Matches in SemOpenAlex for { <https://semopenalex.org/work/W3027010575> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3027010575 endingPage "101939" @default.
- W3027010575 startingPage "101939" @default.
- W3027010575 abstract "The optic disc (OD) and fovea are two important anatomical landmarks of the retina. Localization of OD and fovea plays an important role in retinal image analysis. This paper proposes a novel, efficient and robust method for OD detection and fovea localization. The proposed method consists of two steps. First, we use region proposal network to generate multiple OD region proposals, and then OD’s bounding box is identified as the proposal with the highest probability. Second, we create a region of interest containing the fovea based on the geometrical relationship between OD and fovea, and then employ a three-level cascaded convolutional neural network to locate the fovea, which is treated as a regression problem. The proposed method is trained and evaluated on three sets of fundus images (the first dataset contains 1955 fundus images and the other two are publicly available datasets respectively containing 516 and 1200 fundus images). According to 5-fold cross-validation experiments, our OD detection accuracy is respective 99.59%, 100%, and 100% for the three datasets and the corresponding fovea localization accuracy is respective 97.8%, 99.03%, and 99.25%. The proposed method is found to be robust and effective in OD detection and fovea localization, and its accuracy is comparable, or even superior to representative state-of-the-art algorithms." @default.
- W3027010575 created "2020-05-29" @default.
- W3027010575 creator A5002069152 @default.
- W3027010575 creator A5056599169 @default.
- W3027010575 creator A5079055375 @default.
- W3027010575 creator A5080168999 @default.
- W3027010575 date "2020-07-01" @default.
- W3027010575 modified "2023-10-18" @default.
- W3027010575 title "Efficient and robust optic disc detection and fovea localization using region proposal network and cascaded network" @default.
- W3027010575 cites W1596717185 @default.
- W3027010575 cites W1966206262 @default.
- W3027010575 cites W1969496006 @default.
- W3027010575 cites W1999354443 @default.
- W3027010575 cites W2016194585 @default.
- W3027010575 cites W2037969410 @default.
- W3027010575 cites W2088049833 @default.
- W3027010575 cites W2097612780 @default.
- W3027010575 cites W2100756624 @default.
- W3027010575 cites W2108598243 @default.
- W3027010575 cites W2123303981 @default.
- W3027010575 cites W2756892287 @default.
- W3027010575 cites W2802531310 @default.
- W3027010575 cites W2805499487 @default.
- W3027010575 doi "https://doi.org/10.1016/j.bspc.2020.101939" @default.
- W3027010575 hasPublicationYear "2020" @default.
- W3027010575 type Work @default.
- W3027010575 sameAs 3027010575 @default.
- W3027010575 citedByCount "21" @default.
- W3027010575 countsByYear W30270105752020 @default.
- W3027010575 countsByYear W30270105752021 @default.
- W3027010575 countsByYear W30270105752022 @default.
- W3027010575 countsByYear W30270105752023 @default.
- W3027010575 crossrefType "journal-article" @default.
- W3027010575 hasAuthorship W3027010575A5002069152 @default.
- W3027010575 hasAuthorship W3027010575A5056599169 @default.
- W3027010575 hasAuthorship W3027010575A5079055375 @default.
- W3027010575 hasAuthorship W3027010575A5080168999 @default.
- W3027010575 hasConcept C115961682 @default.
- W3027010575 hasConcept C118487528 @default.
- W3027010575 hasConcept C147037132 @default.
- W3027010575 hasConcept C153180895 @default.
- W3027010575 hasConcept C154945302 @default.
- W3027010575 hasConcept C185592680 @default.
- W3027010575 hasConcept C2776391266 @default.
- W3027010575 hasConcept C2779735895 @default.
- W3027010575 hasConcept C2780827179 @default.
- W3027010575 hasConcept C31972630 @default.
- W3027010575 hasConcept C41008148 @default.
- W3027010575 hasConcept C55493867 @default.
- W3027010575 hasConcept C63584917 @default.
- W3027010575 hasConcept C71924100 @default.
- W3027010575 hasConcept C81363708 @default.
- W3027010575 hasConceptScore W3027010575C115961682 @default.
- W3027010575 hasConceptScore W3027010575C118487528 @default.
- W3027010575 hasConceptScore W3027010575C147037132 @default.
- W3027010575 hasConceptScore W3027010575C153180895 @default.
- W3027010575 hasConceptScore W3027010575C154945302 @default.
- W3027010575 hasConceptScore W3027010575C185592680 @default.
- W3027010575 hasConceptScore W3027010575C2776391266 @default.
- W3027010575 hasConceptScore W3027010575C2779735895 @default.
- W3027010575 hasConceptScore W3027010575C2780827179 @default.
- W3027010575 hasConceptScore W3027010575C31972630 @default.
- W3027010575 hasConceptScore W3027010575C41008148 @default.
- W3027010575 hasConceptScore W3027010575C55493867 @default.
- W3027010575 hasConceptScore W3027010575C63584917 @default.
- W3027010575 hasConceptScore W3027010575C71924100 @default.
- W3027010575 hasConceptScore W3027010575C81363708 @default.
- W3027010575 hasFunder F4320321001 @default.
- W3027010575 hasLocation W30270105751 @default.
- W3027010575 hasOpenAccess W3027010575 @default.
- W3027010575 hasPrimaryLocation W30270105751 @default.
- W3027010575 hasRelatedWork W2387360586 @default.
- W3027010575 hasRelatedWork W2883297582 @default.
- W3027010575 hasRelatedWork W2952736415 @default.
- W3027010575 hasRelatedWork W2962677013 @default.
- W3027010575 hasRelatedWork W3036286480 @default.
- W3027010575 hasRelatedWork W3192357901 @default.
- W3027010575 hasRelatedWork W3205398323 @default.
- W3027010575 hasRelatedWork W3209723314 @default.
- W3027010575 hasRelatedWork W4237171675 @default.
- W3027010575 hasRelatedWork W4287027631 @default.
- W3027010575 hasVolume "60" @default.
- W3027010575 isParatext "false" @default.
- W3027010575 isRetracted "false" @default.
- W3027010575 magId "3027010575" @default.
- W3027010575 workType "article" @default.