Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321605581> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4321605581 abstract "The identification of rock slices is the basis of geological research. However, due to the complex mineral composition and structure of volcanic rocks, microscopic analysis is difficult and requires a lot of time for professionals to complete. This paper uses deep learning technology, which has emerged in recent years, to explore a new method of intelligent rock slice identification to achieve automatic identification of volcanic rock slices. The deep residual shrinkage neural network model is used to study the intelligent recognition of volcanic rock slice images. The study investigated 11 basic types of volcanic rock and collected 12,000 high-definition images of rock slices using an electron polarized light microscope. Each image was processed via histogram equalization and image sharpening; data were expanded by random cropping; and the expanded image data were used as a training set to train the network. When the number of model layers reached 50 layers, the best accuracy rate was achieved. After a series of optimizations and improvements of the network model type, the accuracy rate of the test set classification results exceeded 92%." @default.
- W4321605581 created "2023-02-24" @default.
- W4321605581 creator A5007273011 @default.
- W4321605581 creator A5039885075 @default.
- W4321605581 creator A5054732407 @default.
- W4321605581 date "2023-02-23" @default.
- W4321605581 modified "2023-09-29" @default.
- W4321605581 title "Identification method of volcanic rock slices based on a deep residual shrinkage network" @default.
- W4321605581 cites W1529672735 @default.
- W4321605581 cites W2046164395 @default.
- W4321605581 cites W2054161635 @default.
- W4321605581 cites W2268875920 @default.
- W4321605581 cites W2547563442 @default.
- W4321605581 cites W2619612788 @default.
- W4321605581 cites W2911268982 @default.
- W4321605581 cites W2912250162 @default.
- W4321605581 cites W3002757292 @default.
- W4321605581 cites W3154228626 @default.
- W4321605581 cites W4205496101 @default.
- W4321605581 doi "https://doi.org/10.1117/12.2668168" @default.
- W4321605581 hasPublicationYear "2023" @default.
- W4321605581 type Work @default.
- W4321605581 citedByCount "0" @default.
- W4321605581 crossrefType "proceedings-article" @default.
- W4321605581 hasAuthorship W4321605581A5007273011 @default.
- W4321605581 hasAuthorship W4321605581A5039885075 @default.
- W4321605581 hasAuthorship W4321605581A5054732407 @default.
- W4321605581 hasConcept C11413529 @default.
- W4321605581 hasConcept C116834253 @default.
- W4321605581 hasConcept C119857082 @default.
- W4321605581 hasConcept C120806208 @default.
- W4321605581 hasConcept C127313418 @default.
- W4321605581 hasConcept C155512373 @default.
- W4321605581 hasConcept C17409809 @default.
- W4321605581 hasConcept C180145272 @default.
- W4321605581 hasConcept C41008148 @default.
- W4321605581 hasConcept C59822182 @default.
- W4321605581 hasConcept C86803240 @default.
- W4321605581 hasConceptScore W4321605581C11413529 @default.
- W4321605581 hasConceptScore W4321605581C116834253 @default.
- W4321605581 hasConceptScore W4321605581C119857082 @default.
- W4321605581 hasConceptScore W4321605581C120806208 @default.
- W4321605581 hasConceptScore W4321605581C127313418 @default.
- W4321605581 hasConceptScore W4321605581C155512373 @default.
- W4321605581 hasConceptScore W4321605581C17409809 @default.
- W4321605581 hasConceptScore W4321605581C180145272 @default.
- W4321605581 hasConceptScore W4321605581C41008148 @default.
- W4321605581 hasConceptScore W4321605581C59822182 @default.
- W4321605581 hasConceptScore W4321605581C86803240 @default.
- W4321605581 hasLocation W43216055811 @default.
- W4321605581 hasOpenAccess W4321605581 @default.
- W4321605581 hasPrimaryLocation W43216055811 @default.
- W4321605581 hasRelatedWork W1535068549 @default.
- W4321605581 hasRelatedWork W2013828340 @default.
- W4321605581 hasRelatedWork W2070192581 @default.
- W4321605581 hasRelatedWork W2115012406 @default.
- W4321605581 hasRelatedWork W2167536656 @default.
- W4321605581 hasRelatedWork W2331854417 @default.
- W4321605581 hasRelatedWork W2469646072 @default.
- W4321605581 hasRelatedWork W2907144544 @default.
- W4321605581 hasRelatedWork W3094412894 @default.
- W4321605581 hasRelatedWork W3193970338 @default.
- W4321605581 isParatext "false" @default.
- W4321605581 isRetracted "false" @default.
- W4321605581 workType "article" @default.