Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385454396> ?p ?o ?g. }
- W4385454396 endingPage "102919" @default.
- W4385454396 startingPage "102919" @default.
- W4385454396 abstract "Radiography testing for weld defect detection is an essential inspection procedure to ensure welding quality. However, detecting these defects is a challenging task because they have various size and aspect ratio characteristics and low perceptiveness due to the low luminance and contrast characteristics of the radiography image (RI). To address these difficulties, this paper proposes a twin model-based automatic welding defect detection method to reveal welding defects of various sizes and aspect ratios more accurately. In addition, we propose a new image adjustment technique that is optimized to improve the accuracy of welding defect detection by adaptively adjusting the luminance and contrast of a given RI. The proposed method consists of three steps: preprocessing for defect detection (PDD), context-aware image adjustment (CIA), and size-aware defect detection (SDD). In the PDD step, we extract the region of interest from a RI based on text detection by removing regions unnecessary for welding defect detection. In the CIA step, we adaptively optimize a given image to improve the detection accuracy by utilizing a differentiable parametric module that performs image enhancement filtering. In the SDD step, we define a twin model that outputs the embeddings of different scales from the adjusted RI to detect the defects with various sizes accurately. At the inference stage of the detection model, we ensemble the results using a weighted fusion of the detection results from the twin model to take advantage of the ensemble strategy. The experimental results indicate that the proposed method achieves outstanding detection accuracy compared to the benchmark methods." @default.
- W4385454396 created "2023-08-02" @default.
- W4385454396 creator A5005821234 @default.
- W4385454396 creator A5011102375 @default.
- W4385454396 creator A5021111709 @default.
- W4385454396 creator A5049172004 @default.
- W4385454396 creator A5080385405 @default.
- W4385454396 date "2023-10-01" @default.
- W4385454396 modified "2023-09-27" @default.
- W4385454396 title "Context and scale-aware YOLO for welding defect detection" @default.
- W4385454396 cites W1536680647 @default.
- W4385454396 cites W1976554299 @default.
- W4385454396 cites W2003099669 @default.
- W4385454396 cites W2017745767 @default.
- W4385454396 cites W2065410047 @default.
- W4385454396 cites W2074216025 @default.
- W4385454396 cites W2081613323 @default.
- W4385454396 cites W2102605133 @default.
- W4385454396 cites W2133059825 @default.
- W4385454396 cites W2144506857 @default.
- W4385454396 cites W2145023731 @default.
- W4385454396 cites W2163367160 @default.
- W4385454396 cites W2194775991 @default.
- W4385454396 cites W2589306531 @default.
- W4385454396 cites W2614196303 @default.
- W4385454396 cites W2618530766 @default.
- W4385454396 cites W2621119428 @default.
- W4385454396 cites W2775546317 @default.
- W4385454396 cites W2960155470 @default.
- W4385454396 cites W2963037989 @default.
- W4385454396 cites W2963150697 @default.
- W4385454396 cites W2963351448 @default.
- W4385454396 cites W2964241181 @default.
- W4385454396 cites W2979744596 @default.
- W4385454396 cites W2980611806 @default.
- W4385454396 cites W3042011474 @default.
- W4385454396 cites W3049136696 @default.
- W4385454396 cites W3124196589 @default.
- W4385454396 cites W3127743092 @default.
- W4385454396 cites W3131900481 @default.
- W4385454396 cites W3138118886 @default.
- W4385454396 cites W3203146146 @default.
- W4385454396 cites W3203680926 @default.
- W4385454396 cites W4226042837 @default.
- W4385454396 cites W4239510810 @default.
- W4385454396 cites W4313180186 @default.
- W4385454396 cites W4315705099 @default.
- W4385454396 doi "https://doi.org/10.1016/j.ndteint.2023.102919" @default.
- W4385454396 hasPublicationYear "2023" @default.
- W4385454396 type Work @default.
- W4385454396 citedByCount "0" @default.
- W4385454396 crossrefType "journal-article" @default.
- W4385454396 hasAuthorship W4385454396A5005821234 @default.
- W4385454396 hasAuthorship W4385454396A5011102375 @default.
- W4385454396 hasAuthorship W4385454396A5021111709 @default.
- W4385454396 hasAuthorship W4385454396A5049172004 @default.
- W4385454396 hasAuthorship W4385454396A5080385405 @default.
- W4385454396 hasConcept C105795698 @default.
- W4385454396 hasConcept C117251300 @default.
- W4385454396 hasConcept C126838900 @default.
- W4385454396 hasConcept C127413603 @default.
- W4385454396 hasConcept C13280743 @default.
- W4385454396 hasConcept C151730666 @default.
- W4385454396 hasConcept C153180895 @default.
- W4385454396 hasConcept C154945302 @default.
- W4385454396 hasConcept C185798385 @default.
- W4385454396 hasConcept C19474535 @default.
- W4385454396 hasConcept C205649164 @default.
- W4385454396 hasConcept C2776502983 @default.
- W4385454396 hasConcept C2779343474 @default.
- W4385454396 hasConcept C31972630 @default.
- W4385454396 hasConcept C33923547 @default.
- W4385454396 hasConcept C34736171 @default.
- W4385454396 hasConcept C41008148 @default.
- W4385454396 hasConcept C56529433 @default.
- W4385454396 hasConcept C71924100 @default.
- W4385454396 hasConcept C73313986 @default.
- W4385454396 hasConcept C78519656 @default.
- W4385454396 hasConcept C86803240 @default.
- W4385454396 hasConceptScore W4385454396C105795698 @default.
- W4385454396 hasConceptScore W4385454396C117251300 @default.
- W4385454396 hasConceptScore W4385454396C126838900 @default.
- W4385454396 hasConceptScore W4385454396C127413603 @default.
- W4385454396 hasConceptScore W4385454396C13280743 @default.
- W4385454396 hasConceptScore W4385454396C151730666 @default.
- W4385454396 hasConceptScore W4385454396C153180895 @default.
- W4385454396 hasConceptScore W4385454396C154945302 @default.
- W4385454396 hasConceptScore W4385454396C185798385 @default.
- W4385454396 hasConceptScore W4385454396C19474535 @default.
- W4385454396 hasConceptScore W4385454396C205649164 @default.
- W4385454396 hasConceptScore W4385454396C2776502983 @default.
- W4385454396 hasConceptScore W4385454396C2779343474 @default.
- W4385454396 hasConceptScore W4385454396C31972630 @default.
- W4385454396 hasConceptScore W4385454396C33923547 @default.
- W4385454396 hasConceptScore W4385454396C34736171 @default.
- W4385454396 hasConceptScore W4385454396C41008148 @default.
- W4385454396 hasConceptScore W4385454396C56529433 @default.
- W4385454396 hasConceptScore W4385454396C71924100 @default.