{"id":"https://openalex.org/W4413826416","doi":"https://doi.org/10.1145/3704268.3742690","title":"Text Image Super-Resolution for Improved OCR in Real-Life Scenarios using Swin Transformers","display_name":"Text Image Super-Resolution for Improved OCR in Real-Life Scenarios using Swin Transformers","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413826416","doi":"https://doi.org/10.1145/3704268.3742690"},"language":"en","primary_location":{"id":"doi:10.1145/3704268.3742690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742690","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742690","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086868619","display_name":"Philipp Hildebrandt","orcid":"https://orcid.org/0000-0002-0965-513X"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Philipp Hildebrandt","raw_affiliation_strings":["Hasso-Plattner-Institut, University of Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018534999","display_name":"Mareike Schulze","orcid":"https://orcid.org/0000-0002-4691-1219"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Schulze","raw_affiliation_strings":["Hasso-Plattner-Institut, University of Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049884582","display_name":"Sarel Cohen","orcid":"https://orcid.org/0000-0003-4578-1245"},"institutions":[{"id":"https://openalex.org/I4210141777","display_name":"Academic College of Tel Aviv-Yafo","ror":"https://ror.org/04cg6c004","country_code":"IL","type":"education","lineage":["https://openalex.org/I4210141777"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sarel Cohen","raw_affiliation_strings":["The Academice College of Tel, Aviv-Yaffo, Tel Aviv-Yafo, Israel"],"affiliations":[{"raw_affiliation_string":"The Academice College of Tel, Aviv-Yaffo, Tel Aviv-Yafo, Israel","institution_ids":["https://openalex.org/I4210141777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060486269","display_name":"Vanja Dosko\u010d","orcid":"https://orcid.org/0000-0003-0190-7512"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vanja Dosko\u010d","raw_affiliation_strings":["Hasso-Plattner-Institut, University of Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001041047","display_name":"Raid Saabni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141777","display_name":"Academic College of Tel Aviv-Yafo","ror":"https://ror.org/04cg6c004","country_code":"IL","type":"education","lineage":["https://openalex.org/I4210141777"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Raid Saabni","raw_affiliation_strings":["The Academic College of Tel, Aviv-Yaffo, Triangle R&amp;D Center, Tel-Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"The Academic College of Tel, Aviv-Yaffo, Triangle R&amp;D Center, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I4210141777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077389210","display_name":"Tobias Friedrich","orcid":"https://orcid.org/0000-0003-0076-6308"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Friedrich","raw_affiliation_strings":["Hasso-Plattner-Institut, University of Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut, University of Potsdam, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5086868619"],"corresponding_institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33631477,"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9916999936103821,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9873999953269958,"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":0.982200026512146,"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":0.6420716047286987},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6240268349647522},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49957799911499023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48723068833351135},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.447282999753952},{"id":"https://openalex.org/keywords/image-resolution","display_name":"Image resolution","score":0.41128984093666077},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18833956122398376},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18449372053146362},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12244701385498047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6420716047286987},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6240268349647522},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49957799911499023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48723068833351135},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.447282999753952},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.41128984093666077},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18833956122398376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18449372053146362},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12244701385498047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704268.3742690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742690","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704268.3742690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704268.3742690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704268.3742690","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413826416.pdf","grobid_xml":"https://content.openalex.org/works/W4413826416.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1930824406","https://openalex.org/W2047920195","https://openalex.org/W2194187530","https://openalex.org/W2810983211","https://openalex.org/W2963526661","https://openalex.org/W3103667010","https://openalex.org/W3107840264","https://openalex.org/W3138516171","https://openalex.org/W3177505580","https://openalex.org/W4312349930","https://openalex.org/W4312923907"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Text":[0],"recognition":[1,30,35,71,121],"in":[2,36,86,106,122],"real-life":[3,37,123],"images":[4,96],"poses":[5],"a":[6,83,116],"challenging":[7],"task":[8],"due":[9],"to":[10,32],"blur,":[11],"distortion,":[12],"and":[13,27,48,80,114],"low":[14],"resolution.":[15],"This":[16,101],"work":[17],"presents":[18],"an":[19,53],"innovative":[20],"method":[21],"integrating":[22],"image":[23,25,58,112],"super-resolution,":[24],"restoration,":[26],"optical":[28],"character":[29],"techniques":[31],"enhance":[33],"text":[34,70,111,120],"photographs.":[38],"We":[39],"specifically":[40],"reviewed":[41],"the":[42,45,57,76,87,98,107],"processing":[43],"of":[44,56,64,109],"TextZoom":[46,99],"dataset":[47],"utilized":[49],"transfer":[50],"learning":[51],"on":[52],"improved":[54],"version":[55],"super-resolution":[59,113],"model,":[60],"SwinIR.":[61],"The":[62,125],"findings":[63],"our":[65,69],"experiment":[66],"show":[67],"that":[68],"scores":[72],"are":[73],"better":[74],"than":[75],"current":[77],"best":[78],"scores,":[79],"there":[81],"is":[82],"significant":[84],"rise":[85],"peak":[88],"signal-to-noise":[89],"ratio":[90],"while":[91],"dealing":[92],"with":[93],"deformed":[94],"low-resolution":[95],"from":[97],"dataset.":[100],"approach":[102],"outperforms":[103],"earlier":[104],"research":[105],"domain":[108],"scene":[110],"offers":[115],"promising":[117],"resolution":[118],"for":[119],"images.":[124],"code":[126],"can":[127],"be":[128],"accessed":[129],"at":[130],"this":[131],"location:":[132],"https://github.com/Phimanu/TextSR":[133]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
