FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805499487> ?p ?o ?g. }

• W2805499487 endingPage "295" @default.
• W2805499487 startingPage "285" @default.
• W2805499487 abstract "As a benchmark structure in the retina, the precise localization of the Optic Disc (OD) has received considerable attention from researchers owning to its importance for ophthalmic image analysis and retinopathy screening. In most literature works, although OD localization has achieved fairly good performance, rather less attention has been paid to supervised techniques. As the ODs are common in characteristics and form a fixed pattern, we propose in this paper an OD localization method based on Convolutional Neural Networks (CNNs). In data preparation, the blue channel in the fundus image, which is always empty or noisy and tends to be uninformative, is replaced by coarsely segmented vasculature maps (Red channel, Green channel and vasculatures are denoted as RGV). In addition, the input of the CNN structures is rectangular instead of square in order to involve more context information of the vasculatures. For training, a two-stage process is designed to alleviate the class-imbalance problem by choosing large number of positive samples at the first stage and choosing samples at the center of OD to fine-tune the fist-stage model at the second stage. Then a probability guided search algorithm is developed to improve the efficiency of OD localization by selectively searching patches with large chances to be an OD and their neighbors. Finally, the precise OD position is located as center of the highest probability regions after weighted voting. Extensive experiments on four publicly available databases demonstrate the effectiveness and efficiency of the proposed method, with an average detection rate of 99.11% and detection time less than 15 s per image." @default.
• W2805499487 created "2018-06-13" @default.
• W2805499487 creator A5008387548 @default.
• W2805499487 creator A5029842239 @default.
• W2805499487 creator A5035643040 @default.
• W2805499487 creator A5040809758 @default.
• W2805499487 creator A5076976404 @default.
• W2805499487 creator A5088718594 @default.
• W2805499487 date "2018-10-01" @default.
• W2805499487 modified "2023-10-01" @default.
• W2805499487 title "Fast and effective optic disk localization based on convolutional neural network" @default.
• W2805499487 cites W1540549883 @default.
• W2805499487 cites W1825382665 @default.
• W2805499487 cites W2016194585 @default.
• W2805499487 cites W2032477478 @default.
• W2805499487 cites W2038137113 @default.
• W2805499487 cites W2043960248 @default.
• W2805499487 cites W2057538902 @default.
• W2805499487 cites W2076063813 @default.
• W2805499487 cites W2086106167 @default.
• W2805499487 cites W2105172918 @default.
• W2805499487 cites W2112796928 @default.
• W2805499487 cites W2122644916 @default.
• W2805499487 cites W2123303981 @default.
• W2805499487 cites W2135914471 @default.
• W2805499487 cites W2136103933 @default.
• W2805499487 cites W2141134684 @default.
• W2805499487 cites W2150769593 @default.
• W2805499487 cites W2152201689 @default.
• W2805499487 cites W2159764117 @default.
• W2805499487 cites W2169164902 @default.
• W2805499487 cites W2169736040 @default.
• W2805499487 cites W2170203892 @default.
• W2805499487 cites W2253429366 @default.
• W2805499487 cites W2463681903 @default.
• W2805499487 doi "https://doi.org/10.1016/j.neucom.2018.05.114" @default.
• W2805499487 hasPublicationYear "2018" @default.
• W2805499487 type Work @default.
• W2805499487 sameAs 2805499487 @default.
• W2805499487 citedByCount "16" @default.
• W2805499487 countsByYear W28054994872019 @default.
• W2805499487 countsByYear W28054994872020 @default.
• W2805499487 countsByYear W28054994872021 @default.
• W2805499487 countsByYear W28054994872022 @default.
• W2805499487 countsByYear W28054994872023 @default.
• W2805499487 crossrefType "journal-article" @default.
• W2805499487 hasAuthorship W2805499487A5008387548 @default.
• W2805499487 hasAuthorship W2805499487A5029842239 @default.
• W2805499487 hasAuthorship W2805499487A5035643040 @default.
• W2805499487 hasAuthorship W2805499487A5040809758 @default.
• W2805499487 hasAuthorship W2805499487A5076976404 @default.
• W2805499487 hasAuthorship W2805499487A5088718594 @default.
• W2805499487 hasConcept C111919701 @default.
• W2805499487 hasConcept C127162648 @default.
• W2805499487 hasConcept C13280743 @default.
• W2805499487 hasConcept C151730666 @default.
• W2805499487 hasConcept C153180895 @default.
• W2805499487 hasConcept C154945302 @default.
• W2805499487 hasConcept C185798385 @default.
• W2805499487 hasConcept C205649164 @default.
• W2805499487 hasConcept C2779343474 @default.
• W2805499487 hasConcept C31258907 @default.
• W2805499487 hasConcept C41008148 @default.
• W2805499487 hasConcept C81363708 @default.
• W2805499487 hasConcept C86803240 @default.
• W2805499487 hasConcept C98045186 @default.
• W2805499487 hasConceptScore W2805499487C111919701 @default.
• W2805499487 hasConceptScore W2805499487C127162648 @default.
• W2805499487 hasConceptScore W2805499487C13280743 @default.
• W2805499487 hasConceptScore W2805499487C151730666 @default.
• W2805499487 hasConceptScore W2805499487C153180895 @default.
• W2805499487 hasConceptScore W2805499487C154945302 @default.
• W2805499487 hasConceptScore W2805499487C185798385 @default.
• W2805499487 hasConceptScore W2805499487C205649164 @default.
• W2805499487 hasConceptScore W2805499487C2779343474 @default.
• W2805499487 hasConceptScore W2805499487C31258907 @default.
• W2805499487 hasConceptScore W2805499487C41008148 @default.
• W2805499487 hasConceptScore W2805499487C81363708 @default.
• W2805499487 hasConceptScore W2805499487C86803240 @default.
• W2805499487 hasConceptScore W2805499487C98045186 @default.
• W2805499487 hasFunder F4320321001 @default.
• W2805499487 hasLocation W28054994871 @default.
• W2805499487 hasOpenAccess W2805499487 @default.
• W2805499487 hasPrimaryLocation W28054994871 @default.
• W2805499487 hasRelatedWork W1895390915 @default.
• W2805499487 hasRelatedWork W2175746458 @default.
• W2805499487 hasRelatedWork W2406522397 @default.
• W2805499487 hasRelatedWork W2613736958 @default.
• W2805499487 hasRelatedWork W2732542196 @default.
• W2805499487 hasRelatedWork W2760085659 @default.
• W2805499487 hasRelatedWork W2883200793 @default.
• W2805499487 hasRelatedWork W2949389737 @default.
• W2805499487 hasRelatedWork W2963556241 @default.
• W2805499487 hasRelatedWork W3093612317 @default.
• W2805499487 hasVolume "312" @default.
• W2805499487 isParatext "false" @default.
• W2805499487 isRetracted "false" @default.
• W2805499487 magId "2805499487" @default.

• next