Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204715933> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3204715933 endingPage "107913" @default.
- W3204715933 startingPage "107913" @default.
- W3204715933 abstract "In this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five main steps: preprocessing, automatic pattern period extraction, patch extraction, features selection and anomaly detection. This proposed approach uses a new dynamic and heuristic method for feature selection which avoids the drawbacks of initialization of the number of filters (neurons) and their weights, and those of the backpropagation mechanism such as the vanishing gradients, which are common practice in the state-of-the-art methods. The design and training of the network are performed in a dynamic and input domain-based manner and, thus, no ad-hoc configurations are required. Before building the model, only the number of layers and the stride are defined. We do not initialize the weights randomly nor do we define the filter size or number of filters as conventionally done in CNN-based approaches. This reduces effort and time spent on hyper-parameter initialization and fine-tuning. Only one defect-free sample is required for training and no further labeled data is needed. The trained network is then used to detect anomalies on defective fabric samples. We demonstrate the effectiveness of our approach on the Patterned Fabrics benchmark dataset. Our algorithm yields reliable and competitive results (on recall, precision, accuracy and f1-measure) compared to state-of-the-art unsupervised approaches, in less time, with efficient training in a single epoch and a lower computational cost." @default.
- W3204715933 created "2021-10-11" @default.
- W3204715933 creator A5031852822 @default.
- W3204715933 creator A5055519712 @default.
- W3204715933 date "2021-12-01" @default.
- W3204715933 modified "2023-09-30" @default.
- W3204715933 title "Unsupervised textile defect detection using convolutional neural networks" @default.
- W3204715933 cites W1884984464 @default.
- W3204715933 cites W1975920834 @default.
- W3204715933 cites W1995589954 @default.
- W3204715933 cites W2018435387 @default.
- W3204715933 cites W2019654077 @default.
- W3204715933 cites W2031821661 @default.
- W3204715933 cites W2034856412 @default.
- W3204715933 cites W2070407351 @default.
- W3204715933 cites W2082233783 @default.
- W3204715933 cites W2116090201 @default.
- W3204715933 cites W2141358266 @default.
- W3204715933 cites W2233312350 @default.
- W3204715933 cites W2329706158 @default.
- W3204715933 cites W2344428106 @default.
- W3204715933 cites W2733078087 @default.
- W3204715933 cites W2795647708 @default.
- W3204715933 cites W2898089303 @default.
- W3204715933 cites W2900936384 @default.
- W3204715933 cites W2902856291 @default.
- W3204715933 cites W2921163360 @default.
- W3204715933 cites W2963881378 @default.
- W3204715933 cites W2981845603 @default.
- W3204715933 cites W3024972578 @default.
- W3204715933 doi "https://doi.org/10.1016/j.asoc.2021.107913" @default.
- W3204715933 hasPublicationYear "2021" @default.
- W3204715933 type Work @default.
- W3204715933 sameAs 3204715933 @default.
- W3204715933 citedByCount "4" @default.
- W3204715933 countsByYear W32047159332022 @default.
- W3204715933 countsByYear W32047159332023 @default.
- W3204715933 crossrefType "journal-article" @default.
- W3204715933 hasAuthorship W3204715933A5031852822 @default.
- W3204715933 hasAuthorship W3204715933A5055519712 @default.
- W3204715933 hasConcept C111919701 @default.
- W3204715933 hasConcept C114466953 @default.
- W3204715933 hasConcept C119857082 @default.
- W3204715933 hasConcept C13280743 @default.
- W3204715933 hasConcept C153180895 @default.
- W3204715933 hasConcept C154945302 @default.
- W3204715933 hasConcept C173801870 @default.
- W3204715933 hasConcept C185798385 @default.
- W3204715933 hasConcept C199360897 @default.
- W3204715933 hasConcept C205649164 @default.
- W3204715933 hasConcept C34736171 @default.
- W3204715933 hasConcept C41008148 @default.
- W3204715933 hasConcept C50644808 @default.
- W3204715933 hasConcept C52622490 @default.
- W3204715933 hasConcept C739882 @default.
- W3204715933 hasConcept C74912251 @default.
- W3204715933 hasConcept C8038995 @default.
- W3204715933 hasConcept C81363708 @default.
- W3204715933 hasConceptScore W3204715933C111919701 @default.
- W3204715933 hasConceptScore W3204715933C114466953 @default.
- W3204715933 hasConceptScore W3204715933C119857082 @default.
- W3204715933 hasConceptScore W3204715933C13280743 @default.
- W3204715933 hasConceptScore W3204715933C153180895 @default.
- W3204715933 hasConceptScore W3204715933C154945302 @default.
- W3204715933 hasConceptScore W3204715933C173801870 @default.
- W3204715933 hasConceptScore W3204715933C185798385 @default.
- W3204715933 hasConceptScore W3204715933C199360897 @default.
- W3204715933 hasConceptScore W3204715933C205649164 @default.
- W3204715933 hasConceptScore W3204715933C34736171 @default.
- W3204715933 hasConceptScore W3204715933C41008148 @default.
- W3204715933 hasConceptScore W3204715933C50644808 @default.
- W3204715933 hasConceptScore W3204715933C52622490 @default.
- W3204715933 hasConceptScore W3204715933C739882 @default.
- W3204715933 hasConceptScore W3204715933C74912251 @default.
- W3204715933 hasConceptScore W3204715933C8038995 @default.
- W3204715933 hasConceptScore W3204715933C81363708 @default.
- W3204715933 hasLocation W32047159331 @default.
- W3204715933 hasOpenAccess W3204715933 @default.
- W3204715933 hasPrimaryLocation W32047159331 @default.
- W3204715933 hasRelatedWork W2076520961 @default.
- W3204715933 hasRelatedWork W2126100045 @default.
- W3204715933 hasRelatedWork W2146076056 @default.
- W3204715933 hasRelatedWork W2391959412 @default.
- W3204715933 hasRelatedWork W2592385986 @default.
- W3204715933 hasRelatedWork W2811390910 @default.
- W3204715933 hasRelatedWork W2913302899 @default.
- W3204715933 hasRelatedWork W3196155444 @default.
- W3204715933 hasRelatedWork W4287776258 @default.
- W3204715933 hasRelatedWork W4312376745 @default.
- W3204715933 hasVolume "113" @default.
- W3204715933 isParatext "false" @default.
- W3204715933 isRetracted "false" @default.
- W3204715933 magId "3204715933" @default.
- W3204715933 workType "article" @default.