{"id":"https://openalex.org/W4394783472","doi":"https://doi.org/10.1007/s00371-024-03371-w","title":"A novel approach for improving open scene text translation with modified GAN","display_name":"A novel approach for improving open scene text translation with modified GAN","publication_year":2024,"publication_date":"2024-04-13","ids":{"openalex":"https://openalex.org/W4394783472","doi":"https://doi.org/10.1007/s00371-024-03371-w"},"language":"en","primary_location":{"id":"doi:10.1007/s00371-024-03371-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00371-024-03371-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00371-024-03371-w.pdf","source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Visual Computer","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00371-024-03371-w.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021539892","display_name":"Yasmeen Cheema","orcid":"https://orcid.org/0009-0000-2791-1822"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Yasmeen Cheema","raw_affiliation_strings":["School of Interdisciplinary Engineering & Sciences (SINES), National University of Sciences and Technology, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interdisciplinary Engineering & Sciences (SINES), National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101464117","display_name":"Muhammad Nadeem Cheema","orcid":"https://orcid.org/0000-0003-1306-2916"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Nadeem Cheema","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Attock, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Attock, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110596413","display_name":"Anam Nazir","orcid":null},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Anam Nazir","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Wah Cantt, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Wah Cantt, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085936899","display_name":"Fahad Ahmed Khokhar","orcid":"https://orcid.org/0009-0008-7890-4639"},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Fahad Ahmed Khokhar","raw_affiliation_strings":["Department of Mathematics and Information, University of Florence, Florence, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Information, University of Florence, Florence, Italy","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435494","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-1503-0240"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["Department of Computing and School of Design, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and School of Design, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100302212","display_name":"Ayaz Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ayaz Ahmed","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Wah Cantt, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Wah Cantt, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085936899"],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.7426,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85205616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"41","issue":"2","first_page":"869","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9890999794006348,"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":0.9797000288963318,"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":0.7448468804359436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573173761367798},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5302661657333374},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.46678125858306885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45643746852874756},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.45609888434410095},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4487546384334564},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.42970842123031616},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3254786729812622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448468804359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573173761367798},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5302661657333374},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.46678125858306885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45643746852874756},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.45609888434410095},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4487546384334564},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.42970842123031616},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3254786729812622},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00371-024-03371-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00371-024-03371-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00371-024-03371-w.pdf","source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Visual Computer","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00371-024-03371-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00371-024-03371-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00371-024-03371-w.pdf","source":{"id":"https://openalex.org/S73060445","display_name":"The Visual Computer","issn_l":"0178-2789","issn":["0178-2789","1432-2315"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Visual Computer","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322648","display_name":"Universit\u00e0 degli Studi di Firenze","ror":"https://ror.org/04jr1s763"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394783472.