Matches in SemOpenAlex for { <https://semopenalex.org/work/W2040772670> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2040772670 abstract "The performance of dictionary-based super-resolution (SR) strongly depends on thecontents of the training dataset. Nevertheless, many dictionary-based SR methods randomly select patches from of a larger set of training images to build their dictionaries[8,14,19,20], thus relying on patches being diverse enough. This paper describesa dictionary building method for SR based on adaptively selecting an optimal subset ofpatches out of the training images. Each training image is divided into sub-image entities,named regions, of such a size that texture consistency is preserved and high-frequency(HF) energy is present. For each input patch to super-resolve, the best-fitting region isfound through a Bayesian selection. In order to handle the high number of regions inthe training dataset, a local Naive Bayes Nearest Neighbor (NBNN) approach is used.Trained with this adapted subset of patches, sparse coding SR is applied to recover thehigh-resolution image. Experimental results demonstrate that using our adaptive algo-rithm produces an improvement in SR performance with respect to non-adaptive training." @default.
- W2040772670 created "2016-06-24" @default.
- W2040772670 creator A5013682396 @default.
- W2040772670 creator A5031554273 @default.
- W2040772670 creator A5040412734 @default.
- W2040772670 creator A5085613617 @default.
- W2040772670 date "2013-01-01" @default.
- W2040772670 modified "2023-09-27" @default.
- W2040772670 title "Bayesian region selection for adaptive dictionary-based Super-Resolution" @default.
- W2040772670 cites W2003115311 @default.
- W2040772670 cites W2087380704 @default.
- W2040772670 cites W2097074225 @default.
- W2040772670 cites W2103844245 @default.
- W2040772670 cites W2111634407 @default.
- W2040772670 cites W2113606819 @default.
- W2040772670 cites W2114398647 @default.
- W2040772670 cites W2118963448 @default.
- W2040772670 cites W2121058967 @default.
- W2040772670 cites W2131349449 @default.
- W2040772670 cites W2133665775 @default.
- W2040772670 cites W2149760002 @default.
- W2040772670 cites W2151103935 @default.
- W2040772670 cites W2157494358 @default.
- W2040772670 cites W2160558632 @default.
- W2040772670 cites W2161516371 @default.
- W2040772670 cites W2163523041 @default.
- W2040772670 cites W2163935418 @default.
- W2040772670 cites W2165939075 @default.
- W2040772670 cites W2166742463 @default.
- W2040772670 cites W2140257560 @default.
- W2040772670 doi "https://doi.org/10.5244/c.27.37" @default.
- W2040772670 hasPublicationYear "2013" @default.
- W2040772670 type Work @default.
- W2040772670 sameAs 2040772670 @default.
- W2040772670 citedByCount "4" @default.
- W2040772670 countsByYear W20407726702014 @default.
- W2040772670 countsByYear W20407726702015 @default.
- W2040772670 countsByYear W20407726702017 @default.
- W2040772670 crossrefType "proceedings-article" @default.
- W2040772670 hasAuthorship W2040772670A5013682396 @default.
- W2040772670 hasAuthorship W2040772670A5031554273 @default.
- W2040772670 hasAuthorship W2040772670A5040412734 @default.
- W2040772670 hasAuthorship W2040772670A5085613617 @default.
- W2040772670 hasBestOaLocation W20407726701 @default.
- W2040772670 hasConcept C107673813 @default.
- W2040772670 hasConcept C153180895 @default.
- W2040772670 hasConcept C154945302 @default.
- W2040772670 hasConcept C41008148 @default.
- W2040772670 hasConcept C81917197 @default.
- W2040772670 hasConceptScore W2040772670C107673813 @default.
- W2040772670 hasConceptScore W2040772670C153180895 @default.
- W2040772670 hasConceptScore W2040772670C154945302 @default.
- W2040772670 hasConceptScore W2040772670C41008148 @default.
- W2040772670 hasConceptScore W2040772670C81917197 @default.
- W2040772670 hasLocation W20407726701 @default.
- W2040772670 hasLocation W20407726702 @default.
- W2040772670 hasOpenAccess W2040772670 @default.
- W2040772670 hasPrimaryLocation W20407726701 @default.
- W2040772670 hasRelatedWork W1978450727 @default.
- W2040772670 hasRelatedWork W2033914206 @default.
- W2040772670 hasRelatedWork W2085949256 @default.
- W2040772670 hasRelatedWork W2146076056 @default.
- W2040772670 hasRelatedWork W2163831990 @default.
- W2040772670 hasRelatedWork W2378160586 @default.
- W2040772670 hasRelatedWork W2606073172 @default.
- W2040772670 hasRelatedWork W2970622411 @default.
- W2040772670 hasRelatedWork W3003836766 @default.
- W2040772670 hasRelatedWork W3107474891 @default.
- W2040772670 isParatext "false" @default.
- W2040772670 isRetracted "false" @default.
- W2040772670 magId "2040772670" @default.
- W2040772670 workType "article" @default.