FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387051623> ?p ?o ?g. }

• W4387051623 endingPage "337" @default.
• W4387051623 startingPage "324" @default.
• W4387051623 abstract "Real-time surface roughness measurement is crucial for modern manufacturing. Machine vision-based roughness measurement algorithms have the advantages of non-contact, high efficiency and adaptability. Light source is important for online machine vision-based roughness measurement. And different materials may need different light sources to extract more features. From the previous study, dual light sources are better than single light source for surface roughness prediction. However, it is inconvenient to assign two light sources for online detection equipment, and the two-branch model structure for dual light sources doubles the size of the model. To fully utilize the advantages of dual light sources, and avoid its disadvantages, a feature enhancement based single branch deep learning model FE-Trans-Net is proposed in this paper for surface roughness detection. Firstly, a dataset of different materials (Cu, Zn, Al, and Fe) shined with different light sources (white, red, green, red laser and green laser) is collected. Two most suitable light sources for different materials are chosen for dual light sources model as offline pre-training. In this model, lightweight cross-attention fusion (CAF-Trans) and graph convolutional channel attention (GCC-Atten) modules are designed to fuse the feature information of different light sources from the spatial and channel perspectives respectively, enabling the single-branch model to acquire the feature learning capability of different light sources. Then a single-branch network layer is remained as the online prediction. With the feature enhancement, it preserves the advantages of dual light source images, and has only half size of the dual light source model. Extensive experiments validate the effectiveness and generalization performance of the CAF-Trans and GCC-Atten modules, and the proposed FE-Trans-Net network achieves the best accuracy-efficiency tradeoff compared to other popular deep neural networks." @default.
• W4387051623 created "2023-09-27" @default.
• W4387051623 creator A5033530426 @default.
• W4387051623 creator A5035755529 @default.
• W4387051623 creator A5040612977 @default.
• W4387051623 creator A5050202580 @default.
• W4387051623 creator A5052199711 @default.
• W4387051623 creator A5056597068 @default.
• W4387051623 creator A5072964270 @default.
• W4387051623 creator A5086313562 @default.
• W4387051623 date "2023-11-01" @default.
• W4387051623 modified "2023-10-11" @default.
• W4387051623 title "FE-trans-net: Feature enhancement based single branch deep learning model for surface roughness detection" @default.
• W4387051623 cites W2046510171 @default.
• W4387051623 cites W2112796928 @default.
• W4387051623 cites W2158787690 @default.
• W4387051623 cites W2590420952 @default.
• W4387051623 cites W2794066716 @default.
• W4387051623 cites W2884261455 @default.
• W4387051623 cites W2900868857 @default.
• W4387051623 cites W2901410531 @default.
• W4387051623 cites W2966297622 @default.
• W4387051623 cites W3017961231 @default.
• W4387051623 cites W3048907483 @default.
• W4387051623 cites W3089161410 @default.
• W4387051623 cites W3092379902 @default.
• W4387051623 cites W3127672690 @default.
• W4387051623 cites W3167544688 @default.
• W4387051623 cites W3175515048 @default.
• W4387051623 cites W3195215150 @default.
• W4387051623 cites W3202738328 @default.
• W4387051623 cites W3204074875 @default.
• W4387051623 cites W4220851260 @default.
• W4387051623 cites W4226024981 @default.
• W4387051623 cites W4226322639 @default.
• W4387051623 cites W4285384523 @default.
• W4387051623 cites W4308030173 @default.
• W4387051623 doi "https://doi.org/10.1016/j.jmapro.2023.09.045" @default.
• W4387051623 hasPublicationYear "2023" @default.
• W4387051623 type Work @default.
• W4387051623 citedByCount "0" @default.
• W4387051623 crossrefType "journal-article" @default.
• W4387051623 hasAuthorship W4387051623A5033530426 @default.
• W4387051623 hasAuthorship W4387051623A5035755529 @default.
• W4387051623 hasAuthorship W4387051623A5040612977 @default.
• W4387051623 hasAuthorship W4387051623A5050202580 @default.
• W4387051623 hasAuthorship W4387051623A5052199711 @default.
• W4387051623 hasAuthorship W4387051623A5056597068 @default.
• W4387051623 hasAuthorship W4387051623A5072964270 @default.
• W4387051623 hasAuthorship W4387051623A5086313562 @default.
• W4387051623 hasConcept C107365816 @default.
• W4387051623 hasConcept C108583219 @default.
• W4387051623 hasConcept C119599485 @default.
• W4387051623 hasConcept C120665830 @default.
• W4387051623 hasConcept C121332964 @default.
• W4387051623 hasConcept C127413603 @default.
• W4387051623 hasConcept C138885662 @default.
• W4387051623 hasConcept C141353440 @default.
• W4387051623 hasConcept C154945302 @default.
• W4387051623 hasConcept C159985019 @default.
• W4387051623 hasConcept C192562407 @default.
• W4387051623 hasConcept C2776401178 @default.
• W4387051623 hasConcept C41008148 @default.
• W4387051623 hasConcept C41895202 @default.
• W4387051623 hasConcept C71039073 @default.
• W4387051623 hasConceptScore W4387051623C107365816 @default.
• W4387051623 hasConceptScore W4387051623C108583219 @default.
• W4387051623 hasConceptScore W4387051623C119599485 @default.
• W4387051623 hasConceptScore W4387051623C120665830 @default.
• W4387051623 hasConceptScore W4387051623C121332964 @default.
• W4387051623 hasConceptScore W4387051623C127413603 @default.
• W4387051623 hasConceptScore W4387051623C138885662 @default.
• W4387051623 hasConceptScore W4387051623C141353440 @default.
• W4387051623 hasConceptScore W4387051623C154945302 @default.
• W4387051623 hasConceptScore W4387051623C159985019 @default.
• W4387051623 hasConceptScore W4387051623C192562407 @default.
• W4387051623 hasConceptScore W4387051623C2776401178 @default.
• W4387051623 hasConceptScore W4387051623C41008148 @default.
• W4387051623 hasConceptScore W4387051623C41895202 @default.
• W4387051623 hasConceptScore W4387051623C71039073 @default.
• W4387051623 hasLocation W43870516231 @default.
• W4387051623 hasOpenAccess W4387051623 @default.
• W4387051623 hasPrimaryLocation W43870516231 @default.
• W4387051623 hasRelatedWork W1966522691 @default.
• W4387051623 hasRelatedWork W2032025132 @default.
• W4387051623 hasRelatedWork W2349732462 @default.
• W4387051623 hasRelatedWork W2386922414 @default.
• W4387051623 hasRelatedWork W2782769319 @default.
• W4387051623 hasRelatedWork W2783679862 @default.
• W4387051623 hasRelatedWork W3133982275 @default.
• W4387051623 hasRelatedWork W4297916609 @default.
• W4387051623 hasRelatedWork W4304014137 @default.
• W4387051623 hasRelatedWork W4313638943 @default.
• W4387051623 hasVolume "105" @default.
• W4387051623 isParatext "false" @default.
• W4387051623 isRetracted "false" @default.
• W4387051623 workType "article" @default.