Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386089870> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4386089870 abstract "Artificial Intelligence-based Automated Optical Inspection (AI-AOI) using Convolutional Neural Networks (CNNs) is commonly used for defect detection, including metal defect detection, in modern manufacturing. However, in most AOI applications, the occurrence of defects is much less than the normal ones. CNN-based defection models perform poorly due to the imbalanced and less divergent training data. This study presents the performance of CNN-based AOI for metal defect detection with the techniques of generative AI for data augmentation. The Wasserstein Generative Adversarial Network (WGAN) is employed for generating negative training data and increasing the divergence when training AOI models. The similarity of data generated by WGAN to the original ones is evaluated by the Structural Similarity Index Measure (SSIM). The performance of ten CNN models trained with data before and after being augmented by WGAN are compared. Three metal defect datasets are used for evaluating the performance of CNN-based AOI with WGAN. The experimental results show that the performance of defect classification can be improved by 1%-12% with data augmented by WGAN." @default.
- W4386089870 created "2023-08-24" @default.
- W4386089870 creator A5004066253 @default.
- W4386089870 creator A5004527645 @default.
- W4386089870 creator A5034146966 @default.
- W4386089870 creator A5039664226 @default.
- W4386089870 date "2023-06-01" @default.
- W4386089870 modified "2023-09-26" @default.
- W4386089870 title "GAN-based Data Augmentation for Metal Surface Defect Detection Using Convolutional Neural Networks" @default.
- W4386089870 cites W2133665775 @default.
- W4386089870 cites W2886256586 @default.
- W4386089870 cites W2944303778 @default.
- W4386089870 cites W2978742590 @default.
- W4386089870 cites W3000247513 @default.
- W4386089870 cites W3006938707 @default.
- W4386089870 cites W3012374719 @default.
- W4386089870 cites W3094374092 @default.
- W4386089870 cites W3170140136 @default.
- W4386089870 cites W4225898116 @default.
- W4386089870 doi "https://doi.org/10.1109/is3c57901.2023.00029" @default.
- W4386089870 hasPublicationYear "2023" @default.
- W4386089870 type Work @default.
- W4386089870 citedByCount "0" @default.
- W4386089870 crossrefType "proceedings-article" @default.
- W4386089870 hasAuthorship W4386089870A5004066253 @default.
- W4386089870 hasAuthorship W4386089870A5004527645 @default.
- W4386089870 hasAuthorship W4386089870A5034146966 @default.
- W4386089870 hasAuthorship W4386089870A5039664226 @default.
- W4386089870 hasConcept C103278499 @default.
- W4386089870 hasConcept C108583219 @default.
- W4386089870 hasConcept C115961682 @default.
- W4386089870 hasConcept C138885662 @default.
- W4386089870 hasConcept C153180895 @default.
- W4386089870 hasConcept C154945302 @default.
- W4386089870 hasConcept C207390915 @default.
- W4386089870 hasConcept C2988773926 @default.
- W4386089870 hasConcept C39890363 @default.
- W4386089870 hasConcept C41008148 @default.
- W4386089870 hasConcept C41895202 @default.
- W4386089870 hasConcept C50644808 @default.
- W4386089870 hasConcept C81363708 @default.
- W4386089870 hasConceptScore W4386089870C103278499 @default.
- W4386089870 hasConceptScore W4386089870C108583219 @default.
- W4386089870 hasConceptScore W4386089870C115961682 @default.
- W4386089870 hasConceptScore W4386089870C138885662 @default.
- W4386089870 hasConceptScore W4386089870C153180895 @default.
- W4386089870 hasConceptScore W4386089870C154945302 @default.
- W4386089870 hasConceptScore W4386089870C207390915 @default.
- W4386089870 hasConceptScore W4386089870C2988773926 @default.
- W4386089870 hasConceptScore W4386089870C39890363 @default.
- W4386089870 hasConceptScore W4386089870C41008148 @default.
- W4386089870 hasConceptScore W4386089870C41895202 @default.
- W4386089870 hasConceptScore W4386089870C50644808 @default.
- W4386089870 hasConceptScore W4386089870C81363708 @default.
- W4386089870 hasFunder F4320322108 @default.
- W4386089870 hasLocation W43860898701 @default.
- W4386089870 hasOpenAccess W4386089870 @default.
- W4386089870 hasPrimaryLocation W43860898701 @default.
- W4386089870 hasRelatedWork W2731899572 @default.
- W4386089870 hasRelatedWork W2999805992 @default.
- W4386089870 hasRelatedWork W3116150086 @default.
- W4386089870 hasRelatedWork W3133861977 @default.
- W4386089870 hasRelatedWork W4200173597 @default.
- W4386089870 hasRelatedWork W4211070796 @default.
- W4386089870 hasRelatedWork W4291897433 @default.
- W4386089870 hasRelatedWork W4301431435 @default.
- W4386089870 hasRelatedWork W4312417841 @default.
- W4386089870 hasRelatedWork W4321369474 @default.
- W4386089870 isParatext "false" @default.
- W4386089870 isRetracted "false" @default.
- W4386089870 workType "article" @default.