Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206619116> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3206619116 endingPage "2508" @default.
- W3206619116 startingPage "2501" @default.
- W3206619116 abstract "The Fast Super-Resolution Convolutional Neural Network algorithm (FSRCNN) is difficult to extract deep image information due to the small number of convolution layers and the correlation lack between the feature information of adjacent convolutional layers. To solve this problem, a deep residual network super-resolution reconstruction method with multi-level skip connections is proposed. Firstly, a residual block with multi-level skip connections is designed to solve the problem that the characteristic information of adjacent convolutional layers lacks relevance. A deep residual network with multi-level skip connections is constructed on the basis of the residual block. Then, the deep residual network connected to the multi-level skip is trained by using the adaptive gradient rate strategy of Stochastic Gradient Descent (SGD) method and the network super-resolution reconstruction model is obtained. Finally, the low-resolution image is input into the deep residual network super-resolution reconstruction model with the multi-level skip connections, and the residual eigenvalue is obtained by the residual block connected the multi-level skip connections. The residual eigenvalue and the low resolution image are combined and converted into a high resolution image. The proposed method is compared with the bicubic, A+, SRCNN, FSRCNN and ESPCN algorithms in the Set5 and Set14 test sets. The proposed method is superior to other comparison algorithms in terms of visual effects and evaluation index values." @default.
- W3206619116 created "2021-10-25" @default.
- W3206619116 creator A5034489653 @default.
- W3206619116 creator A5040724309 @default.
- W3206619116 date "2019-10-01" @default.
- W3206619116 modified "2023-09-28" @default.
- W3206619116 title "Super-Resolution Reconstruction of Deep Residual Network with Multi-Level Skip Connections" @default.
- W3206619116 doi "https://doi.org/10.11999/jeit190036" @default.
- W3206619116 hasPublicationYear "2019" @default.
- W3206619116 type Work @default.
- W3206619116 sameAs 3206619116 @default.
- W3206619116 citedByCount "1" @default.
- W3206619116 countsByYear W32066191162020 @default.
- W3206619116 crossrefType "journal-article" @default.
- W3206619116 hasAuthorship W3206619116A5034489653 @default.
- W3206619116 hasAuthorship W3206619116A5040724309 @default.
- W3206619116 hasConcept C11413529 @default.
- W3206619116 hasConcept C138885662 @default.
- W3206619116 hasConcept C153180895 @default.
- W3206619116 hasConcept C154945302 @default.
- W3206619116 hasConcept C155512373 @default.
- W3206619116 hasConcept C171836373 @default.
- W3206619116 hasConcept C2524010 @default.
- W3206619116 hasConcept C2776401178 @default.
- W3206619116 hasConcept C2777210771 @default.
- W3206619116 hasConcept C33923547 @default.
- W3206619116 hasConcept C41008148 @default.
- W3206619116 hasConcept C41895202 @default.
- W3206619116 hasConcept C45347329 @default.
- W3206619116 hasConcept C49608258 @default.
- W3206619116 hasConcept C50644808 @default.
- W3206619116 hasConcept C81363708 @default.
- W3206619116 hasConceptScore W3206619116C11413529 @default.
- W3206619116 hasConceptScore W3206619116C138885662 @default.
- W3206619116 hasConceptScore W3206619116C153180895 @default.
- W3206619116 hasConceptScore W3206619116C154945302 @default.
- W3206619116 hasConceptScore W3206619116C155512373 @default.
- W3206619116 hasConceptScore W3206619116C171836373 @default.
- W3206619116 hasConceptScore W3206619116C2524010 @default.
- W3206619116 hasConceptScore W3206619116C2776401178 @default.
- W3206619116 hasConceptScore W3206619116C2777210771 @default.
- W3206619116 hasConceptScore W3206619116C33923547 @default.
- W3206619116 hasConceptScore W3206619116C41008148 @default.
- W3206619116 hasConceptScore W3206619116C41895202 @default.
- W3206619116 hasConceptScore W3206619116C45347329 @default.
- W3206619116 hasConceptScore W3206619116C49608258 @default.
- W3206619116 hasConceptScore W3206619116C50644808 @default.
- W3206619116 hasConceptScore W3206619116C81363708 @default.
- W3206619116 hasIssue "10" @default.
- W3206619116 hasLocation W32066191161 @default.
- W3206619116 hasOpenAccess W3206619116 @default.
- W3206619116 hasPrimaryLocation W32066191161 @default.
- W3206619116 hasRelatedWork W2059198384 @default.
- W3206619116 hasRelatedWork W2353728785 @default.
- W3206619116 hasRelatedWork W2366823466 @default.
- W3206619116 hasRelatedWork W2384616479 @default.
- W3206619116 hasRelatedWork W2751843641 @default.
- W3206619116 hasRelatedWork W2892633656 @default.
- W3206619116 hasRelatedWork W2951194500 @default.
- W3206619116 hasRelatedWork W2955540013 @default.
- W3206619116 hasRelatedWork W2967819594 @default.
- W3206619116 hasRelatedWork W2991350900 @default.
- W3206619116 hasRelatedWork W3162586188 @default.
- W3206619116 hasRelatedWork W3173281405 @default.
- W3206619116 hasRelatedWork W3173995083 @default.
- W3206619116 hasRelatedWork W3200676563 @default.
- W3206619116 hasRelatedWork W1596460782 @default.
- W3206619116 hasRelatedWork W2931353408 @default.
- W3206619116 hasRelatedWork W2957868400 @default.
- W3206619116 hasRelatedWork W2975754295 @default.
- W3206619116 hasRelatedWork W3000949370 @default.
- W3206619116 hasRelatedWork W3155338829 @default.
- W3206619116 hasVolume "41" @default.
- W3206619116 isParatext "false" @default.
- W3206619116 isRetracted "false" @default.
- W3206619116 magId "3206619116" @default.
- W3206619116 workType "article" @default.