Matches in SemOpenAlex for { <https://semopenalex.org/work/W2168118331> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2168118331 endingPage "531" @default.
- W2168118331 startingPage "516" @default.
- W2168118331 abstract "We address the problem of adaptive regularization in image restoration by adopting a neural-network learning approach. Instead of explicitly specifying the local regularization parameter values, they are regarded as network weights which are then modified through the supply of appropriate training examples. The desired response of the network is in the form of a gray level value estimate of the current pixel using weighted order statistic (WOS) filter. However, instead of replacing the previous value with this estimate, this is used to modify the network weights, or equivalently, the regularization parameters such that the restored gray level value produced by the network is closer to this desired response. In this way, the single WOS estimation scheme can allow appropriate parameter values to emerge under different noise conditions, rather than requiring their explicit selection in each occasion. In addition, we also consider the separate regularization of edges and textures due to their different noise masking capabilities. This in turn requires discriminating between these two feature types. Due to the inability of conventional local variance measures to distinguish these two high variance features, we propose the new edge-texture characterization (ETC) measure which performs this discrimination based on a scalar value only. This is then incorporated into a fuzzified form of the previous neural network which determines the degree of membership of each high variance pixel in two fuzzy sets, the EDGE and TEXTURE fuzzy sets, from the local ETC value, and then evaluates the appropriate regularization parameter by appropriately combining these two membership function values." @default.
- W2168118331 created "2016-06-24" @default.
- W2168118331 creator A5001287866 @default.
- W2168118331 creator A5014196059 @default.
- W2168118331 date "2001-05-01" @default.
- W2168118331 modified "2023-09-26" @default.
- W2168118331 title "A neural learning approach for adaptive image restoration using a fuzzy model-based network architecture" @default.
- W2168118331 cites W1545988247 @default.
- W2168118331 cites W1996692737 @default.
- W2168118331 cites W1998644394 @default.
- W2168118331 cites W2007148047 @default.
- W2168118331 cites W2015470290 @default.
- W2168118331 cites W2020999234 @default.
- W2168118331 cites W2028364099 @default.
- W2168118331 cites W2031879798 @default.
- W2168118331 cites W2035097277 @default.
- W2168118331 cites W2052055672 @default.
- W2168118331 cites W2096798358 @default.
- W2168118331 cites W2102091600 @default.
- W2168118331 cites W2102897151 @default.
- W2168118331 cites W2106866681 @default.
- W2168118331 cites W2110483414 @default.
- W2168118331 cites W2120829258 @default.
- W2168118331 cites W2132732065 @default.
- W2168118331 cites W2136766943 @default.
- W2168118331 cites W2140075227 @default.
- W2168118331 cites W2146615496 @default.
- W2168118331 cites W2150060382 @default.
- W2168118331 cites W2159540571 @default.
- W2168118331 cites W2170042613 @default.
- W2168118331 cites W2476868371 @default.
- W2168118331 cites W4211007335 @default.
- W2168118331 cites W4214910658 @default.
- W2168118331 cites W2142447555 @default.
- W2168118331 doi "https://doi.org/10.1109/72.925555" @default.
- W2168118331 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/18249885" @default.
- W2168118331 hasPublicationYear "2001" @default.
- W2168118331 type Work @default.
- W2168118331 sameAs 2168118331 @default.
- W2168118331 citedByCount "47" @default.
- W2168118331 countsByYear W21681183312012 @default.
- W2168118331 countsByYear W21681183312013 @default.
- W2168118331 countsByYear W21681183312014 @default.
- W2168118331 countsByYear W21681183312015 @default.
- W2168118331 countsByYear W21681183312019 @default.
- W2168118331 countsByYear W21681183312021 @default.
- W2168118331 countsByYear W21681183312022 @default.
- W2168118331 crossrefType "journal-article" @default.
- W2168118331 hasAuthorship W2168118331A5001287866 @default.
- W2168118331 hasAuthorship W2168118331A5014196059 @default.
- W2168118331 hasConcept C11413529 @default.
- W2168118331 hasConcept C153180895 @default.
- W2168118331 hasConcept C154945302 @default.
- W2168118331 hasConcept C160633673 @default.
- W2168118331 hasConcept C2776135515 @default.
- W2168118331 hasConcept C33923547 @default.
- W2168118331 hasConcept C41008148 @default.
- W2168118331 hasConcept C50644808 @default.
- W2168118331 hasConcept C58166 @default.
- W2168118331 hasConceptScore W2168118331C11413529 @default.
- W2168118331 hasConceptScore W2168118331C153180895 @default.
- W2168118331 hasConceptScore W2168118331C154945302 @default.
- W2168118331 hasConceptScore W2168118331C160633673 @default.
- W2168118331 hasConceptScore W2168118331C2776135515 @default.
- W2168118331 hasConceptScore W2168118331C33923547 @default.
- W2168118331 hasConceptScore W2168118331C41008148 @default.
- W2168118331 hasConceptScore W2168118331C50644808 @default.
- W2168118331 hasConceptScore W2168118331C58166 @default.
- W2168118331 hasIssue "3" @default.
- W2168118331 hasLocation W21681183311 @default.
- W2168118331 hasLocation W21681183312 @default.
- W2168118331 hasOpenAccess W2168118331 @default.
- W2168118331 hasPrimaryLocation W21681183311 @default.
- W2168118331 hasRelatedWork W1965781815 @default.
- W2168118331 hasRelatedWork W2004374232 @default.
- W2168118331 hasRelatedWork W2136485282 @default.
- W2168118331 hasRelatedWork W2149249189 @default.
- W2168118331 hasRelatedWork W2269705005 @default.
- W2168118331 hasRelatedWork W2542880803 @default.
- W2168118331 hasRelatedWork W2546871836 @default.
- W2168118331 hasRelatedWork W2547748020 @default.
- W2168118331 hasRelatedWork W2565015337 @default.
- W2168118331 hasRelatedWork W3043252291 @default.
- W2168118331 hasVolume "12" @default.
- W2168118331 isParatext "false" @default.
- W2168118331 isRetracted "false" @default.
- W2168118331 magId "2168118331" @default.
- W2168118331 workType "article" @default.