Please use this identifier to cite or link to this item: https://scholarhub.balamand.edu.lb/handle/uob/2057
DC FieldValueLanguage
dc.contributor.authorOprean, Cristinaen_US
dc.contributor.authorLikforman-Sulem, Laurenceen_US
dc.contributor.authorPopescu, Adrianen_US
dc.contributor.authorMokbel, Chaficen_US
dc.date.accessioned2020-12-23T09:05:35Z-
dc.date.available2020-12-23T09:05:35Z-
dc.date.issued2015-
dc.identifier.urihttps://scholarhub.balamand.edu.lb/handle/uob/2057-
dc.description.abstractHandwriting recognition systems usually rely on static dictionaries and language models. Full coverage of these dictionaries is generally not achieved when dealing with unrestricted document corpora due to the presence of Out-Of-Vocabulary (OOV) words. We propose an approach which uses the World Wide Web as a corpus to improve dictionary coverage. We exploit the very large and freely available Wikipedia corpus in order to obtain dynamic dictionaries on the fly. We rely on recurrent neural network (RNN) recognizers, with and without linguistic resources, to detect words that are non-reliably recognized within a word sequence. Such words are labeled as non-anchor words (NAWs) and include OOVs and In-Vocabulary words recognized with low confidence. To recognize a non-anchor word, a dynamic dictionary is built by selecting words from the Web resource based on their string similarity with the NAW image, and their linguistic relevance in the NAW context. Similarity is evaluated by computing the edit distance between the sequence of characters generated by the RNN recognizer exploited as a filler model, and the Wikipedia words. Linguistic relevance is based on an N-gram language model estimated from the Wikipedia corpus. Experiments conducted on a word-segmented version of the publicly available RIMES database show that the proposed approach can improve recognition accuracy compared to systems based on static dictionaries only. The proposed approach shows even better behavior as the proportion of OOVs increases, in terms of both accuracy and dictionary coverage.en_US
dc.format.extent14 p.en_US
dc.language.isoengen_US
dc.subjectHandwritten word recognitionen_US
dc.subjectOut-of-vocabulary word recognitionen_US
dc.subjectWeb resourcesen_US
dc.subjectDynamic dictionaryen_US
dc.subjectRecurrent neural networksen_US
dc.titleHandwritten word recognition using web resources and recurrent neural networksen_US
dc.typeJournal Articleen_US
dc.contributor.affiliationDepartment of Electrical Engineeringen_US
dc.description.volume18en_US
dc.description.issue4en_US
dc.description.startpage287en_US
dc.description.endpage301en_US
dc.date.catalogued2019-05-28-
dc.description.statusPublisheden_US
dc.identifier.ezproxyURLhttp://ezsecureaccess.balamand.edu.lb/login?url=https://link.springer.com/article/10.1007/s10032-015-0251-1en_US
dc.identifier.OlibID192137-
dc.relation.ispartoftextInternational journal on document analysis and recognition (IJDAR)en_US
dc.provenance.recordsourceOliben_US
Appears in Collections:Department of Electrical Engineering
Show simple item record

Record view(s)

5
checked on Jan 17, 2022

Google ScholarTM

Check


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