Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175012015> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3175012015 endingPage "108897" @default.
- W3175012015 startingPage "108897" @default.
- W3175012015 abstract "In this work we propose a novel and fully automated method for extracting the yarn geometrical features in woven composites so that a direct parametrization of the textile reinforcement is achieved ( e.g. , FE mesh). Thus, our aim is not only to perform yarn segmentation from tomographic images but rather to provide a complete descriptive modeling of the fabric. As such, this direct approach improves on previous methods that use voxel-wise masks as intermediate representations followed by re-meshing operations (yarn envelope estimation). The proposed approach employs two deep neural network architectures (U-Net and Mask R-CNN). First, we train the U-Net to generate synthetic CT images from the corresponding FE simulations. This allows to generate large quantities of annotated data without requiring costly manual annotations. This data is then used to train the Mask R-CNN, which is focused on predicting contour points around each of the yarns in the image. Experimental results show that our method is accurate and robust for performing yarn instance segmentation on CT images, this is further validated by quantitative and qualitative analyses." @default.
- W3175012015 created "2021-07-05" @default.
- W3175012015 creator A5010392645 @default.
- W3175012015 creator A5049143430 @default.
- W3175012015 creator A5068419029 @default.
- W3175012015 date "2021-09-01" @default.
- W3175012015 modified "2023-10-04" @default.
- W3175012015 title "Descriptive modeling of textiles using FE simulations and deep learning" @default.
- W3175012015 cites W1277574275 @default.
- W3175012015 cites W1969087886 @default.
- W3175012015 cites W1971446388 @default.
- W3175012015 cites W2004001057 @default.
- W3175012015 cites W2007176968 @default.
- W3175012015 cites W2012496982 @default.
- W3175012015 cites W2030950131 @default.
- W3175012015 cites W2032094625 @default.
- W3175012015 cites W2033078482 @default.
- W3175012015 cites W2053630853 @default.
- W3175012015 cites W2060423425 @default.
- W3175012015 cites W2069110348 @default.
- W3175012015 cites W2088773918 @default.
- W3175012015 cites W2098386335 @default.
- W3175012015 cites W2117539524 @default.
- W3175012015 cites W2136645680 @default.
- W3175012015 cites W2695475716 @default.
- W3175012015 cites W2736753887 @default.
- W3175012015 cites W2952585635 @default.
- W3175012015 cites W2964764269 @default.
- W3175012015 cites W2973495422 @default.
- W3175012015 cites W2975143270 @default.
- W3175012015 cites W3005486845 @default.
- W3175012015 cites W3008710022 @default.
- W3175012015 cites W3010892243 @default.
- W3175012015 cites W3025847162 @default.
- W3175012015 cites W3084645800 @default.
- W3175012015 cites W3090930540 @default.
- W3175012015 cites W3128677848 @default.
- W3175012015 doi "https://doi.org/10.1016/j.compscitech.2021.108897" @default.
- W3175012015 hasPublicationYear "2021" @default.
- W3175012015 type Work @default.
- W3175012015 sameAs 3175012015 @default.
- W3175012015 citedByCount "21" @default.
- W3175012015 countsByYear W31750120152022 @default.
- W3175012015 countsByYear W31750120152023 @default.
- W3175012015 crossrefType "journal-article" @default.
- W3175012015 hasAuthorship W3175012015A5010392645 @default.
- W3175012015 hasAuthorship W3175012015A5049143430 @default.
- W3175012015 hasAuthorship W3175012015A5068419029 @default.
- W3175012015 hasBestOaLocation W31750120152 @default.
- W3175012015 hasConcept C159985019 @default.
- W3175012015 hasConcept C192562407 @default.
- W3175012015 hasConceptScore W3175012015C159985019 @default.
- W3175012015 hasConceptScore W3175012015C192562407 @default.
- W3175012015 hasLocation W31750120151 @default.
- W3175012015 hasLocation W31750120152 @default.
- W3175012015 hasOpenAccess W3175012015 @default.
- W3175012015 hasPrimaryLocation W31750120151 @default.
- W3175012015 hasRelatedWork W1994103032 @default.
- W3175012015 hasRelatedWork W2011052271 @default.
- W3175012015 hasRelatedWork W2051270029 @default.
- W3175012015 hasRelatedWork W2082293200 @default.
- W3175012015 hasRelatedWork W2137307547 @default.
- W3175012015 hasRelatedWork W2366754381 @default.
- W3175012015 hasRelatedWork W2380293314 @default.
- W3175012015 hasRelatedWork W2943188944 @default.
- W3175012015 hasRelatedWork W4285802202 @default.
- W3175012015 hasRelatedWork W4317433637 @default.
- W3175012015 hasVolume "213" @default.
- W3175012015 isParatext "false" @default.
- W3175012015 isRetracted "false" @default.
- W3175012015 magId "3175012015" @default.
- W3175012015 workType "article" @default.