Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900193097> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2900193097 endingPage "553" @default.
- W2900193097 startingPage "549" @default.
- W2900193097 abstract "Speckle noise is inherent to synthetic aperture radar (SAR) images and degrades the target recognition performance. Deep learning based on convolutional neural networks (CNNs) has been widely applied for SAR target recognition, but the extracted features are still sensitive to speckle noise. In addition, speckle noise has been seldom considered in such CNN-based approaches. In this letter, we propose a speckle-noise-invariant CNN that employs regularization for minimizing feature variations caused by this noise. Before CNN training, we performed SAR image despeckling using the improved Lee sigma filter for feature extraction. Then, we generated SAR images for CNN training by adding speckle noise to the despeckled images. The proposed regularization improves both the feature robustness to speckle noise and SAR target recognition. Experiments on the moving and stationary target acquisition and recognition database demonstrate that the proposed CNN notably improves the classification accuracy compared with the conventional methods." @default.
- W2900193097 created "2018-11-16" @default.
- W2900193097 creator A5005281029 @default.
- W2900193097 creator A5005719536 @default.
- W2900193097 creator A5046468998 @default.
- W2900193097 date "2019-04-01" @default.
- W2900193097 modified "2023-10-16" @default.
- W2900193097 title "Speckle-Noise-Invariant Convolutional Neural Network for SAR Target Recognition" @default.
- W2900193097 cites W1677182931 @default.
- W2900193097 cites W2034350730 @default.
- W2900193097 cites W2053024573 @default.
- W2900193097 cites W2058543239 @default.
- W2900193097 cites W2111847198 @default.
- W2900193097 cites W2129038850 @default.
- W2900193097 cites W2130615595 @default.
- W2900193097 cites W2281856034 @default.
- W2900193097 cites W2292481059 @default.
- W2900193097 cites W2342045095 @default.
- W2900193097 cites W2410591237 @default.
- W2900193097 cites W2517475170 @default.
- W2900193097 cites W2752788177 @default.
- W2900193097 cites W322998299 @default.
- W2900193097 doi "https://doi.org/10.1109/lgrs.2018.2877599" @default.
- W2900193097 hasPublicationYear "2019" @default.
- W2900193097 type Work @default.
- W2900193097 sameAs 2900193097 @default.
- W2900193097 citedByCount "45" @default.
- W2900193097 countsByYear W29001930972019 @default.
- W2900193097 countsByYear W29001930972020 @default.
- W2900193097 countsByYear W29001930972021 @default.
- W2900193097 countsByYear W29001930972022 @default.
- W2900193097 countsByYear W29001930972023 @default.
- W2900193097 crossrefType "journal-article" @default.
- W2900193097 hasAuthorship W2900193097A5005281029 @default.
- W2900193097 hasAuthorship W2900193097A5005719536 @default.
- W2900193097 hasAuthorship W2900193097A5046468998 @default.
- W2900193097 hasConcept C102290492 @default.
- W2900193097 hasConcept C153180895 @default.
- W2900193097 hasConcept C154945302 @default.
- W2900193097 hasConcept C180940675 @default.
- W2900193097 hasConcept C190470478 @default.
- W2900193097 hasConcept C28490314 @default.
- W2900193097 hasConcept C31972630 @default.
- W2900193097 hasConcept C33923547 @default.
- W2900193097 hasConcept C37914503 @default.
- W2900193097 hasConcept C41008148 @default.
- W2900193097 hasConcept C81363708 @default.
- W2900193097 hasConcept C87360688 @default.
- W2900193097 hasConceptScore W2900193097C102290492 @default.
- W2900193097 hasConceptScore W2900193097C153180895 @default.
- W2900193097 hasConceptScore W2900193097C154945302 @default.
- W2900193097 hasConceptScore W2900193097C180940675 @default.
- W2900193097 hasConceptScore W2900193097C190470478 @default.
- W2900193097 hasConceptScore W2900193097C28490314 @default.
- W2900193097 hasConceptScore W2900193097C31972630 @default.
- W2900193097 hasConceptScore W2900193097C33923547 @default.
- W2900193097 hasConceptScore W2900193097C37914503 @default.
- W2900193097 hasConceptScore W2900193097C41008148 @default.
- W2900193097 hasConceptScore W2900193097C81363708 @default.
- W2900193097 hasConceptScore W2900193097C87360688 @default.
- W2900193097 hasFunder F4320322120 @default.
- W2900193097 hasIssue "4" @default.
- W2900193097 hasLocation W29001930971 @default.
- W2900193097 hasOpenAccess W2900193097 @default.
- W2900193097 hasPrimaryLocation W29001930971 @default.
- W2900193097 hasRelatedWork W1964343417 @default.
- W2900193097 hasRelatedWork W1973066300 @default.
- W2900193097 hasRelatedWork W2923077656 @default.
- W2900193097 hasRelatedWork W2959574828 @default.
- W2900193097 hasRelatedWork W2982947611 @default.
- W2900193097 hasRelatedWork W3118135528 @default.
- W2900193097 hasRelatedWork W3191568623 @default.
- W2900193097 hasRelatedWork W3191671917 @default.
- W2900193097 hasRelatedWork W3216726918 @default.
- W2900193097 hasRelatedWork W4313525660 @default.
- W2900193097 hasVolume "16" @default.
- W2900193097 isParatext "false" @default.
- W2900193097 isRetracted "false" @default.
- W2900193097 magId "2900193097" @default.
- W2900193097 workType "article" @default.