FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3148767009> ?p ?o ?g. }

• W3148767009 endingPage "3155" @default.
• W3148767009 startingPage "3155" @default.
• W3148767009 abstract "In this paper, an efficient instance segmentation scheme based on deep convolutional neural networks is proposed to deal with unconstrained psoriasis images for computer-aided diagnosis. To achieve instance segmentation, the You Only Look At CoefficienTs (YOLACT) network composed of backbone, feature pyramid network (FPN), Protonet, and prediction head is used to deal with psoriasis images. The backbone network is used to extract feature maps from an image, and FPN is designed to generate multiscale feature maps for effectively classifying and localizing objects with multiple sizes. The prediction head is used to predict the classification information, bounding box information, and mask coefficients of objects. Some prototypes generated by Protonet are combined with mask coefficients to estimate the pixel-level shapes for objects. To achieve instance segmentation for unconstrained psoriasis images, YOLACT++ with a pretrained model is retrained via transfer learning. To evaluate the performance of the proposed scheme, unconstrained psoriasis images with different severity levels are collected for testing. As for subjective testing, the psoriasis regions and normal skin areas can be located and classified well. The four performance indices of the proposed scheme were higher than 93% after cross validation. About object localization, the Mean Average Precision (mAP) rates of the proposed scheme were at least 85.9% after cross validation. As for efficiency, the frames per second (FPS) rate of the proposed scheme reached up to 15. In addition, the F1_score and the execution speed of the proposed scheme were higher than those of the Mask Region-Based Convolutional Neural Networks (R-CNN)-based method. These results show that the proposed scheme based on YOLACT++ can not only detect psoriasis regions but also distinguish psoriasis pixels from background and normal skin pixels well. Furthermore, the proposed instance segmentation scheme outperforms the Mask R-CNN-based method for unconstrained psoriasis images." @default.
• W3148767009 created "2021-04-13" @default.
• W3148767009 creator A5001671313 @default.
• W3148767009 creator A5008974452 @default.
• W3148767009 creator A5023487478 @default.
• W3148767009 creator A5030271774 @default.
• W3148767009 creator A5043010515 @default.
• W3148767009 date "2021-04-01" @default.
• W3148767009 modified "2023-09-26" @default.
• W3148767009 title "Instance Segmentation Based on Deep Convolutional Neural Networks and Transfer Learning for Unconstrained Psoriasis Skin Images" @default.
• W3148767009 cites W1778864350 @default.
• W3148767009 cites W1986927962 @default.
• W3148767009 cites W2011990745 @default.
• W3148767009 cites W2041748931 @default.
• W3148767009 cites W2045850347 @default.
• W3148767009 cites W2088339116 @default.
• W3148767009 cites W2154785460 @default.
• W3148767009 cites W2165698076 @default.
• W3148767009 cites W2168113750 @default.
• W3148767009 cites W2277070532 @default.
• W3148767009 cites W2947263797 @default.
• W3148767009 cites W2954996726 @default.
• W3148767009 cites W2978457402 @default.
• W3148767009 cites W3012291630 @default.
• W3148767009 cites W3031443669 @default.
• W3148767009 cites W3035647949 @default.
• W3148767009 cites W3048334363 @default.
• W3148767009 cites W3101612813 @default.
• W3148767009 cites W4211264657 @default.
• W3148767009 doi "https://doi.org/10.3390/app11073155" @default.
• W3148767009 hasPublicationYear "2021" @default.
• W3148767009 type Work @default.
• W3148767009 sameAs 3148767009 @default.
• W3148767009 citedByCount "3" @default.
• W3148767009 countsByYear W31487670092021 @default.
• W3148767009 countsByYear W31487670092022 @default.
• W3148767009 crossrefType "journal-article" @default.
• W3148767009 hasAuthorship W3148767009A5001671313 @default.
• W3148767009 hasAuthorship W3148767009A5008974452 @default.
• W3148767009 hasAuthorship W3148767009A5023487478 @default.
• W3148767009 hasAuthorship W3148767009A5030271774 @default.
• W3148767009 hasAuthorship W3148767009A5043010515 @default.
• W3148767009 hasBestOaLocation W31487670091 @default.
• W3148767009 hasConcept C108583219 @default.
• W3148767009 hasConcept C115961682 @default.
• W3148767009 hasConcept C134306372 @default.
• W3148767009 hasConcept C138885662 @default.
• W3148767009 hasConcept C142575187 @default.
• W3148767009 hasConcept C147037132 @default.
• W3148767009 hasConcept C150899416 @default.
• W3148767009 hasConcept C153180895 @default.
• W3148767009 hasConcept C154945302 @default.
• W3148767009 hasConcept C2524010 @default.
• W3148767009 hasConcept C2776401178 @default.
• W3148767009 hasConcept C31972630 @default.
• W3148767009 hasConcept C33923547 @default.
• W3148767009 hasConcept C41008148 @default.
• W3148767009 hasConcept C41895202 @default.
• W3148767009 hasConcept C50644808 @default.
• W3148767009 hasConcept C77618280 @default.
• W3148767009 hasConcept C81363708 @default.
• W3148767009 hasConcept C89600930 @default.
• W3148767009 hasConceptScore W3148767009C108583219 @default.
• W3148767009 hasConceptScore W3148767009C115961682 @default.
• W3148767009 hasConceptScore W3148767009C134306372 @default.
• W3148767009 hasConceptScore W3148767009C138885662 @default.
• W3148767009 hasConceptScore W3148767009C142575187 @default.
• W3148767009 hasConceptScore W3148767009C147037132 @default.
• W3148767009 hasConceptScore W3148767009C150899416 @default.
• W3148767009 hasConceptScore W3148767009C153180895 @default.
• W3148767009 hasConceptScore W3148767009C154945302 @default.
• W3148767009 hasConceptScore W3148767009C2524010 @default.
• W3148767009 hasConceptScore W3148767009C2776401178 @default.
• W3148767009 hasConceptScore W3148767009C31972630 @default.
• W3148767009 hasConceptScore W3148767009C33923547 @default.
• W3148767009 hasConceptScore W3148767009C41008148 @default.
• W3148767009 hasConceptScore W3148767009C41895202 @default.
• W3148767009 hasConceptScore W3148767009C50644808 @default.
• W3148767009 hasConceptScore W3148767009C77618280 @default.
• W3148767009 hasConceptScore W3148767009C81363708 @default.
• W3148767009 hasConceptScore W3148767009C89600930 @default.
• W3148767009 hasIssue "7" @default.
• W3148767009 hasLocation W31487670091 @default.
• W3148767009 hasOpenAccess W3148767009 @default.
• W3148767009 hasPrimaryLocation W31487670091 @default.
• W3148767009 hasRelatedWork W2738221750 @default.
• W3148767009 hasRelatedWork W2997709384 @default.
• W3148767009 hasRelatedWork W3018421652 @default.
• W3148767009 hasRelatedWork W3091976719 @default.
• W3148767009 hasRelatedWork W3102253946 @default.
• W3148767009 hasRelatedWork W3166467183 @default.
• W3148767009 hasRelatedWork W3189091156 @default.
• W3148767009 hasRelatedWork W3192840557 @default.
• W3148767009 hasRelatedWork W4293211451 @default.
• W3148767009 hasRelatedWork W4362564549 @default.
• W3148767009 hasVolume "11" @default.
• W3148767009 isParatext "false" @default.
• W3148767009 isRetracted "false" @default.

• next