{"id":"https://openalex.org/W4414192474","doi":"https://doi.org/10.1007/978-3-032-04630-7_20","title":"WildKhmerST: A Comprehensive Dataset and\u00a0Benchmark for\u00a0Khmer Scene Text Detection and\u00a0Recognition in\u00a0the\u00a0Wild","display_name":"WildKhmerST: A Comprehensive Dataset and\u00a0Benchmark for\u00a0Khmer Scene Text Detection and\u00a0Recognition in\u00a0the\u00a0Wild","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4414192474","doi":"https://doi.org/10.1007/978-3-032-04630-7_20"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-04630-7_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-04630-7_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-032-04630-7_20","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114618033","display_name":"Vannkinh Nom","orcid":null},"institutions":[{"id":"https://openalex.org/I186365177","display_name":"Institute of Technology of Cambodia","ror":"https://ror.org/054z67s11","country_code":"KH","type":"education","lineage":["https://openalex.org/I186365177"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR","KH"],"is_corresponding":false,"raw_author_name":"Vannkinh Nom","raw_affiliation_strings":["Cambodia Academy of Digital Technology (CADT), Phnom Penh, Cambodia","La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France"],"raw_orcid":"https://orcid.org/0009-0004-4684-0416","affiliations":[{"raw_affiliation_string":"Cambodia Academy of Digital Technology (CADT), Phnom Penh, Cambodia","institution_ids":["https://openalex.org/I186365177"]},{"raw_affiliation_string":"La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048921757","display_name":"Saly Keo","orcid":null},"institutions":[{"id":"https://openalex.org/I186365177","display_name":"Institute of Technology of Cambodia","ror":"https://ror.org/054z67s11","country_code":"KH","type":"education","lineage":["https://openalex.org/I186365177"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR","KH"],"is_corresponding":true,"raw_author_name":"Saly Keo","raw_affiliation_strings":["Cambodia Academy of Digital Technology (CADT), Phnom Penh, Cambodia","La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France"],"raw_orcid":"https://orcid.org/0009-0000-9878-4015","affiliations":[{"raw_affiliation_string":"Cambodia Academy of Digital Technology (CADT), Phnom Penh, Cambodia","institution_ids":["https://openalex.org/I186365177"]},{"raw_affiliation_string":"La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086210853","display_name":"Souhail Bakkali","orcid":"https://orcid.org/0000-0001-9383-3842"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Souhail Bakkali","raw_affiliation_strings":["La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France"],"raw_orcid":"https://orcid.org/0000-0001-9383-3842","affiliations":[{"raw_affiliation_string":"La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015093671","display_name":"Muhammad Muzzamil Luqman","orcid":"https://orcid.org/0000-0002-9658-0833"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Muhammad Muzzamil Luqman","raw_affiliation_strings":["La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France"],"raw_orcid":"https://orcid.org/0000-0002-9658-0833","affiliations":[{"raw_affiliation_string":"La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063992777","display_name":"Micka\u00ebl Coustaty","orcid":"https://orcid.org/0000-0002-0123-439X"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Micka\u00ebl Coustaty","raw_affiliation_strings":["La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France"],"raw_orcid":"https://orcid.org/0000-0002-0123-439X","affiliations":[{"raw_affiliation_string":"La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mar\u00e7al Rossinyol","orcid":"https://orcid.org/0000-0002-1734-2205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mar\u00e7al Rossinyol","raw_affiliation_strings":["AllRead Machine Learning Technologies, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1734-2205","affiliations":[{"raw_affiliation_string":"AllRead Machine Learning Technologies, Barcelona, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051777602","display_name":"Jean-Marc Ogier","orcid":"https://orcid.org/0000-0002-5666-475X"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Marc Ogier","raw_affiliation_strings":["La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France"],"raw_orcid":"https://orcid.org/0000-0002-5666-475X","affiliations":[{"raw_affiliation_string":"La Rochelle University, Laboratoire Informatique Image Interaction (L3i), La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048921757"],"corresponding_institution_ids":["https://openalex.org/I186365177","https://openalex.org/I78744979"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"351","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9932000041007996,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9821000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7174999713897705},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6510000228881836},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6428999900817871},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5347999930381775},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5184000134468079},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45750001072883606},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.44020000100135803},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490999937057495},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7174999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833000183105469},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6509000062942505},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6428999900817871},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5347999930381775},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.44020000100135803},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31929999589920044},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-04630-7_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-04630-7_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-04630-7_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-04630-7_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2008806374","https://openalex.org/W2019273017","https://openalex.org/W2061802763","https://openalex.org/W2082223180","https://openalex.org/W2088677042","https://openalex.org/W2099247484","https://openalex.org/W2140511609","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2194187530","https://openalex.org/W2519818067","https://openalex.org/W2598199894","https://openalex.org/W2605982830","https://openalex.org/W2763468124","https://openalex.org/W2786162033","https://openalex.org/W2787523828","https://openalex.org/W2806565062","https://openalex.org/W2895392434","https://openalex.org/W2945136398","https://openalex.org/W2963037989","https://openalex.org/W2963444790","https://openalex.org/W2963517393","https://openalex.org/W2979800489","https://openalex.org/W2981630388","https://openalex.org/W3004846386","https://openalex.org/W3005400651","https://openalex.org/W3011353592","https://openalex.org/W3024193103","https://openalex.org/W3101577715","https://openalex.org/W3107623930","https://openalex.org/W3197118814","https://openalex.org/W3198680251","https://openalex.org/W3204479434","https://openalex.org/W4213116910","https://openalex.org/W4281679764","https://openalex.org/W4312879041","https://openalex.org/W4382202677","https://openalex.org/W4388642413","https://openalex.org/W4393154079","https://openalex.org/W4405138790"],"related_works":[],"abstract_inverted_index":{"This":[0,119],"study":[1],"presents":[2],"a":[3,102,167,189],"large-scale":[4],"dataset":[5,105,120],"of":[6,19,57,79,106,200,210],"Khmer":[7,46,72,107,174,181,195,212],"scene":[8,108],"text":[9,113,135,143,163,182],"images":[10],"captured":[11],"in":[12,38,71,136,173],"real-world":[13],"environments.":[14],"Khmer,":[15],"the":[16,77,207,211],"official":[17],"language":[18],"Cambodia,":[20],"is":[21,121,145],"spoken":[22],"by":[23],"approximately":[24],"17":[25],"million":[26],"people.":[27],"While":[28],"Optical":[29],"Character":[30],"Recognition":[31],"(OCR)":[32],"systems":[33],"have":[34],"achieved":[35],"remarkable":[36],"success":[37],"Roman":[39],"(Latin)":[40],"script":[41,47],"languages":[42],"such":[43],"as":[44],"English,":[45],"poses":[48],"unique":[49,117,208],"challenges":[50],"due":[51],"to":[52,92],"its":[53],"intricate":[54],"structure,":[55],"absence":[56],"clear":[58],"word":[59],"boundaries,":[60],"and":[61,66,124,139,152,162,184,202],"highly":[62,122],"diverse":[63,123],"character":[64,160],"shapes":[65],"sizes.":[67],"A":[68],"significant":[69],"limitation":[70],"OCR":[73],"research":[74,172],"has":[75],"been":[76],"scarcity":[78],"high-quality":[80],"training":[81],"data,":[82],"particularly":[83],"for":[84,170,180,194,206],"deep":[85],"learning-based":[86],"models,":[87],"which":[88],"require":[89],"extensive":[90],"datasets":[91],"achieve":[93],"robust":[94,190],"performance.":[95],"To":[96,165],"address":[97],"these":[98],"challenges,":[99],"we":[100,176,187],"introduce":[101],"newly":[103],"constructed":[104],"text,":[109,128,130,134],"comprising":[110],"29,601":[111],"annotated":[112,146],"lines":[114],"from":[115],"10,000":[116],"images.":[118],"challenging,":[125],"encompassing":[126],"artistic":[127],"blurred":[129],"low-light":[131],"conditions,":[132],"curved":[133],"complex":[137],"backgrounds,":[138],"occluded":[140],"text.":[141],"Each":[142],"line":[144],"with":[147],"polygonal":[148],"bounding":[149],"box":[150],"coordinates":[151],"line-level":[153],"transcriptions,":[154],"alongside":[155],"attributes":[156],"describing":[157],"background":[158],"complexity,":[159],"appearance,":[161],"style.":[164],"establish":[166],"foundational":[168],"benchmark":[169],"future":[171],"OCR,":[175,196],"provide":[177],"baseline":[178],"results":[179],"detection":[183],"recognition.":[185],"Additionally,":[186],"propose":[188],"evaluation":[191],"metric":[192],"tailored":[193],"enabling":[197],"precise":[198],"assessment":[199],"CER":[201],"WER":[203],"while":[204],"accounting":[205],"characteristics":[209],"script.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}