Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285241648> ?p ?o ?g. }
- W4285241648 endingPage "8803" @default.
- W4285241648 startingPage "8786" @default.
- W4285241648 abstract "The automatic surface defect detection system supports the real-time surface defect detection by reducing the information and high-lighting the critical defect regions for high level image under-standing. However, the defects exhibit low contrast, different textures and geometric structures, and several defects making the surface defect detection more difficult. In this paper, a pixel-wise detection framework based on convolutional neural network (CNN) for strip steel surface defect detection is proposed. First we extract the salient features by a pre-trained backbone network. Secondly, contextual weighting module, with different convolutional kernels, is used to extract multi-scale context features to achieve overall defect perception. Finally, the cross integrate is employed to make the full use of these context information and decoded the information to realize feature information complementation. The experimental results of this study demonstrate that the proposed method outperforms against the previous state-of-the-art methods on strip steel surface defect dataset (MAE: 0.0396; Fβ: 0.8485)." @default.
- W4285241648 created "2022-07-14" @default.
- W4285241648 creator A5022009397 @default.
- W4285241648 date "2022-01-01" @default.
- W4285241648 modified "2023-10-01" @default.
- W4285241648 title "A pixel-wise framework based on convolutional neural network for surface defect detection" @default.
- W4285241648 cites W1580389772 @default.
- W4285241648 cites W1745334888 @default.
- W4285241648 cites W1901129140 @default.
- W4285241648 cites W1903029394 @default.
- W4285241648 cites W1982075130 @default.
- W4285241648 cites W1986306729 @default.
- W4285241648 cites W2023657522 @default.
- W4285241648 cites W2027870374 @default.
- W4285241648 cites W2037654606 @default.
- W4285241648 cites W2055715616 @default.
- W4285241648 cites W2064014153 @default.
- W4285241648 cites W2092072518 @default.
- W4285241648 cites W2100470808 @default.
- W4285241648 cites W2100690466 @default.
- W4285241648 cites W2113101204 @default.
- W4285241648 cites W2128100226 @default.
- W4285241648 cites W2132083787 @default.
- W4285241648 cites W2145456339 @default.
- W4285241648 cites W2196029350 @default.
- W4285241648 cites W2346506533 @default.
- W4285241648 cites W2402144811 @default.
- W4285241648 cites W2461475918 @default.
- W4285241648 cites W2523922765 @default.
- W4285241648 cites W2539264956 @default.
- W4285241648 cites W2560311620 @default.
- W4285241648 cites W2569272946 @default.
- W4285241648 cites W2588600710 @default.
- W4285241648 cites W2589306531 @default.
- W4285241648 cites W2612454721 @default.
- W4285241648 cites W2618530766 @default.
- W4285241648 cites W2626543860 @default.
- W4285241648 cites W2737075200 @default.
- W4285241648 cites W2763152181 @default.
- W4285241648 cites W2766108561 @default.
- W4285241648 cites W2766997090 @default.
- W4285241648 cites W2769856093 @default.
- W4285241648 cites W2783300979 @default.
- W4285241648 cites W2793624836 @default.
- W4285241648 cites W2905416267 @default.
- W4285241648 cites W2907868778 @default.
- W4285241648 cites W2944303778 @default.
- W4285241648 cites W2945270739 @default.
- W4285241648 cites W2953868242 @default.
- W4285241648 cites W2994615081 @default.
- W4285241648 cites W2995986020 @default.
- W4285241648 cites W3000247513 @default.
- W4285241648 cites W3035487542 @default.
- W4285241648 cites W3163646131 @default.
- W4285241648 cites W3167001621 @default.
- W4285241648 cites W3210144980 @default.
- W4285241648 cites W4239147634 @default.
- W4285241648 cites W4247694365 @default.
- W4285241648 doi "https://doi.org/10.3934/mbe.2022408" @default.
- W4285241648 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35942736" @default.
- W4285241648 hasPublicationYear "2022" @default.
- W4285241648 type Work @default.
- W4285241648 citedByCount "1" @default.
- W4285241648 countsByYear W42852416482023 @default.
- W4285241648 crossrefType "journal-article" @default.
- W4285241648 hasAuthorship W4285241648A5022009397 @default.
- W4285241648 hasBestOaLocation W42852416481 @default.
- W4285241648 hasConcept C126838900 @default.
- W4285241648 hasConcept C138885662 @default.
- W4285241648 hasConcept C151730666 @default.
- W4285241648 hasConcept C153180895 @default.
- W4285241648 hasConcept C154945302 @default.
- W4285241648 hasConcept C160633673 @default.
- W4285241648 hasConcept C183115368 @default.
- W4285241648 hasConcept C2524010 @default.
- W4285241648 hasConcept C2776401178 @default.
- W4285241648 hasConcept C2776799497 @default.
- W4285241648 hasConcept C2779343474 @default.
- W4285241648 hasConcept C31972630 @default.
- W4285241648 hasConcept C33923547 @default.
- W4285241648 hasConcept C41008148 @default.
- W4285241648 hasConcept C41895202 @default.
- W4285241648 hasConcept C71924100 @default.
- W4285241648 hasConcept C81363708 @default.
- W4285241648 hasConcept C86803240 @default.
- W4285241648 hasConceptScore W4285241648C126838900 @default.
- W4285241648 hasConceptScore W4285241648C138885662 @default.
- W4285241648 hasConceptScore W4285241648C151730666 @default.
- W4285241648 hasConceptScore W4285241648C153180895 @default.
- W4285241648 hasConceptScore W4285241648C154945302 @default.
- W4285241648 hasConceptScore W4285241648C160633673 @default.
- W4285241648 hasConceptScore W4285241648C183115368 @default.
- W4285241648 hasConceptScore W4285241648C2524010 @default.
- W4285241648 hasConceptScore W4285241648C2776401178 @default.
- W4285241648 hasConceptScore W4285241648C2776799497 @default.
- W4285241648 hasConceptScore W4285241648C2779343474 @default.
- W4285241648 hasConceptScore W4285241648C31972630 @default.
- W4285241648 hasConceptScore W4285241648C33923547 @default.