{"id":"https://openalex.org/W4391383905","doi":"https://doi.org/10.1145/3627631.3627639","title":"TransDocUNet: A Transformer-based UNet Architecture for Degraded Document Image Binarization","display_name":"TransDocUNet: A Transformer-based UNet Architecture for Degraded Document Image Binarization","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391383905","doi":"https://doi.org/10.1145/3627631.3627639"},"language":"en","primary_location":{"id":"doi:10.1145/3627631.3627639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","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/A5065529448","display_name":"Risab Biswas","orcid":"https://orcid.org/0000-0001-9906-0609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Risab Biswas","raw_affiliation_strings":["Artificial Intelligence Group, Optiks Innovations Pvt. Ltd. (P360), India"],"raw_orcid":"https://orcid.org/0000-0001-9906-0609","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Group, Optiks Innovations Pvt. Ltd. (P360), India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093828436","display_name":"Soumik Sarkhel","orcid":"https://orcid.org/0009-0008-7198-3004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soumik Sarkhel","raw_affiliation_strings":["Artificial Intelligence Group, Optiks Innovations Pvt. Ltd. (P360), India"],"raw_orcid":"https://orcid.org/0009-0008-7198-3004","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Group, Optiks Innovations Pvt. Ltd. (P360), India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087427076","display_name":"Swalpa Kumar Roy","orcid":"https://orcid.org/0000-0002-6580-3977"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swalpa Kumar Roy","raw_affiliation_strings":["Department of Computer Science and Engineering, Alipurduar Government Engineering and Management College, India"],"raw_orcid":"https://orcid.org/0000-0002-6580-3977","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Alipurduar Government Engineering and Management College, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068803496","display_name":"Umapada Pal","orcid":"https://orcid.org/0000-0002-5426-2618"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Umapada Pal","raw_affiliation_strings":["Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0002-5426-2618","affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9936000108718872,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9883000254631042,"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":0.7034123539924622},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6370788812637329},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6161825656890869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.499586820602417},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49744847416877747},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.4242528975009918},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3910999894142151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3506007194519043},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.34924596548080444},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.29712408781051636},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13987389206886292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1367466151714325},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.06356337666511536},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06277167797088623},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06270095705986023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034123539924622},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6370788812637329},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6161825656890869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499586820602417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49744847416877747},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.4242528975009918},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3506007194519043},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.34924596548080444},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29712408781051636},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13987389206886292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1367466151714325},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06356337666511536},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06277167797088623},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06270095705986023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627631.3627639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627631.3627639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing","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":39,"referenced_works":["https://openalex.org/W2003099669","https://openalex.org/W2016829658","https://openalex.org/W2022989269","https://openalex.org/W2038037829","https://openalex.org/W2081868602","https://openalex.org/W2133059825","https://openalex.org/W2156508493","https://openalex.org/W2170472910","https://openalex.org/W2317505761","https://openalex.org/W2577429903","https://openalex.org/W2751352153","https://openalex.org/W2785874433","https://openalex.org/W2884367402","https://openalex.org/W2911489097","https://openalex.org/W2915106267","https://openalex.org/W2915527102","https://openalex.org/W2957223244","https://openalex.org/W2964010994","https://openalex.org/W2971023110","https://openalex.org/W2988314300","https://openalex.org/W3048313648","https://openalex.org/W3081567905","https://openalex.org/W3081929364","https://openalex.org/W3083907077","https://openalex.org/W3132571997","https://openalex.org/W3135565841","https://openalex.org/W3159291204","https://openalex.org/W3165107603","https://openalex.org/W3204366741","https://openalex.org/W3207255384","https://openalex.org/W3216352822","https://openalex.org/W4206401103","https://openalex.org/W4243521730","https://openalex.org/W4246411305","https://openalex.org/W4247264488","https://openalex.org/W4311459452","https://openalex.org/W4319937615","https://openalex.org/W4376482646","https://openalex.org/W4380763457"],"related_works":["https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3200723557","https://openalex.org/W4312713546","https://openalex.org/W2362195430","https://openalex.org/W2347494122","https://openalex.org/W2567983276","https://openalex.org/W2802298219","https://openalex.org/W2393996461"],"abstract_inverted_index":{"The":[0,115,179],"enhancement":[1],"of":[2,14,75,136,163,195],"historical":[3],"document":[4,18,27,91,149,207],"images":[5],"is":[6],"critical":[7],"for":[8,26,90,203],"improving":[9],"the":[10,112,120,130,161,166,174,185,193],"quality":[11,139,143],"and":[12,98,105,141,188,199],"legibility":[13],"scanned":[15],"or":[16],"captured":[17],"images.":[19,208],"Convolutional-based":[20],"techniques":[21],"previously":[22],"generated":[23],"competitive":[24],"results":[25],"image":[28,92,150],"binarization,":[29],"however,":[30,63],"due":[31,71],"to":[32,59,72,111,159,168],"their":[33],"inherent":[34],"locality,":[35],"these":[36],"models":[37],"are":[38],"often":[39],"limited":[40],"in":[41,67,101,134,148,165],"explicitly":[42],"expressing":[43],"long-range":[44],"dependency.":[45],"Transformers":[46],"(ViT)":[47],"have":[48],"evolved":[49],"as":[50,107,177],"an":[51,156],"alternative":[52,110],"design":[53],"with":[54],"a":[55,73,85,102,108],"global":[56,198],"self-attention":[57],"mechanism":[58],"tackle":[60],"this":[61,80],"issue,":[62],"they":[64],"can":[65],"result":[66],"restricted":[68],"localization":[69],"capabilities":[70,100],"lack":[74],"low-level":[76],"details.":[77],"To":[78],"address":[79],"problem,":[81],"we":[82,154],"propose":[83],"TransDocUNet,":[84],"CNN-Transformer":[86],"hybrid":[87],"UNet":[88],"architecture":[89,104],"binarization":[93],"that":[94,124],"merits":[95],"both":[96,137,197],"attention":[97],"convolution":[99],"U-Net":[103],"serves":[106],"strong":[109],"existing":[113,131],"solutions.":[114],"experimental":[116],"results,":[117],"obtained":[118],"using":[119],"DIBCO/H-DIBCO":[121],"datasets,":[122],"highlight":[123],"our":[125],"proposed":[126],"method":[127],"outperforms":[128],"all":[129],"competing":[132],"methods":[133],"terms":[135],"objective":[138],"metrics":[140],"visual":[142],"assessment,":[144],"achieving":[145],"state-of-the-art":[146],"performance":[147],"binarization.":[151],"In":[152],"addition,":[153],"undertake":[155],"ablation":[157],"study":[158],"understand":[160],"role":[162],"dilation":[164],"CNN":[167],"capture":[169],"feature":[170],"dependencies":[171],"while":[172],"reducing":[173],"computational":[175],"cost":[176],"well.":[178],"findings":[180],"helped":[181],"us":[182],"arrive":[183],"at":[184],"final":[186],"model":[187],"provide":[189],"valuable":[190],"insights":[191],"into":[192],"importance":[194],"acquiring":[196],"local":[200],"contextual":[201],"information":[202],"tasks":[204],"like":[205],"enhancing":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}