{"id":"https://openalex.org/W3021512437","doi":"https://doi.org/10.1109/wacv45572.2020.9093532","title":"DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images","display_name":"DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3021512437","doi":"https://doi.org/10.1109/wacv45572.2020.9093532","mag":"3021512437"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5020795030","display_name":"Yike Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155099","display_name":"Ernst & Young (Israel)","ror":"https://ror.org/049kt3f30","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210108721","https://openalex.org/I4210155099"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yike Qi","raw_affiliation_strings":["Ernst & Young LLP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ernst & Young LLP","institution_ids":["https://openalex.org/I4210155099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103901590","display_name":"W. Ronny Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155099","display_name":"Ernst & Young (Israel)","ror":"https://ror.org/049kt3f30","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210108721","https://openalex.org/I4210155099"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"W. Ronny Huang","raw_affiliation_strings":["Ernst & Young LLP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ernst & Young LLP","institution_ids":["https://openalex.org/I4210155099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383897","display_name":"Qianqian Li","orcid":"https://orcid.org/0000-0002-3866-8159"},"institutions":[{"id":"https://openalex.org/I4210155099","display_name":"Ernst & Young (Israel)","ror":"https://ror.org/049kt3f30","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210108721","https://openalex.org/I4210155099"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Qianqian Li","raw_affiliation_strings":["Ernst & Young LLP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ernst & Young LLP","institution_ids":["https://openalex.org/I4210155099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085670535","display_name":"Jonathan Degange","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155099","display_name":"Ernst & Young (Israel)","ror":"https://ror.org/049kt3f30","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210108721","https://openalex.org/I4210155099"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jonathan L. DeGange","raw_affiliation_strings":["Ernst & Young LLP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ernst & Young LLP","institution_ids":["https://openalex.org/I4210155099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210155099"],"apc_list":null,"apc_paid":null,"fwci":0.2563,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.54356273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3511","last_page":"3519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9976999759674072,"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":0.9925000071525574,"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/optical-character-recognition","display_name":"Optical character recognition","score":0.8266817331314087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8186149001121521},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6851980686187744},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.6751200556755066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6577705144882202},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.6385881304740906},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.635713517665863},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.5787988305091858},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5165149569511414},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.5012028217315674},{"id":"https://openalex.org/keywords/inkwell","display_name":"Inkwell","score":0.49130406975746155},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.436244398355484},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4241848587989807},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4100346863269806},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36383891105651855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.24785494804382324},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2235375940799713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14970707893371582}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8266817331314087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186149001121521},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6851980686187744},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.6751200556755066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6577705144882202},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.6385881304740906},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.635713517665863},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.5787988305091858},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5165149569511414},