Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387387971> ?p ?o ?g. }
- W4387387971 endingPage "108411" @default.
- W4387387971 startingPage "108411" @default.
- W4387387971 abstract "Vision-based mineral image recognition and classification is a proven solution for autonomous unmanned ore sorting. Although accurate identification can be achieved by training models offline using large-scale datasets, the lack of sufficient labeled images still limits the accessibility and exploration of high-performance deep learning models. To address the above issues, referring to the generative adversarial networks, three different deep learning-based mineral image data augmentation models are proposed in this work. The experimental results show that the proposed models can generate mineral images with high fidelity and have high similarity to the ground truth in terms of texture, color and shape. Compared with classic data augmentation methods, proposed ones can better optimize downstream sorting tasks: the accuracy of ResNet101, ResNet50, InceptionV3 and VGG19 is improved by 18.52%, 9.94%, 4.39% and 2.39%, respectively. Finally, this work also presents a monolithic three-stage system workflow for large-scale mineral image recognition and classification." @default.
- W4387387971 created "2023-10-06" @default.
- W4387387971 creator A5000601542 @default.
- W4387387971 creator A5027008332 @default.
- W4387387971 creator A5028821745 @default.
- W4387387971 creator A5031656256 @default.
- W4387387971 date "2023-12-01" @default.
- W4387387971 modified "2023-10-16" @default.
- W4387387971 title "Deep learning based data augmentation for large-scale mineral image recognition and classification" @default.
- W4387387971 cites W1964700079 @default.
- W4387387971 cites W2057168667 @default.
- W4387387971 cites W2152240655 @default.
- W4387387971 cites W2300527407 @default.
- W4387387971 cites W2439118858 @default.
- W4387387971 cites W2577255913 @default.
- W4387387971 cites W2619612788 @default.
- W4387387971 cites W2740886731 @default.
- W4387387971 cites W2766073597 @default.
- W4387387971 cites W2783455139 @default.
- W4387387971 cites W2792952603 @default.
- W4387387971 cites W2893424576 @default.
- W4387387971 cites W2895860858 @default.
- W4387387971 cites W2899614066 @default.
- W4387387971 cites W2901691125 @default.
- W4387387971 cites W2901867351 @default.
- W4387387971 cites W2903880955 @default.
- W4387387971 cites W2928392788 @default.
- W4387387971 cites W2944668789 @default.
- W4387387971 cites W2962793481 @default.
- W4387387971 cites W2963470893 @default.
- W4387387971 cites W2969897252 @default.
- W4387387971 cites W2973134644 @default.
- W4387387971 cites W3042907219 @default.
- W4387387971 cites W3081392779 @default.
- W4387387971 cites W3094457887 @default.
- W4387387971 cites W3096831136 @default.
- W4387387971 cites W3098040851 @default.
- W4387387971 cites W3168244790 @default.
- W4387387971 cites W3190401571 @default.
- W4387387971 cites W4212936479 @default.
- W4387387971 cites W4224032407 @default.
- W4387387971 cites W4286784861 @default.
- W4387387971 doi "https://doi.org/10.1016/j.mineng.2023.108411" @default.
- W4387387971 hasPublicationYear "2023" @default.
- W4387387971 type Work @default.
- W4387387971 citedByCount "0" @default.
- W4387387971 crossrefType "journal-article" @default.
- W4387387971 hasAuthorship W4387387971A5000601542 @default.
- W4387387971 hasAuthorship W4387387971A5027008332 @default.
- W4387387971 hasAuthorship W4387387971A5028821745 @default.
- W4387387971 hasAuthorship W4387387971A5031656256 @default.
- W4387387971 hasConcept C103278499 @default.
- W4387387971 hasConcept C108583219 @default.
- W4387387971 hasConcept C111696304 @default.
- W4387387971 hasConcept C115961682 @default.
- W4387387971 hasConcept C116834253 @default.
- W4387387971 hasConcept C119857082 @default.
- W4387387971 hasConcept C121332964 @default.
- W4387387971 hasConcept C153180895 @default.
- W4387387971 hasConcept C154945302 @default.
- W4387387971 hasConcept C177212765 @default.
- W4387387971 hasConcept C199360897 @default.
- W4387387971 hasConcept C2778755073 @default.
- W4387387971 hasConcept C31972630 @default.
- W4387387971 hasConcept C41008148 @default.
- W4387387971 hasConcept C59822182 @default.
- W4387387971 hasConcept C62520636 @default.
- W4387387971 hasConcept C77088390 @default.
- W4387387971 hasConcept C86803240 @default.
- W4387387971 hasConceptScore W4387387971C103278499 @default.
- W4387387971 hasConceptScore W4387387971C108583219 @default.
- W4387387971 hasConceptScore W4387387971C111696304 @default.
- W4387387971 hasConceptScore W4387387971C115961682 @default.
- W4387387971 hasConceptScore W4387387971C116834253 @default.
- W4387387971 hasConceptScore W4387387971C119857082 @default.
- W4387387971 hasConceptScore W4387387971C121332964 @default.
- W4387387971 hasConceptScore W4387387971C153180895 @default.
- W4387387971 hasConceptScore W4387387971C154945302 @default.
- W4387387971 hasConceptScore W4387387971C177212765 @default.
- W4387387971 hasConceptScore W4387387971C199360897 @default.
- W4387387971 hasConceptScore W4387387971C2778755073 @default.
- W4387387971 hasConceptScore W4387387971C31972630 @default.
- W4387387971 hasConceptScore W4387387971C41008148 @default.
- W4387387971 hasConceptScore W4387387971C59822182 @default.
- W4387387971 hasConceptScore W4387387971C62520636 @default.
- W4387387971 hasConceptScore W4387387971C77088390 @default.
- W4387387971 hasConceptScore W4387387971C86803240 @default.
- W4387387971 hasLocation W43873879711 @default.
- W4387387971 hasOpenAccess W4387387971 @default.
- W4387387971 hasPrimaryLocation W43873879711 @default.
- W4387387971 hasRelatedWork W188202134 @default.
- W4387387971 hasRelatedWork W1981780420 @default.
- W4387387971 hasRelatedWork W2029380707 @default.
- W4387387971 hasRelatedWork W2155675398 @default.
- W4387387971 hasRelatedWork W2182707996 @default.
- W4387387971 hasRelatedWork W2397952901 @default.
- W4387387971 hasRelatedWork W2465382974 @default.
- W4387387971 hasRelatedWork W2964988449 @default.