.":[128,185],"human":[130],"annotator":[131],"will":[132],"correct":[133],"process":[140],"verify":[142],"document.":[144],"Finally,":[145],"created":[147],"dataset":[150],"containing":[151],"their":[155],"ground":[157],"truth":[158],"transcriptions.":[159],"demonstrate":[164],"tool":[167],"14":[170,195],"sets":[171],"13":[174],"Indic":[175],"languages":[176],"English.":[178],"Each":[179],"set":[180],"contains":[181],"15000":[182],"document":[184,192],"On":[186],"extensive":[188],"collection":[189],"languages,":[196],"80%":[197],"are":[200,212],"correctly":[201],"by":[203],"tool,":[207],"while":[208],"remaining":[210],"20%":[211],"corrected":[213],"manually.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}