{"id":"https://openalex.org/W2912920224","doi":"https://doi.org/10.1109/cisp-bmei.2018.8633103","title":"Challenges and Preprocessing Recommendations for MADCAT Dataset of Handwritten Arabic Documents","display_name":"Challenges and Preprocessing Recommendations for MADCAT Dataset of Handwritten Arabic Documents","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2912920224","doi":"https://doi.org/10.1109/cisp-bmei.2018.8633103","mag":"2912920224"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei.2018.8633103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei.2018.8633103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","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/A5036769756","display_name":"Gheith A. Abandah","orcid":"https://orcid.org/0000-0002-0672-809X"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":true,"raw_author_name":"Gheith A. Abandah","raw_affiliation_strings":["Computer Engineering Department, The University of Jordan, Amman, Jordan"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, The University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054591449","display_name":"Ahmad S. Ai-Hourani","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ahmad S. Ai-Hourani","raw_affiliation_strings":["Computer Engineering Department, The University of Jordan, Amman, Jordan"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, The University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036769756"],"corresponding_institution_ids":["https://openalex.org/I114972647"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17711948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/preprocessor","display_name":"Preprocessor","score":0.8826928734779358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.871473491191864},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6581802368164062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6561784148216248},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5849897861480713},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5242139101028442},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46932336688041687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41657504439353943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4157114624977112}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8826928734779358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871473491191864},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6581802368164062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6561784148216248},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5849897861480713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5242139101028442},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46932336688041687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41657504439353943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4157114624977112},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cisp-bmei.2018.8633103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei.2018.8633103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1606953891","https://openalex.org/W1982673299","https://openalex.org/W2012442176","https://openalex.org/W2013042514","https://openalex.org/W2024870788","https://openalex.org/W2030318047","https://openalex.org/W2037424248","https://openalex.org/W2042898371","https://openalex.org/W2079068771","https://openalex.org/W2093100897","https://openalex.org/W2103377156","https://openalex.org/W2131823159","https://openalex.org/W2145684309","https://openalex.org/W2152909144","https://openalex.org/W2170325377"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"In":[0],"this":[1,97],"paper,":[2],"we":[3,86],"analyze":[4],"the":[5,18,31,38,48,51,76,79,88],"dataset":[6,26,64,98],"often":[7],"used":[8],"in":[9,35],"training":[10,57],"and":[11,24,46,58,69,90],"testing":[12],"Arabic":[13,66,101],"handwritten":[14,67,100],"document":[15],"recognition":[16,43,103],"systems,":[17],"Multilingual":[19],"Automatic":[20],"Document":[21],"Classification":[22],"Analysis":[23],"Translation":[25],"(MADCAT).":[27],"We":[28],"report":[29],"here":[30],"main":[32],"challenges":[33,72],"present":[34],"MADCAT":[36,60],"that":[37,53],"preprocessing":[39,80,92],"stage":[40],"of":[41,50,65,78],"any":[42],"algorithm":[44],"faces":[45],"affect":[47],"performance":[49],"systems":[52,104],"use":[54],"it":[55],"for":[56,99],"testing.":[59],"is":[61],"a":[62],"representative":[63],"documents":[68],"investigating":[70],"its":[71],"helps":[73],"to":[74,95],"identify":[75],"requirements":[77],"stage.":[81],"After":[82],"presenting":[83],"these":[84],"challenges,":[85],"review":[87],"literature":[89],"recommend":[91],"algorithms":[93],"suitable":[94],"preprocess":[96],"word":[102],"such":[105],"as":[106],"JU-OCR2.":[107]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
