Please use this identifier to cite or link to this item: https://scholarhub.balamand.edu.lb/handle/uob/1346
DC FieldValueLanguage
dc.contributor.authorMorillot , Olivieren_US
dc.contributor.authorOprean, Cristinaen_US
dc.contributor.authorLikforman-Sulem, Laurenceen_US
dc.contributor.authorMokbel, Chaficen_US
dc.contributor.authorChammas, Edgaren_US
dc.contributor.authorGrosick, Emmanuèleen_US
dc.date.accessioned2020-12-23T08:48:36Z-
dc.date.available2020-12-23T08:48:36Z-
dc.date.issued2013-
dc.identifier.urihttps://scholarhub.balamand.edu.lb/handle/uob/1346-
dc.description.abstractThis article is a description of the two systems proposed for the recognition of Arabic handwritten text lines and for the automatic translation of text-line and sentence images into English text. The recognition systems are based on HMMs (Hidden Markov Models) and BLSTMs (bi-directional long short term memory) recurrent networks. Two SMT (Statistical Machine Translation) systems based on MOSES [1] were built for the evaluation system: one on text-line translation and one for sentence translation.en_US
dc.language.isoengen_US
dc.subjectArabic handwriting recognitionen_US
dc.subjectTextline recognitionen_US
dc.subjectPreprocessingen_US
dc.subjectHMMen_US
dc.subjectBLSTMen_US
dc.subject.lcshTranslationen_US
dc.titleThe UOB-Telecom paristech arabic handwriting recognition and translation systems for the openHart 2013 competitionen_US
dc.typeConference Presentationen_US
dc.relation.conferenceInternational Conference on Document Analysis and Recognition (ICDAR) (12th : 25-28 Aug 2013 : Washington DC, United States)en_US
dc.contributor.affiliationDepartment of Electrical Engineeringen_US
dc.date.catalogued2019-05-24-
dc.description.statusPublisheden_US
dc.identifier.OlibID192055-
dc.identifier.openURLhttps://www.nist.gov/sites/default/files/documents/itl/iad/mig/OpenHaRT2013_WorkshopPres_UOB-TPT.pdfen_US
dc.provenance.recordsourceOliben_US
Appears in Collections:Department of Electrical Engineering
Show simple item record

Record view(s)

8
checked on Jan 17, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.