Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290189491> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4290189491 endingPage "346" @default.
- W4290189491 startingPage "337" @default.
- W4290189491 abstract "Semantic segmentation is a fundamental problem for computer vision. On the other hand, for studies in the field of biometrics, semantic segmentation is gaining more importance. Many successful biometric recognition systems require a high- performance semantic segmentation algorithm. In this study, we present an effective ear segmentation technique in natural images. A convolutional neural network is trained for pixel-based ear segmentation. DeepLab v3+ network structure, with ResNet-18 as the backbone and Tversky lost function layer as the last layer, has been trained with natural and uncontrolled images. We perform the proposed network training using only the 750 images in the Annotated Web Ears (AWE) training set. The corresponding tests are performed on the AWE Test Set, University of Ljubljana Test Set, and the Collection A of In-The-Wild dataset. For the Annotated Web Ears (AWE) dataset, intersection over union (IoU) is measured as 86.3% for the AWE database. To the best of our knowledge, this is the highest performance achieved among the algorithms tested on the AWE test set." @default.
- W4290189491 created "2022-08-07" @default.
- W4290189491 creator A5000022616 @default.
- W4290189491 creator A5003882493 @default.
- W4290189491 date "2022-07-30" @default.
- W4290189491 modified "2023-09-25" @default.
- W4290189491 title "Ear semantic segmentation in natural images with Tversky loss function supported DeepLabv3+ convolutional neural network" @default.
- W4290189491 cites W2018953191 @default.
- W4290189491 cites W2062690810 @default.
- W4290189491 cites W2108598243 @default.
- W4290189491 cites W2154559504 @default.
- W4290189491 cites W2194775991 @default.
- W4290189491 cites W2340897893 @default.
- W4290189491 cites W2551082533 @default.
- W4290189491 cites W2561196672 @default.
- W4290189491 cites W2563705555 @default.
- W4290189491 cites W2607432142 @default.
- W4290189491 cites W2726523436 @default.
- W4290189491 cites W2737258237 @default.
- W4290189491 cites W2792583777 @default.
- W4290189491 cites W2804860796 @default.
- W4290189491 cites W2888744770 @default.
- W4290189491 cites W2903961886 @default.
- W4290189491 cites W2912327653 @default.
- W4290189491 cites W2915175583 @default.
- W4290189491 cites W2924485953 @default.
- W4290189491 cites W2941193406 @default.
- W4290189491 cites W2959069256 @default.
- W4290189491 cites W2959696114 @default.
- W4290189491 cites W2963049950 @default.
- W4290189491 cites W2963136578 @default.
- W4290189491 cites W2964309882 @default.
- W4290189491 cites W2981689412 @default.
- W4290189491 cites W2999219213 @default.
- W4290189491 cites W3006425815 @default.
- W4290189491 cites W3102049645 @default.
- W4290189491 cites W3134909192 @default.
- W4290189491 cites W3210185901 @default.
- W4290189491 doi "https://doi.org/10.17694/bajece.1024073" @default.
- W4290189491 hasPublicationYear "2022" @default.
- W4290189491 type Work @default.
- W4290189491 citedByCount "0" @default.
- W4290189491 crossrefType "journal-article" @default.
- W4290189491 hasAuthorship W4290189491A5000022616 @default.
- W4290189491 hasAuthorship W4290189491A5003882493 @default.
- W4290189491 hasBestOaLocation W42901894911 @default.
- W4290189491 hasConcept C124504099 @default.
- W4290189491 hasConcept C153180895 @default.
- W4290189491 hasConcept C154945302 @default.
- W4290189491 hasConcept C169903167 @default.
- W4290189491 hasConcept C177264268 @default.
- W4290189491 hasConcept C199360897 @default.
- W4290189491 hasConcept C41008148 @default.
- W4290189491 hasConcept C50644808 @default.
- W4290189491 hasConcept C81363708 @default.
- W4290189491 hasConcept C89600930 @default.
- W4290189491 hasConceptScore W4290189491C124504099 @default.
- W4290189491 hasConceptScore W4290189491C153180895 @default.
- W4290189491 hasConceptScore W4290189491C154945302 @default.
- W4290189491 hasConceptScore W4290189491C169903167 @default.
- W4290189491 hasConceptScore W4290189491C177264268 @default.
- W4290189491 hasConceptScore W4290189491C199360897 @default.
- W4290189491 hasConceptScore W4290189491C41008148 @default.
- W4290189491 hasConceptScore W4290189491C50644808 @default.
- W4290189491 hasConceptScore W4290189491C81363708 @default.
- W4290189491 hasConceptScore W4290189491C89600930 @default.
- W4290189491 hasIssue "3" @default.
- W4290189491 hasLocation W42901894911 @default.
- W4290189491 hasOpenAccess W4290189491 @default.
- W4290189491 hasPrimaryLocation W42901894911 @default.
- W4290189491 hasRelatedWork W134976887 @default.
- W4290189491 hasRelatedWork W2138214894 @default.
- W4290189491 hasRelatedWork W2549765251 @default.
- W4290189491 hasRelatedWork W2767651786 @default.
- W4290189491 hasRelatedWork W2912288872 @default.
- W4290189491 hasRelatedWork W3027394838 @default.
- W4290189491 hasRelatedWork W3094130944 @default.
- W4290189491 hasRelatedWork W3161321444 @default.
- W4290189491 hasRelatedWork W4200528772 @default.
- W4290189491 hasRelatedWork W564581980 @default.
- W4290189491 hasVolume "10" @default.
- W4290189491 isParatext "false" @default.
- W4290189491 isRetracted "false" @default.
- W4290189491 workType "article" @default.