Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119154513> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3119154513 endingPage "12920" @default.
- W3119154513 startingPage "12912" @default.
- W3119154513 abstract "X-ray imaging has been broadly adopted as a nondestructive testing method for product quality inspection. Deep learning has demonstrated powerful image scene understanding capabilities. In this article, U-Net with resnet101 is taken as the baseline for defect segmentation. First, there exist gray inhomogeneous and low-contrast regions in X-ray images, which can hardly be segmented. Contrast-limited adaptive histogram equalization (CLAHE) could be used to improve the contrast and consistency of the X-ray image. A two-stream convolutional neural network (CNN) is proposed that takes the original image and CLAHE processed image as inputs to address this issue. And then in CNN, low-level feature maps are lacking semantic information, which may lead to worse results. A gated multilayer fusion module is proposed to adaptively fuse the high-level features into low-level features. Furthermore, loss functions (such as cross entropy) in semantic segmentation are usually pixel level, ignoring the regional information. A weighted intersection over union (IOU) loss function is proposed to introduce IOU information to guide the model to focus on the objects that are easy to mine. The experimental results prove that the three proposed methods have better performance than the baseline for our dataset, achieving 42.2 in mIoU, 59.2 in Dice, and 54.5%, 74.9%, and 86.3% in small, middle, and large object recall rate, respectively." @default.
- W3119154513 created "2021-01-18" @default.
- W3119154513 creator A5014808269 @default.
- W3119154513 creator A5028546359 @default.
- W3119154513 creator A5050986537 @default.
- W3119154513 date "2021-12-01" @default.
- W3119154513 modified "2023-10-16" @default.
- W3119154513 title "Automatic Defect Segmentation in X-Ray Images Based on Deep Learning" @default.
- W3119154513 cites W1665445158 @default.
- W3119154513 cites W1903029394 @default.
- W3119154513 cites W2001412060 @default.
- W3119154513 cites W2004695321 @default.
- W3119154513 cites W2051359111 @default.
- W3119154513 cites W2061446052 @default.
- W3119154513 cites W2100690466 @default.
- W3119154513 cites W2108598243 @default.
- W3119154513 cites W2511554009 @default.
- W3119154513 cites W2521720065 @default.
- W3119154513 cites W2560023338 @default.
- W3119154513 cites W2884436604 @default.
- W3119154513 cites W2894496171 @default.
- W3119154513 cites W2905203854 @default.
- W3119154513 cites W2928133111 @default.
- W3119154513 cites W2957908269 @default.
- W3119154513 cites W2962914239 @default.
- W3119154513 cites W2963351448 @default.
- W3119154513 cites W2963466857 @default.
- W3119154513 cites W2963698633 @default.
- W3119154513 cites W2964027659 @default.
- W3119154513 cites W2996788668 @default.
- W3119154513 cites W3013798510 @default.
- W3119154513 cites W3025211569 @default.
- W3119154513 doi "https://doi.org/10.1109/tie.2020.3047060" @default.
- W3119154513 hasPublicationYear "2021" @default.
- W3119154513 type Work @default.
- W3119154513 sameAs 3119154513 @default.
- W3119154513 citedByCount "14" @default.
- W3119154513 countsByYear W31191545132022 @default.
- W3119154513 countsByYear W31191545132023 @default.
- W3119154513 crossrefType "journal-article" @default.
- W3119154513 hasAuthorship W3119154513A5014808269 @default.
- W3119154513 hasAuthorship W3119154513A5028546359 @default.
- W3119154513 hasAuthorship W3119154513A5050986537 @default.
- W3119154513 hasConcept C108583219 @default.
- W3119154513 hasConcept C115961682 @default.
- W3119154513 hasConcept C124504099 @default.
- W3119154513 hasConcept C136943445 @default.
- W3119154513 hasConcept C138885662 @default.
- W3119154513 hasConcept C153180895 @default.
- W3119154513 hasConcept C154945302 @default.
- W3119154513 hasConcept C2776401178 @default.
- W3119154513 hasConcept C2776502983 @default.
- W3119154513 hasConcept C30387639 @default.
- W3119154513 hasConcept C31972630 @default.
- W3119154513 hasConcept C41008148 @default.
- W3119154513 hasConcept C41895202 @default.
- W3119154513 hasConcept C53533937 @default.
- W3119154513 hasConcept C81363708 @default.
- W3119154513 hasConcept C89600930 @default.
- W3119154513 hasConceptScore W3119154513C108583219 @default.
- W3119154513 hasConceptScore W3119154513C115961682 @default.
- W3119154513 hasConceptScore W3119154513C124504099 @default.
- W3119154513 hasConceptScore W3119154513C136943445 @default.
- W3119154513 hasConceptScore W3119154513C138885662 @default.
- W3119154513 hasConceptScore W3119154513C153180895 @default.
- W3119154513 hasConceptScore W3119154513C154945302 @default.
- W3119154513 hasConceptScore W3119154513C2776401178 @default.
- W3119154513 hasConceptScore W3119154513C2776502983 @default.
- W3119154513 hasConceptScore W3119154513C30387639 @default.
- W3119154513 hasConceptScore W3119154513C31972630 @default.
- W3119154513 hasConceptScore W3119154513C41008148 @default.
- W3119154513 hasConceptScore W3119154513C41895202 @default.
- W3119154513 hasConceptScore W3119154513C53533937 @default.
- W3119154513 hasConceptScore W3119154513C81363708 @default.
- W3119154513 hasConceptScore W3119154513C89600930 @default.
- W3119154513 hasFunder F4320321001 @default.
- W3119154513 hasFunder F4320335787 @default.
- W3119154513 hasIssue "12" @default.
- W3119154513 hasLocation W31191545131 @default.
- W3119154513 hasOpenAccess W3119154513 @default.
- W3119154513 hasPrimaryLocation W31191545131 @default.
- W3119154513 hasRelatedWork W1669643531 @default.
- W3119154513 hasRelatedWork W2122581818 @default.
- W3119154513 hasRelatedWork W2738221750 @default.
- W3119154513 hasRelatedWork W2948658236 @default.
- W3119154513 hasRelatedWork W2971526870 @default.
- W3119154513 hasRelatedWork W3102253946 @default.
- W3119154513 hasRelatedWork W3144574764 @default.
- W3119154513 hasRelatedWork W3156786002 @default.
- W3119154513 hasRelatedWork W4226289457 @default.
- W3119154513 hasRelatedWork W4293211451 @default.
- W3119154513 hasVolume "68" @default.
- W3119154513 isParatext "false" @default.
- W3119154513 isRetracted "false" @default.
- W3119154513 magId "3119154513" @default.
- W3119154513 workType "article" @default.