Matches in SemOpenAlex for { <https://semopenalex.org/work/W2051654810> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2051654810 endingPage "156" @default.
- W2051654810 startingPage "149" @default.
- W2051654810 abstract "Hidden Markov Models (HMMs) are now widely used for off-line handwriting recognition in many languages. As in speech recognition, they are usually built from shared, embedded HMMs at symbol level, where state-conditional probability density functions in each HMM are modeled with Gaussian mixtures. In contrast to speech recognition, however, it is unclear which kind of features should be used and, indeed, very different features sets are in use today. Among them, we have recently proposed to directly use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea is to by-pass feature extraction and to ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. In this work, column bit vectors are extended by means of a sliding window of adequate width to better capture image context at each horizontal position of the word image. Using these windowed Bernoulli mixture HMMs, good results are reported on the well-known IAM and RIMES databases of Latin script, and in particular, state-of-the-art results are provided on the IfN/ENIT database of Arabic handwritten words." @default.
- W2051654810 created "2016-06-24" @default.
- W2051654810 creator A5002610864 @default.
- W2051654810 creator A5019869698 @default.
- W2051654810 creator A5027811439 @default.
- W2051654810 creator A5040605861 @default.
- W2051654810 date "2014-01-01" @default.
- W2051654810 modified "2023-09-24" @default.
- W2051654810 title "Handwriting word recognition using windowed Bernoulli HMMs" @default.
- W2051654810 cites W2007257917 @default.
- W2051654810 cites W2020407556 @default.
- W2051654810 cites W2053033904 @default.
- W2051654810 cites W2105518985 @default.
- W2051654810 cites W2106986062 @default.
- W2051654810 cites W2133316488 @default.
- W2051654810 cites W2135743131 @default.
- W2051654810 cites W2152928267 @default.
- W2051654810 cites W2154094385 @default.
- W2051654810 cites W2154895996 @default.
- W2051654810 cites W2164867695 @default.
- W2051654810 cites W2168504305 @default.
- W2051654810 cites W2917150894 @default.
- W2051654810 cites W4246411900 @default.
- W2051654810 doi "https://doi.org/10.1016/j.patrec.2012.09.002" @default.
- W2051654810 hasPublicationYear "2014" @default.
- W2051654810 type Work @default.
- W2051654810 sameAs 2051654810 @default.
- W2051654810 citedByCount "34" @default.
- W2051654810 countsByYear W20516548102013 @default.
- W2051654810 countsByYear W20516548102014 @default.
- W2051654810 countsByYear W20516548102015 @default.
- W2051654810 countsByYear W20516548102016 @default.
- W2051654810 countsByYear W20516548102017 @default.
- W2051654810 countsByYear W20516548102018 @default.
- W2051654810 countsByYear W20516548102019 @default.
- W2051654810 countsByYear W20516548102020 @default.
- W2051654810 countsByYear W20516548102021 @default.
- W2051654810 countsByYear W20516548102022 @default.
- W2051654810 crossrefType "journal-article" @default.
- W2051654810 hasAuthorship W2051654810A5002610864 @default.
- W2051654810 hasAuthorship W2051654810A5019869698 @default.
- W2051654810 hasAuthorship W2051654810A5027811439 @default.
- W2051654810 hasAuthorship W2051654810A5040605861 @default.
- W2051654810 hasBestOaLocation W20516548102 @default.
- W2051654810 hasConcept C127413603 @default.
- W2051654810 hasConcept C138885662 @default.
- W2051654810 hasConcept C146978453 @default.
- W2051654810 hasConcept C150856459 @default.
- W2051654810 hasConcept C152361515 @default.
- W2051654810 hasConcept C153180895 @default.
- W2051654810 hasConcept C154945302 @default.
- W2051654810 hasConcept C204321447 @default.
- W2051654810 hasConcept C2779386606 @default.
- W2051654810 hasConcept C28490314 @default.
- W2051654810 hasConcept C41008148 @default.
- W2051654810 hasConcept C41895202 @default.
- W2051654810 hasConcept C554936623 @default.
- W2051654810 hasConcept C90805587 @default.
- W2051654810 hasConceptScore W2051654810C127413603 @default.
- W2051654810 hasConceptScore W2051654810C138885662 @default.
- W2051654810 hasConceptScore W2051654810C146978453 @default.
- W2051654810 hasConceptScore W2051654810C150856459 @default.
- W2051654810 hasConceptScore W2051654810C152361515 @default.
- W2051654810 hasConceptScore W2051654810C153180895 @default.
- W2051654810 hasConceptScore W2051654810C154945302 @default.
- W2051654810 hasConceptScore W2051654810C204321447 @default.
- W2051654810 hasConceptScore W2051654810C2779386606 @default.
- W2051654810 hasConceptScore W2051654810C28490314 @default.
- W2051654810 hasConceptScore W2051654810C41008148 @default.
- W2051654810 hasConceptScore W2051654810C41895202 @default.
- W2051654810 hasConceptScore W2051654810C554936623 @default.
- W2051654810 hasConceptScore W2051654810C90805587 @default.
- W2051654810 hasLocation W20516548101 @default.
- W2051654810 hasLocation W20516548102 @default.
- W2051654810 hasOpenAccess W2051654810 @default.
- W2051654810 hasPrimaryLocation W20516548101 @default.
- W2051654810 hasRelatedWork W1489815656 @default.
- W2051654810 hasRelatedWork W1555006578 @default.
- W2051654810 hasRelatedWork W1588276545 @default.
- W2051654810 hasRelatedWork W1711257623 @default.
- W2051654810 hasRelatedWork W2051654810 @default.
- W2051654810 hasRelatedWork W207717038 @default.
- W2051654810 hasRelatedWork W2158785961 @default.
- W2051654810 hasRelatedWork W2358212252 @default.
- W2051654810 hasRelatedWork W3107474891 @default.
- W2051654810 hasRelatedWork W2121178211 @default.
- W2051654810 hasVolume "35" @default.
- W2051654810 isParatext "false" @default.
- W2051654810 isRetracted "false" @default.
- W2051654810 magId "2051654810" @default.
- W2051654810 workType "article" @default.