{"id":"https://openalex.org/W7161718530","doi":"https://doi.org/10.1109/access.2026.3694922","title":"MuSCAT: An End-to-End Multi-Scale Confidence-Aware Deep Framework for Understanding Text From Images in Unconstrained Environments","display_name":"MuSCAT: An End-to-End Multi-Scale Confidence-Aware Deep Framework for Understanding Text From Images in Unconstrained Environments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7161718530","doi":"https://doi.org/10.1109/access.2026.3694922"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3694922","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694922","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3694922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135978069","display_name":"Aditya Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131147","display_name":"SRM University","ror":"https://ror.org/037skf023","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018","https://openalex.org/I4210131147"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Patil","raw_affiliation_strings":["Department of Software and System Engineering, School of Computer Science and Engineering (SCOPE), VIT-AP University, Amaravati, Andhra Pradesh, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software and System Engineering, School of Computer Science and Engineering (SCOPE), VIT-AP University, Amaravati, Andhra Pradesh, India","institution_ids":["https://openalex.org/I4210131147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084522547","display_name":"Tauseef Khan","orcid":"https://orcid.org/0000-0002-3713-2248"},"institutions":[{"id":"https://openalex.org/I4210131147","display_name":"SRM University","ror":"https://ror.org/037skf023","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018","https://openalex.org/I4210131147"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tauseef Khan","raw_affiliation_strings":["Department of Software and System Engineering, School of Computer Science and Engineering (SCOPE), VIT-AP University, Amaravati, Andhra Pradesh, India"],"raw_orcid":"https://orcid.org/0000-0002-3359-9967","affiliations":[{"raw_affiliation_string":"Department of Software and System Engineering, School of Computer Science and Engineering (SCOPE), VIT-AP University, Amaravati, Andhra Pradesh, India","institution_ids":["https://openalex.org/I4210131147"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049120490","display_name":"Ayatullah Faruk Mollah","orcid":"https://orcid.org/0000-0002-3445-7469"},"institutions":[{"id":"https://openalex.org/I180765649","display_name":"Aliah University","ror":"https://ror.org/03rfycd69","country_code":"IN","type":"education","lineage":["https://openalex.org/I180765649"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ayatullah Faruk Mollah","raw_affiliation_strings":["Department of Computer Science and Engineering, Aliah University, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0002-3445-7469","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Aliah University, Kolkata, India","institution_ids":["https://openalex.org/I180765649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79743605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"77906","last_page":"77930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.304500013589859,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.304500013589859,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.19020000100135803,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16130000352859497,"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/visualization","display_name":"Visualization","score":0.3610999882221222},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32519999146461487},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3212999999523163},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3197000026702881},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3073999881744385},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2913999855518341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906999707221985},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4596000015735626},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3694922","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694922","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f582d4ffa72544bab3ea7c79371784fe","is_oa":true,"landing_page_url":"https://doaj.org/article/f582d4ffa72544bab3ea7c79371784fe","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 77906-77930 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3694922","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3694922","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.48192599415779114,"display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322947","display_name":"Sichuan University of Science and Engineering","ror":"https://ror.org/053fzma23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"texts":[1],"from":[2,10,77],"imagery":[3],"is":[4,25,71],"pertinent":[5],"for":[6,73],"diverse":[7,40],"applications":[8],"ranging":[9],"traditional":[11],"text-embedded":[12],"image":[13],"reading":[14,21],"to":[15,29],"perceiving":[16],"text-labeled":[17],"environments.":[18],"However,":[19],"text":[20,41,75,98,107,121,154],"in":[22,57,153,159],"the":[23,111,119,176,180,186],"wild":[24,60],"quite":[26],"challenging":[27],"due":[28],"environmental":[30],"heterogeneity,":[31],"degradation":[32],"and":[33,59,79,115,145,147,157,183,191,196],"deformation":[34],"of":[35,87,96,102,118,134,173],"acquired":[36],"images,":[37],"multi-lingual":[38],"scenarios,":[39],"appearance,":[42],"etc.":[43],"Though":[44],"recent":[45],"deep":[46,69],"learning":[47],"approaches":[48],"are":[49],"demonstrating":[50],"reasonably":[51],"good":[52],"performance,":[53],"they":[54],"often":[55],"struggle":[56],"complex":[58,78],"imagery.":[61],"In":[62],"this":[63],"paper,":[64],"a":[65,103,132],"novel":[66],"multi-scale":[67,97],"end-to-end":[68],"framework":[70],"presented":[72],"effective":[74],"understanding":[76],"multilingual":[80],"scene":[81,142],"images.":[82],"It":[83,166],"involves":[84],"(i)":[85],"crafting":[86],"fuzzy":[88,112],"textness":[89,113],"map":[90],"with":[91],"VGG-16":[92],"driven":[93],"class-confidence":[94],"aggregation":[95],"proposals,":[99],"(ii)":[100],"designing":[101],"soft-to-hard":[104],"tuneable":[105],"tightness-aware":[106],"detection":[108],"technique":[109],"using":[110],"map,":[114],"(iii)":[116],"recognition":[117,156],"detected":[120],"regions":[122],"followed":[123],"by":[124],"translation":[125,158],"into":[126],"native":[127],"language.":[128],"Rigorous":[129],"experiments":[130],"over":[131],"number":[133],"related":[135],"benchmark":[136],"datasets":[137],"viz.":[138],"ICDAR":[139,181],"2013":[140,182],"focused":[141],"text,":[143],"AU-MSTR":[144],"Total-Text":[146],"obtained":[148],"findings":[149],"demonstrate":[150],"high":[151],"accuracy":[152],"extraction,":[155],"uncontrollable":[160],"environments,":[161],"outperforming":[162],"other":[163],"contemporary":[164],"methods.":[165],"has":[167],"produced":[168],"an":[169],"overall":[170],"f-measure":[171],"score":[172],"85.39%":[174],"on":[175,179,185],"AU-MSTR,":[177],"86.03%":[178],"81.69%":[184],"Total-Text,":[187],"indicating":[188],"its":[189],"effectiveness":[190],"robustness.":[192],"The":[193],"source":[194],"codes":[195],"documentation":[197],"have":[198],"been":[199],"publicly":[200],"released":[201],"at":[202],"https://github.com/adinp1213/MuSCATText-Reader.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}
