FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320508716> ?p ?o ?g. }

• W4320508716 endingPage "166" @default.
• W4320508716 startingPage "152" @default.
• W4320508716 abstract "Purpose of research. Corrosion recognition on metal structures is a serious problem in conducting inspections of industrial facilities. Existing approaches to image analysis use all images to recognize areas damaged by corrosion, which is not suitable for structural analysis, since the percentage of errors in this approach is very large. Under conditions of corrosion prediction throughout the image, errors related to predictive mask not on metal structure are possible. Therefore, it is necessary to delete the results of positive class prediction for areas damaged by corrosion but not placed on metal structure. Therefore, in this work, the authors have developed two-step approach for recognizing corrosion of metal structures, thereby achieving the goal of improving recognition accuracy. Methods. We implement two deep learning models focused on Semantic segmentation (DeepLabv3, BiSeNetV2) for corrosion detection that work better in terms of accuracy and time and require fewer annotated samples compared to other deep models, such as Unet, FCN, Mask-RCNN. A new detection approach to metal areas damaged by corrosion, based on the combination of two convolutional neural networks for more accurate pixel prediction by depth architecture models: DeepLabv3 and BiSeNetV2. Results. Experimental studies have calculated the accuracy and F1 measures using FCN, Unet, Mask-RCNN models as well as the proposed approach. Based on obtained results, it was concluded that proposed approach of combining DeepLabv3 and BiSeNetV2 networks increases accuracy and F1 measure for Unet algorithm by 3%, accuracy by 10% and 2% F1 measure for Mask R-CNN and by 12% accuracy and 4% F1 measure for FCN network. Experimental results and comparisons with real data sets confirm the effectiveness of proposed scheme even for very complex images with many different defects. Productivity was assessed based on data annotated by experts. Conclusion. Analyses of existing solutions in the field of recognition of metal structures damaged by corrosion is described. Shortcomings of existing solutions based either on detection of corrosion sites or on pixel segmentation of full image are identified. A new approach to the recognition of metal areas damaged by corrosion based on the combination of two convolutional neural networks for more accurate pixel prediction of DeepLabv3 and BiSeNetV2 is indroduced. Production is evaluated based on data annotated by Precision and F1-score metrics experts." @default.
• W4320508716 created "2023-02-14" @default.
• W4320508716 creator A5006793390 @default.
• W4320508716 creator A5038355248 @default.
• W4320508716 date "2022-01-29" @default.
• W4320508716 modified "2023-09-27" @default.
• W4320508716 title "Two-step Approach to Corrosion Detection of Metal Structures Using Convolutional Neural Networks When Inspecting Industrial Facilities" @default.
• W4320508716 cites W234388709 @default.
• W4320508716 cites W2511065100 @default.
• W4320508716 cites W2531409750 @default.
• W4320508716 cites W2598457882 @default.
• W4320508716 cites W2613456556 @default.
• W4320508716 cites W2744616270 @default.
• W4320508716 cites W2765854388 @default.
• W4320508716 cites W2913029471 @default.
• W4320508716 cites W2944087961 @default.
• W4320508716 cites W2955982164 @default.
• W4320508716 cites W2964309882 @default.
• W4320508716 cites W2966177638 @default.
• W4320508716 cites W2976519442 @default.
• W4320508716 cites W2998297633 @default.
• W4320508716 cites W2998927093 @default.
• W4320508716 cites W3117704695 @default.
• W4320508716 cites W3196904463 @default.
• W4320508716 doi "https://doi.org/10.21869/2223-1560-2021-25-3-152-166" @default.
• W4320508716 hasPublicationYear "2022" @default.
• W4320508716 type Work @default.
• W4320508716 citedByCount "0" @default.
• W4320508716 crossrefType "journal-article" @default.
• W4320508716 hasAuthorship W4320508716A5006793390 @default.
• W4320508716 hasAuthorship W4320508716A5038355248 @default.
• W4320508716 hasBestOaLocation W43205087161 @default.
• W4320508716 hasConcept C108583219 @default.
• W4320508716 hasConcept C119857082 @default.
• W4320508716 hasConcept C124101348 @default.
• W4320508716 hasConcept C153180895 @default.
• W4320508716 hasConcept C154945302 @default.
• W4320508716 hasConcept C160633673 @default.
• W4320508716 hasConcept C191897082 @default.
• W4320508716 hasConcept C192562407 @default.
• W4320508716 hasConcept C20625102 @default.
• W4320508716 hasConcept C2780009758 @default.
• W4320508716 hasConcept C41008148 @default.
• W4320508716 hasConcept C50644808 @default.
• W4320508716 hasConcept C81363708 @default.
• W4320508716 hasConcept C89600930 @default.
• W4320508716 hasConceptScore W4320508716C108583219 @default.
• W4320508716 hasConceptScore W4320508716C119857082 @default.
• W4320508716 hasConceptScore W4320508716C124101348 @default.
• W4320508716 hasConceptScore W4320508716C153180895 @default.
• W4320508716 hasConceptScore W4320508716C154945302 @default.
• W4320508716 hasConceptScore W4320508716C160633673 @default.
• W4320508716 hasConceptScore W4320508716C191897082 @default.
• W4320508716 hasConceptScore W4320508716C192562407 @default.
• W4320508716 hasConceptScore W4320508716C20625102 @default.
• W4320508716 hasConceptScore W4320508716C2780009758 @default.
• W4320508716 hasConceptScore W4320508716C41008148 @default.
• W4320508716 hasConceptScore W4320508716C50644808 @default.
• W4320508716 hasConceptScore W4320508716C81363708 @default.
• W4320508716 hasConceptScore W4320508716C89600930 @default.
• W4320508716 hasIssue "3" @default.
• W4320508716 hasLocation W43205087161 @default.
• W4320508716 hasOpenAccess W4320508716 @default.
• W4320508716 hasPrimaryLocation W43205087161 @default.
• W4320508716 hasRelatedWork W2731899572 @default.
• W4320508716 hasRelatedWork W2790662084 @default.
• W4320508716 hasRelatedWork W2999805992 @default.
• W4320508716 hasRelatedWork W3116150086 @default.
• W4320508716 hasRelatedWork W3133861977 @default.
• W4320508716 hasRelatedWork W4200173597 @default.
• W4320508716 hasRelatedWork W4291897433 @default.
• W4320508716 hasRelatedWork W4312417841 @default.
• W4320508716 hasRelatedWork W4321369474 @default.
• W4320508716 hasRelatedWork W4380075502 @default.
• W4320508716 hasVolume "25" @default.
• W4320508716 isParatext "false" @default.
• W4320508716 isRetracted "false" @default.
• W4320508716 workType "article" @default.