FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2071799300> ?p ?o ?g. }

• W2071799300 abstract "Optimal translation-invariant binary windowed filters are determined by probabilities of the form P(Y = 1|x), where x is a vector (template) of observed values in the observation window and Y is the value in the image to be estimated by the filter. The optimal window filter is defined by y(x) = 1 if P(Y = 1|x) > 0.5 and y(x) = 0 if P(Y = 1|x) ≤ 0.5, which is the binary conditional expectation. The fundamental problem of filter design is to estimate P(Y = 1|x) from data (image realizations), where x ranges over all possible observation vectors in the window. A Bayesian approach to the problem can be employed by assuming, for each x, a prior distribution for P(Y = 1|x). These prior distributions result from considering a range of model states by which the observed images are obtained from the ideal. Instead of estimating P(Y = 1|x) directly from observations by its sample mean relative to an image sample, P(Y = 1|x) is estimated in the Bayesian fashion, its Bayes estimator being the conditional expectation of P(Y = 1|x) given the data. Recently the authors have shown that, with accurate prior information, the Bayesian multiresolution filter has significant benefits from multiresolution filter design. Further, since the Bayesian filter is trained over a wider range of degradation levels, it inherits the added benefit of filtering a degraded image at different degradation levels in addition permitting iterative filtering. We discuss the necessary conditions that make a binary filter a good iterative filter and show that the Bayesian multiresolution filter is a natural candidate. The basic idea behind Bayesian iterative filtering is that, since the prior distribution covers a wide range of degradation levels, an application of the filter converts the degraded image to an image of less degradation for which the prior distribution is sufficiently robust to still be effective. Further application of the filter leads to further reduction of degradation. We consider edge noise in the experiments, with an emphasis on realistically degraded document images." @default.
• W2071799300 created "2016-06-24" @default.
• W2071799300 creator A5010097254 @default.
• W2071799300 creator A5073884353 @default.
• W2071799300 date "2001-05-08" @default.
• W2071799300 modified "2023-09-23" @default.
• W2071799300 title "<title>Bayesian iterative binary filter design</title>" @default.
• W2071799300 doi "https://doi.org/10.1117/12.424975" @default.
• W2071799300 hasPublicationYear "2001" @default.
• W2071799300 type Work @default.
• W2071799300 sameAs 2071799300 @default.
• W2071799300 citedByCount "0" @default.
• W2071799300 crossrefType "proceedings-article" @default.
• W2071799300 hasAuthorship W2071799300A5010097254 @default.
• W2071799300 hasAuthorship W2071799300A5073884353 @default.
• W2071799300 hasConcept C105795698 @default.
• W2071799300 hasConcept C106131492 @default.
• W2071799300 hasConcept C107673813 @default.
• W2071799300 hasConcept C11413529 @default.
• W2071799300 hasConcept C153180895 @default.
• W2071799300 hasConcept C154945302 @default.
• W2071799300 hasConcept C185429906 @default.
• W2071799300 hasConcept C186215838 @default.
• W2071799300 hasConcept C207201462 @default.
• W2071799300 hasConcept C31972630 @default.
• W2071799300 hasConcept C33923547 @default.
• W2071799300 hasConcept C41008148 @default.
• W2071799300 hasConcept C43555835 @default.
• W2071799300 hasConcept C44492722 @default.
• W2071799300 hasConcept C48372109 @default.
• W2071799300 hasConcept C94375191 @default.
• W2071799300 hasConceptScore W2071799300C105795698 @default.
• W2071799300 hasConceptScore W2071799300C106131492 @default.
• W2071799300 hasConceptScore W2071799300C107673813 @default.
• W2071799300 hasConceptScore W2071799300C11413529 @default.
• W2071799300 hasConceptScore W2071799300C153180895 @default.
• W2071799300 hasConceptScore W2071799300C154945302 @default.
• W2071799300 hasConceptScore W2071799300C185429906 @default.
• W2071799300 hasConceptScore W2071799300C186215838 @default.
• W2071799300 hasConceptScore W2071799300C207201462 @default.
• W2071799300 hasConceptScore W2071799300C31972630 @default.
• W2071799300 hasConceptScore W2071799300C33923547 @default.
• W2071799300 hasConceptScore W2071799300C41008148 @default.
• W2071799300 hasConceptScore W2071799300C43555835 @default.
• W2071799300 hasConceptScore W2071799300C44492722 @default.
• W2071799300 hasConceptScore W2071799300C48372109 @default.
• W2071799300 hasConceptScore W2071799300C94375191 @default.
• W2071799300 hasLocation W20717993001 @default.
• W2071799300 hasOpenAccess W2071799300 @default.
• W2071799300 hasPrimaryLocation W20717993001 @default.
• W2071799300 hasRelatedWork W1481784412 @default.
• W2071799300 hasRelatedWork W1841317565 @default.
• W2071799300 hasRelatedWork W1998224952 @default.
• W2071799300 hasRelatedWork W2005215483 @default.
• W2071799300 hasRelatedWork W2022899266 @default.
• W2071799300 hasRelatedWork W2035784308 @default.
• W2071799300 hasRelatedWork W2036273357 @default.
• W2071799300 hasRelatedWork W2041880908 @default.
• W2071799300 hasRelatedWork W2068047946 @default.
• W2071799300 hasRelatedWork W2102293690 @default.
• W2071799300 hasRelatedWork W2102557234 @default.
• W2071799300 hasRelatedWork W2103254499 @default.
• W2071799300 hasRelatedWork W2112899949 @default.
• W2071799300 hasRelatedWork W2119962468 @default.
• W2071799300 hasRelatedWork W2141423041 @default.
• W2071799300 hasRelatedWork W2149972629 @default.
• W2071799300 hasRelatedWork W2153504680 @default.
• W2071799300 hasRelatedWork W2244270984 @default.
• W2071799300 hasRelatedWork W2401794807 @default.
• W2071799300 hasRelatedWork W2922160104 @default.
• W2071799300 isParatext "false" @default.
• W2071799300 isRetracted "false" @default.
• W2071799300 magId "2071799300" @default.
• W2071799300 workType "article" @default.