{"id":"https://openalex.org/W4416183442","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223364","title":"Exploring Light-Weight Object Recognition for Real-Time Document Detection","display_name":"Exploring Light-Weight Object Recognition for Real-Time Document Detection","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4416183442","doi":"https://doi.org/10.1109/sibgrapi67909.2025.11223364"},"language":null,"primary_location":{"id":"doi:10.1109/sibgrapi67909.2025.11223364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","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/A5092749484","display_name":"Lucas Wojcik","orcid":null},"institutions":[{"id":"https://openalex.org/I52418104","display_name":"Universidade Federal do Paran\u00e1","ror":"https://ror.org/05syd6y78","country_code":"BR","type":"education","lineage":["https://openalex.org/I52418104"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Lucas Wojcik","raw_affiliation_strings":["Federal University of Paraná,Curitiba,PR,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Paraná,Curitiba,PR,Brazil","institution_ids":["https://openalex.org/I52418104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013645472","display_name":"Luiz Coelho","orcid":"https://orcid.org/0000-0002-0561-0612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luiz Coelho","raw_affiliation_strings":["unico - idTech,Brazil"],"affiliations":[{"raw_affiliation_string":"unico - idTech,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066324951","display_name":"Roger Granada","orcid":"https://orcid.org/0000-0001-5908-9247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roger Granada","raw_affiliation_strings":["unico - idTech,Brazil"],"affiliations":[{"raw_affiliation_string":"unico - idTech,Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033489756","display_name":"David Menotti","orcid":"https://orcid.org/0000-0003-2430-2030"},"institutions":[{"id":"https://openalex.org/I52418104","display_name":"Universidade Federal do Paran\u00e1","ror":"https://ror.org/05syd6y78","country_code":"BR","type":"education","lineage":["https://openalex.org/I52418104"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"David Menotti","raw_affiliation_strings":["Federal University of Paraná,Curitiba,PR,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Paraná,Curitiba,PR,Brazil","institution_ids":["https://openalex.org/I52418104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092749484"],"corresponding_institution_ids":["https://openalex.org/I52418104"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36812089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8974000215530396,"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":0.8974000215530396,"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":0.03500000014901161,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.02979999966919422,"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/skew","display_name":"Skew","score":0.7491999864578247},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7486000061035156},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.5907999873161316},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5350000262260437},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.527999997138977},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5005999803543091},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4334999918937683},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.3806999921798706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3781999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032000064849854},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7491999864578247},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7486000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593500018119812},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.5907999873161316},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5350000262260437},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5005999803543091},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3222000002861023},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sibgrapi67909.2025.11223364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sibgrapi67909.2025.11223364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","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":12,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2895160027","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2967615747","https://openalex.org/W3129621855","https://openalex.org/W3177126114","https://openalex.org/W3199859411","https://openalex.org/W4281968684","https://openalex.org/W4308234030"],"related_works":[],"abstract_inverted_index":{"Object":[0,142],"Recognition":[1,83,143],"and":[2,15,29,39,86,100,117,125,144,161,237],"Document":[3],"Skew":[4,145],"Estimation":[5,146],"have":[6,221],"come":[7],"a":[8,42,54,95,107,180,207,214,246],"long":[9],"way":[10],"in":[11,78],"terms":[12,79],"of":[13,21,80],"performance":[14,25,208,228],"efficiency.":[16],"New":[17],"models":[18],"follow":[19],"one":[20],"two":[22],"directions:":[23],"improving":[24,30],"using":[26,32,179],"larger":[27],"models,":[28],"efficiency":[31],"smaller":[33,236],"models.":[34],"However,":[35],"real-time":[36],"document":[37,72,127,217],"detection":[38,73,98,104],"rectification":[40,218],"is":[41,45,76,166,176,194,235,253],"niche":[43],"that":[44,75,212,232],"largely":[46],"unexplored":[47],"by":[48,169],"the":[49,131,135,141,163,187,191,202],"literature,":[50],"yet":[51],"it":[52,102],"remains":[53],"vital":[55],"step":[56],"for":[57,103,134,150],"automatic":[58,197],"information":[59,198],"retrieval":[60,85],"from":[61,139],"visual":[62],"documents.":[63],"In":[64],"this":[65],"work,":[66],"we":[67,200],"strive":[68],"towards":[69],"an":[70,170],"efficient":[71,239],"pipeline":[74],"satisfactory":[77],"Optical":[81],"Character":[82],"(OCR)":[84],"faster":[87],"than":[88,240],"other":[89],"available":[90,254],"solutions.":[91],"We":[92,112,155,210,230],"adapt":[93],"IWPOD-Net,":[94],"license":[96],"plate":[97],"network,":[99],"train":[101],"on":[105,186],"NBID,":[106],"synthetic":[108,123],"ID":[109,124],"card":[110],"dataset.":[111],"experiment":[113],"with":[114,120,152,213],"data":[115],"augmentation":[116],"cross-dataset":[118],"validation":[119],"MIDV":[121],"(another":[122],"passport":[126],"dataset)":[128],"to":[129,159,195,222,225],"find":[130],"optimal":[132],"scenario":[133],"model.":[136],"Other":[137],"methods":[138],"both":[140],"state-of-the-art":[147,227,242],"are":[148],"evaluated":[149,178],"comparison":[151],"our":[153,233],"approach.":[154],"use":[156,201],"each":[157],"method":[158],"detect":[160],"rectify":[162],"document,":[164],"which":[165],"then":[167,177],"read":[168],"OCR":[171,174,182,204,248],"system.":[172],"The":[173],"output":[175],"novel":[181],"quality":[183,205,249],"metric":[184],"based":[185],"Levenshtein":[188],"distance.":[189],"Since":[190],"end":[192],"goal":[193],"improve":[196],"retrieval,":[199],"overall":[203],"as":[206],"metric.":[209,250],"observe":[211],"promising":[215],"model,":[216],"does":[219],"not":[220],"be":[223],"perfect":[224],"attain":[226],"scores.":[229],"show":[231],"model":[234],"more":[238],"current":[241],"solutions":[243],"while":[244],"retaining":[245],"competitive":[247],"All":[251],"code":[252],"at":[255],"https://github.com/BOVIFOCR/iwpod-doc-corners.git":[256]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-11T00:00:00"}