{"id":"https://openalex.org/W7127586562","doi":"https://doi.org/10.1109/dese68208.2025.11367891","title":"Investigating Large Multimodal Models' Potential in Arabic Handwriting Recognition","display_name":"Investigating Large Multimodal Models' Potential in Arabic Handwriting Recognition","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7127586562","doi":"https://doi.org/10.1109/dese68208.2025.11367891"},"language":null,"primary_location":{"id":"doi:10.1109/dese68208.2025.11367891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dese68208.2025.11367891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 18th International Conference on Development in eSystem Engineering (DeSE)","raw_type":"proceedings-article"},"type":"article","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/A5012552403","display_name":"Najla Alsaedi","orcid":null},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Najla Alsaedi","raw_affiliation_strings":["Taibah University,dept. of Computer Science,Madinah,Saudi Arabia"],"raw_orcid":"https://orcid.org/0009-0001-1362-9233","affiliations":[{"raw_affiliation_string":"Taibah University,dept. of Computer Science,Madinah,Saudi Arabia","institution_ids":["https://openalex.org/I23075662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124653631","display_name":"Bushra Aljohani","orcid":null},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Bushra Aljohani","raw_affiliation_strings":["Taibah University,dept. of Computer Science,Madinah,Saudi Arabia"],"raw_orcid":"https://orcid.org/0009-0006-5748-2372","affiliations":[{"raw_affiliation_string":"Taibah University,dept. of Computer Science,Madinah,Saudi Arabia","institution_ids":["https://openalex.org/I23075662"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Raghad Alharbi","orcid":"https://orcid.org/0009-0008-2461-8960"},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Raghad Alharbi","raw_affiliation_strings":["Taibah University,dept. of Computer Science,Madinah,Saudi Arabia"],"raw_orcid":"https://orcid.org/0009-0008-2461-8960","affiliations":[{"raw_affiliation_string":"Taibah University,dept. of Computer Science,Madinah,Saudi Arabia","institution_ids":["https://openalex.org/I23075662"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125069813","display_name":"Liyakathunisa Ansari","orcid":null},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Liyakathunisa Ansari","raw_affiliation_strings":["Taibah University,dept. of Computer Science,Madinah,Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taibah University,dept. of Computer Science,Madinah,Saudi Arabia","institution_ids":["https://openalex.org/I23075662"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23075662"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62729558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"232","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9901000261306763,"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":0.9901000261306763,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0010000000474974513,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/word-error-rate","display_name":"Word error rate","score":0.751800000667572},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6449999809265137},{"id":"https://openalex.org/keywords/cursive","display_name":"Cursive","score":0.6290000081062317},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6133000254631042},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5795999765396118},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.5013999938964844},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4156000018119812},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41280001401901245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646999955177307},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.751800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474000215530396},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6449999809265137},{"id":"https://openalex.org/C2778943297","wikidata":"https://www.wikidata.org/wiki/Q1079418","display_name":"Cursive","level":2,"score":0.6290000081062317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6252999901771545},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6133000254631042},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5444999933242798},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.5013999938964844},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.40700000524520874},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.4043999910354614},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2777323237","wikidata":"https://www.wikidata.org/wiki/Q1828555","display_name":"Arabic script","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dese68208.2025.11367891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dese68208.2025.11367891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 18th International Conference on Development in eSystem Engineering (DeSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7823819518089294,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W3004048800","https://openalex.org/W3037641445","https://openalex.org/W3171002083","https://openalex.org/W3172417134","https://openalex.org/W3185830590","https://openalex.org/W4200356778","https://openalex.org/W4207029058","https://openalex.org/W4285166436","https://openalex.org/W4288075678","https://openalex.org/W4308475352","https://openalex.org/W4362612070","https://openalex.org/W4382402998","https://openalex.org/W4385245566","https://openalex.org/W4390670543","https://openalex.org/W4402671279","https://openalex.org/W4402672157","https://openalex.org/W4405750315","https://openalex.org/W4412887686"],"related_works":[],"abstract_inverted_index":{"Arabic":[0,32,60,154,179],"Optical":[1],"Character":[2,96],"Recognition":[3,7],"(OCR)":[4],"and":[5,27,38,53,62,70,81,100,120,157,162,187],"Handwriting":[6],"(HWR)":[8],"have":[9],"been":[10],"a":[11,46],"hot":[12],"topic":[13],"in":[14,36,48,65,168],"recent":[15],"years.":[16],"However,":[17],"this":[18,143],"domain":[19],"presents":[20],"significant":[21],"challenges":[22],"due":[23],"to":[24,146,153,158],"the":[25,31,50,85,116,135,148,170],"cursive":[26],"context-dependent":[28],"characteristics":[29],"of":[30,55,67,142,150,174],"script.":[33],"Despite":[34],"advancements":[35],"traditional":[37],"deep":[39],"learning":[40],"based":[41],"OCR":[42,61,133,176],"approaches,":[43],"there":[44],"remains":[45],"gap":[47],"evaluating":[49],"accuracy,":[51],"strengths,":[52],"limitations":[54],"large":[56],"multimodal":[57],"models":[58],"for":[59,178,183],"HWR,":[63],"particularly":[64],"terms":[66],"error":[68,108,137],"analysis":[69],"performance":[71],"benchmarking.":[72],"This":[73],"study":[74],"evaluates":[75],"four":[76],"models-Mistral":[77],"OCR,":[78],"GPT-4o,":[79],"TrOCR,":[80],"PaddleOCR":[82,125],"3.0":[83,126],"(PP-OCRv5)-using":[84],"OnlineKHATT":[86],"dataset.":[87],"Performance":[88],"was":[89],"assessed":[90],"using":[91],"standard":[92],"objective":[93],"metrics,":[94],"namely":[95],"Error":[97,102],"Rate":[98,103],"(CER)":[99],"Word":[101],"(WER),":[104],"supported":[105],"by":[106,124],"an":[107],"analysis.":[109],"Experimental":[110],"results":[111],"show":[112],"that":[113],"GPT-4o":[114],"achieved":[115],"lowest":[117],"CER":[118],"(0.39)":[119],"WER":[121],"(0.70),":[122],"followed":[123],"(0.4720":[127],"CER,":[128],"0.8450":[129],"WER),":[130],"while":[131],"Mistral":[132],"recorded":[134],"highest":[136],"rates.":[138],"The":[139,164],"primary":[140],"goal":[141],"work":[144],"is":[145],"examine":[147],"feasibility":[149],"applying":[151],"LMMs":[152],"handwriting":[155],"recognition":[156],"highlight":[159],"their":[160],"strengths":[161],"limitations.":[163],"main":[165],"contribution":[166],"lies":[167],"presenting":[169],"first":[171],"comparative":[172],"benchmark":[173],"LMM-based":[175],"systems":[177],"handwriting,":[180],"providing":[181],"insights":[182],"future":[184],"model":[185],"fine-tuning":[186],"dataset":[188],"adaptation.":[189]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-06T00:00:00"}