Matches in SemOpenAlex for { <https://semopenalex.org/work/W1996567568> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W1996567568 endingPage "3103" @default.
- W1996567568 startingPage "3092" @default.
- W1996567568 abstract "In this paper, we investigate the application of dynamic Bayesian networks (DBNs) to the recognition of degraded characters. DBNs are an extension of one-dimensional hidden Markov models (HMMs) which can handle several observation and state sequences. In our study, characters are represented by the coupling of two HMM architectures into a single DBN model. The interacting HMMs are a vertical HMM and a horizontal HMM whose observable outputs are the image columns and image rows, respectively. Various couplings are proposed where interactions are achieved through the causal influence between state variables. We compare non-coupled and coupled models on two tasks: the recognition of artificially degraded handwritten digits and the recognition of real degraded old printed characters. Our models show that coupled architectures perform more accurately on degraded characters than basic HMMs, the linear combination of independent HMM scores, as well as discriminative methods such as support vector machines (SVMs)." @default.
- W1996567568 created "2016-06-24" @default.
- W1996567568 creator A5060819073 @default.
- W1996567568 creator A5063346157 @default.
- W1996567568 date "2008-10-01" @default.
- W1996567568 modified "2023-09-30" @default.
- W1996567568 title "Recognition of degraded characters using dynamic Bayesian networks" @default.
- W1996567568 cites W1525219465 @default.
- W1996567568 cites W1566193143 @default.
- W1996567568 cites W1592735339 @default.
- W1996567568 cites W1815331012 @default.
- W1996567568 cites W1985079464 @default.
- W1996567568 cites W1990002148 @default.
- W1996567568 cites W1990036093 @default.
- W1996567568 cites W2021982596 @default.
- W1996567568 cites W2024986448 @default.
- W1996567568 cites W2046683788 @default.
- W1996567568 cites W2052441401 @default.
- W1996567568 cites W2055853283 @default.
- W1996567568 cites W2056148478 @default.
- W1996567568 cites W2058597114 @default.
- W1996567568 cites W2083814382 @default.
- W1996567568 cites W2088937907 @default.
- W1996567568 cites W2091088554 @default.
- W1996567568 cites W2106898383 @default.
- W1996567568 cites W2111301113 @default.
- W1996567568 cites W2123011716 @default.
- W1996567568 cites W2125838338 @default.
- W1996567568 cites W2130416704 @default.
- W1996567568 cites W2131612517 @default.
- W1996567568 cites W2136016133 @default.
- W1996567568 cites W2141915486 @default.
- W1996567568 cites W2142069714 @default.
- W1996567568 cites W2142114945 @default.
- W1996567568 cites W2144731007 @default.
- W1996567568 cites W2149597185 @default.
- W1996567568 cites W2152239535 @default.
- W1996567568 cites W2153635508 @default.
- W1996567568 cites W2158275940 @default.
- W1996567568 cites W2159080219 @default.
- W1996567568 cites W2162770305 @default.
- W1996567568 cites W2168868236 @default.
- W1996567568 cites W2242301282 @default.
- W1996567568 cites W413250226 @default.
- W1996567568 doi "https://doi.org/10.1016/j.patcog.2008.03.022" @default.
- W1996567568 hasPublicationYear "2008" @default.
- W1996567568 type Work @default.
- W1996567568 sameAs 1996567568 @default.
- W1996567568 citedByCount "36" @default.
- W1996567568 countsByYear W19965675682012 @default.
- W1996567568 countsByYear W19965675682014 @default.
- W1996567568 countsByYear W19965675682015 @default.
- W1996567568 countsByYear W19965675682016 @default.
- W1996567568 countsByYear W19965675682017 @default.
- W1996567568 countsByYear W19965675682018 @default.
- W1996567568 countsByYear W19965675682019 @default.
- W1996567568 crossrefType "journal-article" @default.
- W1996567568 hasAuthorship W1996567568A5060819073 @default.
- W1996567568 hasAuthorship W1996567568A5063346157 @default.
- W1996567568 hasConcept C107673813 @default.
- W1996567568 hasConcept C153180895 @default.
- W1996567568 hasConcept C154945302 @default.
- W1996567568 hasConcept C23224414 @default.
- W1996567568 hasConcept C28490314 @default.
- W1996567568 hasConcept C41008148 @default.
- W1996567568 hasConcept C82142266 @default.
- W1996567568 hasConcept C97931131 @default.
- W1996567568 hasConceptScore W1996567568C107673813 @default.
- W1996567568 hasConceptScore W1996567568C153180895 @default.
- W1996567568 hasConceptScore W1996567568C154945302 @default.
- W1996567568 hasConceptScore W1996567568C23224414 @default.
- W1996567568 hasConceptScore W1996567568C28490314 @default.
- W1996567568 hasConceptScore W1996567568C41008148 @default.
- W1996567568 hasConceptScore W1996567568C82142266 @default.
- W1996567568 hasConceptScore W1996567568C97931131 @default.
- W1996567568 hasIssue "10" @default.
- W1996567568 hasLocation W19965675681 @default.
- W1996567568 hasOpenAccess W1996567568 @default.
- W1996567568 hasPrimaryLocation W19965675681 @default.
- W1996567568 hasRelatedWork W1565453839 @default.
- W1996567568 hasRelatedWork W1652783584 @default.
- W1996567568 hasRelatedWork W198264392 @default.
- W1996567568 hasRelatedWork W2017210410 @default.
- W1996567568 hasRelatedWork W2024160000 @default.
- W1996567568 hasRelatedWork W2134999511 @default.
- W1996567568 hasRelatedWork W2167155152 @default.
- W1996567568 hasRelatedWork W2355170890 @default.
- W1996567568 hasRelatedWork W2404514746 @default.
- W1996567568 hasRelatedWork W2773500201 @default.
- W1996567568 hasVolume "41" @default.
- W1996567568 isParatext "false" @default.
- W1996567568 isRetracted "false" @default.
- W1996567568 magId "1996567568" @default.
- W1996567568 workType "article" @default.