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1978729128","https://openalex.org/W2011181254","https://openalex.org/W2012875423","https://openalex.org/W2074378519","https://openalex.org/W2110158442","https://openalex.org/W2125416623","https://openalex.org/W2165736859","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2217433794","https://openalex.org/W2295936755","https://openalex.org/W2341629100","https://openalex.org/W2343052201","https://openalex.org/W2344822769","https://openalex.org/W2516018335","https://openalex.org/W2557414982","https://openalex.org/W2560835665","https://openalex.org/W2574887079","https://openalex.org/W2605982830","https://openalex.org/W2606911419","https://openalex.org/W2619328388","https://openalex.org/W2738361803","https://openalex.org/W2784050770","https://openalex.org/W2808950571","https://openalex.org/W2886603769","https://openalex.org/W2894532024","https://openalex.org/W2902494497","https://openalex.org/W2963212250","https://openalex.org/W2963420272","https://openalex.org/W2963648432","https://openalex.org/W2965336788","https://openalex.org/W2997095758","https://openalex.org/W3043547428","https://openalex.org/W3102695566","https://openalex.org/W4213106035","https://openalex.org/W4220904955","https://openalex.org/W4224064350","https://openalex.org/W4225683503","https://openalex.org/W4364377616","https://openalex.org/W4389672881","https://openalex.org/W6600076646","https://openalex.org/W6603527449","https://openalex.org/W6604253536","https://openalex.org/W6715877029","https://openalex.org/W6819060087"],"related_works":["https://openalex.org/W4288069866","https://openalex.org/W4389232935","https://openalex.org/W3155045749","https://openalex.org/W2936127876","https://openalex.org/W4387421677","https://openalex.org/W4213477128","https://openalex.org/W2957407072","https://openalex.org/W4312511225","https://openalex.org/W4281776416","https://openalex.org/W3094011899"],"abstract_inverted_index":{"Abstract":[0],"Text,":[1],"as":[2,32],"a":[3,25,46,127,211,230],"vital":[4],"tool":[5],"for":[6,91,107,130,177,189,203,237],"communication,":[7],"is":[8,253,304],"playing":[9],"an":[10],"imperative":[11],"role":[12],"in":[13,24,59,76,88,165,259],"modern":[14],"society.":[15],"Precise":[16],"high-level":[17],"text":[18,57,75,99,106,114,133,143,145,147,149,152,172,185,207,215,238,245],"translation":[19,100,179,246,308],"systems":[20,101,247],"are":[21],"essential":[22],"requirements":[23],"wide":[26],"range":[27],"of":[28,43,48,74,82,138,168,206,214,261,268,271,274],"real-world":[29,61],"applications,":[30],"such":[31],"robot":[33],"navigation,":[34],"industrial":[35],"automation,":[36],"image":[37,188],"search,":[38],"and":[39,72,80,84,109,151,180,216,277,290],"instant":[40],"translation.":[41,134],"Regardless":[42],"improved":[44,204],"research,":[45],"series":[47],"grand":[49],"challenges":[50],"may":[51],"still":[52],"become":[53],"upon":[54,306],"when":[55],"translating":[56],"automatically":[58],"the":[60,105,116,121,166,171,174,183,187,196,221],"from":[62,70,173],"open":[63,77,92,131,175],"scene":[64,93,132,142,156,176,217],"images.":[65,94],"The":[66,95,158],"difficulties":[67],"mainly":[68],"stem":[69],"multiplicity":[71],"inconsistency":[73],"scenes,":[78],"complication":[79],"obstruction":[81],"backgrounds,":[83],"deficient":[85],"imaging":[86],"conditions":[87],"uncontrolled":[89],"circumstances":[90],"existing":[96,197],"deep":[97],"learning-based":[98],"do":[102],"not":[103],"eliminate":[104],"translation,":[108,150],"these":[110],"applications":[111],"just":[112],"replace":[113],"on":[115,186,242],"reconstructed":[117],"scene.":[118],"To":[119],"address":[120],"abovementioned":[122],"shortcomings,":[123],"this":[124,226],"study":[125],"proposed":[126],"novel":[128,212],"approach":[129],"Our":[135],"system":[136,252],"consists":[137],"five":[139],"modules":[140],"including":[141],"detection,":[144],"recognition,":[146],"elimination,":[148],"insertion":[153],"along":[154],"with":[155],"reconstruction.":[157],"novelty":[159],"presented":[160],"by":[161,209],"our":[162,235,250],"model":[163],"lies":[164],"idea":[167],"first":[169],"eliminating":[170],"accurate":[178],"then":[181],"reconstructs":[182],"translated":[184],"its":[190],"proper":[191],"alignment.":[192],"We":[193,264],"specifically":[194],"modified":[195],"generative":[198],"adversarial":[199],"network":[200],"(GAN)":[201],"architecture":[202],"performance":[205],"elimination":[208,239],"introducing":[210],"strategy":[213],"concatenation":[218],"to":[219,233,255,301],"reduce":[220],"overall":[222],"loss":[223],"function.":[224],"For":[225],"purpose,":[227],"we":[228],"created":[229],"synthetic":[231],"dataset":[232],"train":[234],"GAN":[236],"module.":[240],"Experiments":[241],"various":[243],"standard":[244],"demonstrate":[248],"that":[249],"integrated":[251],"able":[254],"outperform":[256],"state-of-the-art":[257,307],"approaches":[258],"terms":[260],"result":[262],"quality.":[263],"have":[265],"achieved":[266],"90.87%":[267],"precision,":[269],"83.66%":[270],"recall,":[272],"87.116%":[273],"F":[275],"1-score,":[276],"reduced":[278],"both":[279],"losses":[280],"(":[281],"$$l_1$$":[282],"<mml:math":[283,292],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[284,293],"<mml:msub>":[285,294],"<mml:mi>l</mml:mi>":[286,295],"<mml:mn>1</mml:mn>":[287],"</mml:msub>":[288,297],"</mml:math>":[289,298],"$$l_2$$":[291],"<mml:mn>2</mml:mn>":[296],")":[299],"up":[300],"50%":[302],"which":[303],"remarkable":[305],"systems.":[309]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
