FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317384327> ?p ?o ?g. }

• W4317384327 abstract "Denoising convolutional neural network (DnCNN) has achieved competitive denoising performance for Gaussian noise using residual learning. The same idea can also be applied in the impulse noise (IN) removal by changing the training data. However, as a discriminative learning-based algorithm, DnCNN lacks flexibility in removing spatially varying noise, such as random-valued impulse noise (RVIN). To address this problem, we propose a fine-tuning CNN based on relaxed Bayesian-optimized support vector machine (BO-SVM) for RVIN removal using a relaxed BO-SVM as a detector and a fine-tuning DnCNN as a denoiser. The relaxed BO-SVM is developed to classify all pixels of the test image into two categories: noise and noise-free. A relaxed rule is provided to preserve the information of slightly corrupted pixels, and the system is trained with an optimal feature set, which comprises of newly introduced local ternary pattern with previously used gray-level difference, average background difference, and median value difference. The key hyperparameters of the relaxed SVM are obtained using the Bayesian optimization technique. Then the DnCNN works for image reconstruction through fine-tuning experiments by the use of the corrupted pixels identified by the detector. The experimental results show that the proposed method reports promising results on RVIN removal over other state-of-the-art denoising methods." @default.
• W4317384327 created "2023-01-19" @default.
• W4317384327 creator A5009956735 @default.
• W4317384327 creator A5074141445 @default.
• W4317384327 date "2023-01-18" @default.
• W4317384327 modified "2023-10-16" @default.
• W4317384327 title "Fine-tuning convolutional neural network based on relaxed Bayesian-optimized support vector machine for random-valued impulse noise removal" @default.
• W4317384327 cites W1162493323 @default.
• W4317384327 cites W1510052597 @default.
• W4317384327 cites W1754661426 @default.
• W4317384327 cites W1901129140 @default.
• W4317384327 cites W1909664615 @default.
• W4317384327 cites W1945008097 @default.
• W4317384327 cites W2027354944 @default.
• W4317384327 cites W2050630265 @default.
• W4317384327 cites W2061144551 @default.
• W4317384327 cites W2062925858 @default.
• W4317384327 cites W2071399794 @default.
• W4317384327 cites W2077930717 @default.
• W4317384327 cites W2105884433 @default.
• W4317384327 cites W2106581202 @default.
• W4317384327 cites W2109239774 @default.
• W4317384327 cites W2110158442 @default.
• W4317384327 cites W2122374500 @default.
• W4317384327 cites W2122765317 @default.
• W4317384327 cites W2124139674 @default.
• W4317384327 cites W2127078478 @default.
• W4317384327 cites W2131156776 @default.
• W4317384327 cites W2150427434 @default.
• W4317384327 cites W2160817147 @default.
• W4317384327 cites W2161381512 @default.
• W4317384327 cites W2165141499 @default.
• W4317384327 cites W2166566250 @default.
• W4317384327 cites W2167707673 @default.
• W4317384327 cites W2169733476 @default.
• W4317384327 cites W2192203593 @default.
• W4317384327 cites W2337501905 @default.
• W4317384327 cites W2508457857 @default.
• W4317384327 cites W2565827560 @default.
• W4317384327 cites W2767579567 @default.
• W4317384327 cites W2799265886 @default.
• W4317384327 cites W2811012119 @default.
• W4317384327 cites W2944440084 @default.
• W4317384327 cites W2946032093 @default.
• W4317384327 cites W2947265870 @default.
• W4317384327 cites W2947827328 @default.
• W4317384327 cites W2953085622 @default.
• W4317384327 cites W2963783623 @default.
• W4317384327 cites W2968466051 @default.
• W4317384327 cites W3041133507 @default.
• W4317384327 cites W3104725225 @default.
• W4317384327 cites W3110900810 @default.
• W4317384327 cites W3134030750 @default.
• W4317384327 cites W3134277469 @default.
• W4317384327 cites W3196316500 @default.
• W4317384327 cites W3207382953 @default.
• W4317384327 cites W4220752354 @default.
• W4317384327 cites W4239399610 @default.
• W4317384327 cites W4298225755 @default.
• W4317384327 cites W2899705189 @default.
• W4317384327 doi "https://doi.org/10.1117/1.jei.32.1.013006" @default.
• W4317384327 hasPublicationYear "2023" @default.
• W4317384327 type Work @default.
• W4317384327 citedByCount "0" @default.
• W4317384327 crossrefType "journal-article" @default.
• W4317384327 hasAuthorship W4317384327A5009956735 @default.
• W4317384327 hasAuthorship W4317384327A5074141445 @default.
• W4317384327 hasConcept C115961682 @default.
• W4317384327 hasConcept C12267149 @default.
• W4317384327 hasConcept C153180895 @default.
• W4317384327 hasConcept C154945302 @default.
• W4317384327 hasConcept C160633673 @default.
• W4317384327 hasConcept C163294075 @default.
• W4317384327 hasConcept C41008148 @default.
• W4317384327 hasConcept C4199805 @default.
• W4317384327 hasConcept C81363708 @default.
• W4317384327 hasConcept C8642999 @default.
• W4317384327 hasConcept C99498987 @default.
• W4317384327 hasConceptScore W4317384327C115961682 @default.
• W4317384327 hasConceptScore W4317384327C12267149 @default.
• W4317384327 hasConceptScore W4317384327C153180895 @default.
• W4317384327 hasConceptScore W4317384327C154945302 @default.
• W4317384327 hasConceptScore W4317384327C160633673 @default.
• W4317384327 hasConceptScore W4317384327C163294075 @default.
• W4317384327 hasConceptScore W4317384327C41008148 @default.
• W4317384327 hasConceptScore W4317384327C4199805 @default.
• W4317384327 hasConceptScore W4317384327C81363708 @default.
• W4317384327 hasConceptScore W4317384327C8642999 @default.
• W4317384327 hasConceptScore W4317384327C99498987 @default.
• W4317384327 hasFunder F4320321001 @default.
• W4317384327 hasIssue "01" @default.
• W4317384327 hasLocation W43173843271 @default.
• W4317384327 hasOpenAccess W4317384327 @default.
• W4317384327 hasPrimaryLocation W43173843271 @default.
• W4317384327 hasRelatedWork W2099369243 @default.
• W4317384327 hasRelatedWork W2546871836 @default.
• W4317384327 hasRelatedWork W2781982286 @default.
• W4317384327 hasRelatedWork W2996933976 @default.
• W4317384327 hasRelatedWork W3193301557 @default.
• W4317384327 hasRelatedWork W3208266890 @default.

• next