Matches in SemOpenAlex for { <https://semopenalex.org/work/W2917609910> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2917609910 endingPage "374" @default.
- W2917609910 startingPage "363" @default.
- W2917609910 abstract "In this paper, we propose a convolutional neural network (CNN) based method that inspects non-patterned welding defects (craters, pores, foreign substances and fissures) on the surface of the engine transmission using a single RGB camera. The proposed method consists of two steps: first, extracting the welding area to be inspected from the captured image, and then determining whether the extracted area includes defects. In the first step, to extract the welding area from the captured image, a CNN based approach is proposed to detect a center of the engine transmission in the image. In the second stage, the extracted area is identified by another CNN as defective or non-defective. To train the second stage CNN stably, we propose a class-specific batch sampling method. With our sampling method, biased learning caused by data imbalance (number of collected defective images is much less than that of non-defective images) is effectively prevented. We evaluated our system with a large amount of samples (about 32,000 images) collected manually from the production line, and our system shows a remarkable performance in all experiments." @default.
- W2917609910 created "2019-03-02" @default.
- W2917609910 creator A5038741705 @default.
- W2917609910 creator A5052445060 @default.
- W2917609910 creator A5085397062 @default.
- W2917609910 date "2019-02-22" @default.
- W2917609910 modified "2023-09-29" @default.
- W2917609910 title "Convolutional Neural Network Based Surface Inspection System for Non-patterned Welding Defects" @default.
- W2917609910 cites W1588043677 @default.
- W2917609910 cites W1963970230 @default.
- W2917609910 cites W1981759979 @default.
- W2917609910 cites W1985345361 @default.
- W2917609910 cites W2016142907 @default.
- W2917609910 cites W2034856412 @default.
- W2917609910 cites W2048692651 @default.
- W2917609910 cites W2055575018 @default.
- W2917609910 cites W2069853858 @default.
- W2917609910 cites W2125629257 @default.
- W2917609910 cites W2178525996 @default.
- W2917609910 cites W2289500379 @default.
- W2917609910 cites W234388709 @default.
- W2917609910 cites W2468676150 @default.
- W2917609910 cites W2555875178 @default.
- W2917609910 cites W2623496481 @default.
- W2917609910 cites W2767244425 @default.
- W2917609910 cites W2775465287 @default.
- W2917609910 cites W2776320244 @default.
- W2917609910 cites W2806489440 @default.
- W2917609910 doi "https://doi.org/10.1007/s12541-019-00074-4" @default.
- W2917609910 hasPublicationYear "2019" @default.
- W2917609910 type Work @default.
- W2917609910 sameAs 2917609910 @default.
- W2917609910 citedByCount "37" @default.
- W2917609910 countsByYear W29176099102019 @default.
- W2917609910 countsByYear W29176099102020 @default.
- W2917609910 countsByYear W29176099102021 @default.
- W2917609910 countsByYear W29176099102022 @default.
- W2917609910 countsByYear W29176099102023 @default.
- W2917609910 crossrefType "journal-article" @default.
- W2917609910 hasAuthorship W2917609910A5038741705 @default.
- W2917609910 hasAuthorship W2917609910A5052445060 @default.
- W2917609910 hasAuthorship W2917609910A5085397062 @default.
- W2917609910 hasBestOaLocation W29176099101 @default.
- W2917609910 hasConcept C115961682 @default.
- W2917609910 hasConcept C127413603 @default.
- W2917609910 hasConcept C153180895 @default.
- W2917609910 hasConcept C154945302 @default.
- W2917609910 hasConcept C19474535 @default.
- W2917609910 hasConcept C31972630 @default.
- W2917609910 hasConcept C41008148 @default.
- W2917609910 hasConcept C50644808 @default.
- W2917609910 hasConcept C761482 @default.
- W2917609910 hasConcept C76155785 @default.
- W2917609910 hasConcept C78519656 @default.
- W2917609910 hasConcept C81363708 @default.
- W2917609910 hasConcept C82990744 @default.
- W2917609910 hasConceptScore W2917609910C115961682 @default.
- W2917609910 hasConceptScore W2917609910C127413603 @default.
- W2917609910 hasConceptScore W2917609910C153180895 @default.
- W2917609910 hasConceptScore W2917609910C154945302 @default.
- W2917609910 hasConceptScore W2917609910C19474535 @default.
- W2917609910 hasConceptScore W2917609910C31972630 @default.
- W2917609910 hasConceptScore W2917609910C41008148 @default.
- W2917609910 hasConceptScore W2917609910C50644808 @default.
- W2917609910 hasConceptScore W2917609910C761482 @default.
- W2917609910 hasConceptScore W2917609910C76155785 @default.
- W2917609910 hasConceptScore W2917609910C78519656 @default.
- W2917609910 hasConceptScore W2917609910C81363708 @default.
- W2917609910 hasConceptScore W2917609910C82990744 @default.
- W2917609910 hasFunder F4320322065 @default.
- W2917609910 hasFunder F4320322120 @default.
- W2917609910 hasIssue "3" @default.
- W2917609910 hasLocation W29176099101 @default.
- W2917609910 hasOpenAccess W2917609910 @default.
- W2917609910 hasPrimaryLocation W29176099101 @default.
- W2917609910 hasRelatedWork W2052518016 @default.
- W2917609910 hasRelatedWork W2085956791 @default.
- W2917609910 hasRelatedWork W2283162247 @default.
- W2917609910 hasRelatedWork W2313698153 @default.
- W2917609910 hasRelatedWork W2314488738 @default.
- W2917609910 hasRelatedWork W2524507886 @default.
- W2917609910 hasRelatedWork W2774550181 @default.
- W2917609910 hasRelatedWork W2810384904 @default.
- W2917609910 hasRelatedWork W2940661641 @default.
- W2917609910 hasRelatedWork W4212983513 @default.
- W2917609910 hasVolume "20" @default.
- W2917609910 isParatext "false" @default.
- W2917609910 isRetracted "false" @default.
- W2917609910 magId "2917609910" @default.
- W2917609910 workType "article" @default.