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.5012028217315674},{"id":"https://openalex.org/C109693293","wikidata":"https://www.wikidata.org/wiki/Q1496072","display_name":"Inkwell","level":2,"score":0.49130406975746155},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.436244398355484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4241848587989807},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4100346863269806},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36383891105651855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.24785494804382324},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2235375940799713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14970707893371582},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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":33,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1905829557","https://openalex.org/W1945616565","https://openalex.org/W2107249111","https://openalex.org/W2127141656","https://openalex.org/W2152928267","https://openalex.org/W2154579312","https://openalex.org/W2155912251","https://openalex.org/W2162651021","https://openalex.org/W2163288728","https://openalex.org/W2170942820","https://openalex.org/W2404161646","https://openalex.org/W2519818067","https://openalex.org/W2772325643","https://openalex.org/W2775550436","https://openalex.org/W2786940623","https://openalex.org/W2947697927","https://openalex.org/W2962707697","https://openalex.org/W2962903028","https://openalex.org/W2963136605","https://openalex.org/W2963207607","https://openalex.org/W2963881378","https://openalex.org/W2964010994","https://openalex.org/W2964099383","https://openalex.org/W2964346820","https://openalex.org/W2986619406","https://openalex.org/W6639824700","https://openalex.org/W6640425456","https://openalex.org/W6682751323","https://openalex.org/W6704241340","https://openalex.org/W6713197267","https://openalex.org/W6746301500"],"related_works":["https://openalex.org/W2000372441","https://openalex.org/W2573990671","https://openalex.org/W3090423411","https://openalex.org/W3021512437","https://openalex.org/W2543788071","https://openalex.org/W4388916331","https://openalex.org/W2132474504","https://openalex.org/W124974609","https://openalex.org/W4297207721","https://openalex.org/W3092015448"],"abstract_inverted_index":{"Paper-intensive":[0],"industries":[1],"like":[2],"insurance,":[3],"law,":[4],"and":[5,36,139,147,213,226],"government":[6],"have":[7,89],"long":[8],"leveraged":[9],"optical":[10],"character":[11],"recognition":[12,106,188],"(OCR)":[13],"to":[14,46,122,133,150,173],"automatically":[15,165],"transcribe":[16],"hordes":[17],"of":[18,80,105,207],"scanned":[19,34,208],"documents":[20,35,52],"into":[21,40,142],"text":[22,82,86,127,137,145],"strings":[23],"for":[24],"downstream":[25,110],"processing.":[26],"Even":[27],"in":[28,42,156,187,217],"2019,":[29],"there":[30],"are":[31,164,221],"still":[32],"many":[33],"mail":[37],"that":[38,179],"come":[39],"businesses":[41],"non-digital":[43],"format.":[44],"Text":[45],"be":[47],"extracted":[48],"from":[49,126],"real":[50,136,140],"world":[51],"is":[53],"often":[54,72],"nestled":[55],"inside":[56],"rich":[57],"formatting,":[58],"such":[59,194],"as":[60,195],"tabular":[61],"structures":[62],"or":[63,68,74,93,108],"forms":[64,212],"with":[65,102],"fill-in-the-blank":[66],"boxes":[67],"underlines":[69],"whose":[70],"ink":[71,79,91,97,124],"touches":[73],"even":[75],"strikes":[76],"through":[77],"the":[78,81,85,103,168],"itself.":[83],"Further,":[84],"region":[87],"could":[88],"random":[90],"smudges":[92],"spurious":[94],"strokes.":[95],"Such":[96],"artifacts":[98,125,141],"can":[99],"severely":[100],"interfere":[101],"performance":[104],"algorithms":[107],"other":[109],"processing":[111],"tasks.":[112],"In":[113,171],"this":[114],"work,":[115],"we":[116,177,199],"propose":[117],"DeepErase,":[118],"a":[119,131,157,184],"neural-based":[120],"preprocessor":[121],"erase":[123],"images.":[128],"We":[129],"devise":[130],"method":[132],"programmatically":[134],"assemble":[135],"images":[138,182],"realistic-looking":[143],"\"dirty\"":[144],"images,":[146],"use":[148],"them":[149],"train":[151],"an":[152],"artifact":[153],"segmentation":[154,175],"network":[155],"weakly":[158],"supervised":[159],"manner,":[160],"since":[161],"pixel-level":[162],"annotations":[163],"obtained":[166],"during":[167],"assembly":[169],"process.":[170],"addition":[172],"high":[174],"accuracy,":[176],"show":[178],"our":[180],"cleansed":[181],"achieve":[183,214],"significant":[185],"boost":[186],"accuracy":[189],"by":[190],"popular":[191],"OCR":[192],"software":[193],"Tesseract":[196],"4.0.":[197],"Finally,":[198],"test":[200],"DeepErase":[201],"on":[202,223],"out-of-distribution":[203],"datasets":[204],"(NIST":[205],"SDB)":[206],"IRS":[209],"tax":[210],"return":[211],"double-digit":[215],"improvements":[216],"accuracy.":[218],"All":[219],"experiments":[220],"performed":[222],"both":[224],"printed":[225],"handwritten":[227],"text.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}