FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2899691808> ?p ?o ?g. }

• W2899691808 endingPage "69252" @default.
• W2899691808 startingPage "69242" @default.
• W2899691808 abstract "Blind image deconvolution is an ill-posed problem, which is mainly addressed by the regularization methods. Wavelet transform is an effective denoising method related to regularized inversion. In this paper, wavelet transform is utilized to decompose and extract the low- and high-frequency information of the blurred image, which is taken as the first step of the presented deblurring methods in this paper. However, when the process highlights the approximate portion of the image feature, the blurry image will be smoothed so that the image is distorted. Simultaneously, the overall wavelet transform will result in excessive data redundancy for the image. Thus, in the second step, based upon the recursive convolution neural network, a deep recursive convolutional neural network (R-DbCNN) is designed, which can eliminate or weaken the characteristics of high data redundancy and image smoothness caused by wavelet transform to remove the blur of corrupted image. Comparing with the traditional convolution neural network in image restoration, R-DbCNN has better performance in deblurring with fast training speed. Thereafter, a novel loss function is built to attain the best deblurring effect of the proposed method based on the L <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sub> regularization term. The experiment results demonstrate that our method has practical applicability for image restoration with different blurs, such as the motion blur, Gaussian blur, and out-of-focus by camera." @default.
• W2899691808 created "2018-11-16" @default.
• W2899691808 creator A5005699424 @default.
• W2899691808 creator A5012353096 @default.
• W2899691808 creator A5034470719 @default.
• W2899691808 creator A5059141031 @default.
• W2899691808 date "2018-01-01" @default.
• W2899691808 modified "2023-10-13" @default.
• W2899691808 title "Blind Deblurring via a Novel Recursive Deep CNN Improved by Wavelet Transform" @default.
• W2899691808 cites W1529631489 @default.
• W2899691808 cites W1906770428 @default.
• W2899691808 cites W1967873773 @default.
• W2899691808 cites W1973567017 @default.
• W2899691808 cites W1974013408 @default.
• W2899691808 cites W1994321112 @default.
• W2899691808 cites W1996739866 @default.
• W2899691808 cites W2037133587 @default.
• W2899691808 cites W2048695508 @default.
• W2899691808 cites W2081385919 @default.
• W2899691808 cites W2088691392 @default.
• W2899691808 cites W2099628070 @default.
• W2899691808 cites W2101128983 @default.
• W2899691808 cites W2113945798 @default.
• W2899691808 cites W2117998419 @default.
• W2899691808 cites W2119624920 @default.
• W2899691808 cites W2120364003 @default.
• W2899691808 cites W2122714239 @default.
• W2899691808 cites W2134276905 @default.
• W2899691808 cites W2138204001 @default.
• W2899691808 cites W2153663612 @default.
• W2899691808 cites W2159558889 @default.
• W2899691808 cites W2163612361 @default.
• W2899691808 cites W2254039850 @default.
• W2899691808 cites W2293078015 @default.
• W2899691808 cites W2429289397 @default.
• W2899691808 cites W2508457857 @default.
• W2899691808 cites W2613155248 @default.
• W2899691808 cites W272355707 @default.
• W2899691808 cites W3102025760 @default.
• W2899691808 cites W3123837026 @default.
• W2899691808 cites W4239978906 @default.
• W2899691808 cites W4247043502 @default.
• W2899691808 doi "https://doi.org/10.1109/access.2018.2880279" @default.
• W2899691808 hasPublicationYear "2018" @default.
• W2899691808 type Work @default.
• W2899691808 sameAs 2899691808 @default.
• W2899691808 citedByCount "17" @default.
• W2899691808 countsByYear W28996918082019 @default.
• W2899691808 countsByYear W28996918082020 @default.
• W2899691808 countsByYear W28996918082021 @default.
• W2899691808 countsByYear W28996918082022 @default.
• W2899691808 countsByYear W28996918082023 @default.
• W2899691808 crossrefType "journal-article" @default.
• W2899691808 hasAuthorship W2899691808A5005699424 @default.
• W2899691808 hasAuthorship W2899691808A5012353096 @default.
• W2899691808 hasAuthorship W2899691808A5034470719 @default.
• W2899691808 hasAuthorship W2899691808A5059141031 @default.
• W2899691808 hasBestOaLocation W28996918081 @default.
• W2899691808 hasConcept C104317376 @default.
• W2899691808 hasConcept C106430172 @default.
• W2899691808 hasConcept C11413529 @default.
• W2899691808 hasConcept C115961682 @default.
• W2899691808 hasConcept C153180895 @default.
• W2899691808 hasConcept C154945302 @default.
• W2899691808 hasConcept C174576160 @default.
• W2899691808 hasConcept C196216189 @default.
• W2899691808 hasConcept C2777693668 @default.
• W2899691808 hasConcept C30044814 @default.
• W2899691808 hasConcept C31972630 @default.
• W2899691808 hasConcept C33923547 @default.
• W2899691808 hasConcept C41008148 @default.
• W2899691808 hasConcept C45347329 @default.
• W2899691808 hasConcept C47432892 @default.
• W2899691808 hasConcept C50644808 @default.
• W2899691808 hasConcept C81363708 @default.
• W2899691808 hasConcept C9417928 @default.
• W2899691808 hasConceptScore W2899691808C104317376 @default.
• W2899691808 hasConceptScore W2899691808C106430172 @default.
• W2899691808 hasConceptScore W2899691808C11413529 @default.
• W2899691808 hasConceptScore W2899691808C115961682 @default.
• W2899691808 hasConceptScore W2899691808C153180895 @default.
• W2899691808 hasConceptScore W2899691808C154945302 @default.
• W2899691808 hasConceptScore W2899691808C174576160 @default.
• W2899691808 hasConceptScore W2899691808C196216189 @default.
• W2899691808 hasConceptScore W2899691808C2777693668 @default.
• W2899691808 hasConceptScore W2899691808C30044814 @default.
• W2899691808 hasConceptScore W2899691808C31972630 @default.
• W2899691808 hasConceptScore W2899691808C33923547 @default.
• W2899691808 hasConceptScore W2899691808C41008148 @default.
• W2899691808 hasConceptScore W2899691808C45347329 @default.
• W2899691808 hasConceptScore W2899691808C47432892 @default.
• W2899691808 hasConceptScore W2899691808C50644808 @default.
• W2899691808 hasConceptScore W2899691808C81363708 @default.
• W2899691808 hasConceptScore W2899691808C9417928 @default.
• W2899691808 hasFunder F4320321001 @default.
• W2899691808 hasFunder F4320322859 @default.
• W2899691808 hasLocation W28996918081 @default.
• W2899691808 hasOpenAccess W2899691808 @default.

• next