Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895850631> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2895850631 abstract "The paper addresses the problem of imaging quality enhancement for the Offner hyperspectrometer using a convolutional neural network. We use a deep convolutional neural network with residual training and PReLU activation, inspired by the super-resolution task for RGB images. In the case of hyperspectral imaging, it is often a problem to find a large enough ground truth dataset for training a neural network from scratch. Transfer learning using the network pretrained for RGB images with some pre- and postprocessing is one of the possible workarounds. In this paper, we propose to simulate the necessary ground truth data using non-imaging spectrometer. The obtained dataset with partially simulated ground truth is then used to train the convolutional neural network directly for hyperspectral image quality enhancement. The proposed training approach also allows to incorporate distortions specific for hyperspectral images into the enhancement procedure. It allows to successfully remove the striping distortions inherent to the Offner scheme of image acquisition. The experimental results of the proposed approach show a significant quality gain." @default.
- W2895850631 created "2018-10-26" @default.
- W2895850631 creator A5013369355 @default.
- W2895850631 creator A5038303804 @default.
- W2895850631 creator A5039833478 @default.
- W2895850631 creator A5052313272 @default.
- W2895850631 creator A5060985527 @default.
- W2895850631 creator A5080594712 @default.
- W2895850631 creator A5090758673 @default.
- W2895850631 creator A5091239841 @default.
- W2895850631 date "2018-08-01" @default.
- W2895850631 modified "2023-09-26" @default.
- W2895850631 title "Deep Learning-Based Enhancement of Hyperspectral Images Using Simulated Ground Truth" @default.
- W2895850631 cites W1045132426 @default.
- W2895850631 cites W1974755872 @default.
- W2895850631 cites W1985051078 @default.
- W2895850631 cites W2012946078 @default.
- W2895850631 cites W2058715873 @default.
- W2895850631 cites W2060422862 @default.
- W2895850631 cites W2063310230 @default.
- W2895850631 cites W2065002911 @default.
- W2895850631 cites W2133661405 @default.
- W2895850631 cites W2154815154 @default.
- W2895850631 cites W2242218935 @default.
- W2895850631 cites W2256362396 @default.
- W2895850631 cites W2274472325 @default.
- W2895850631 cites W2329604714 @default.
- W2895850631 cites W2333549353 @default.
- W2895850631 cites W2534320940 @default.
- W2895850631 cites W2588000623 @default.
- W2895850631 cites W2593622915 @default.
- W2895850631 cites W2608602932 @default.
- W2895850631 cites W2792627029 @default.
- W2895850631 cites W2806138840 @default.
- W2895850631 cites W2887840769 @default.
- W2895850631 doi "https://doi.org/10.1109/prrs.2018.8486408" @default.
- W2895850631 hasPublicationYear "2018" @default.
- W2895850631 type Work @default.
- W2895850631 sameAs 2895850631 @default.
- W2895850631 citedByCount "4" @default.
- W2895850631 countsByYear W28958506312019 @default.
- W2895850631 countsByYear W28958506312020 @default.
- W2895850631 countsByYear W28958506312021 @default.
- W2895850631 countsByYear W28958506312023 @default.
- W2895850631 crossrefType "proceedings-article" @default.
- W2895850631 hasAuthorship W2895850631A5013369355 @default.
- W2895850631 hasAuthorship W2895850631A5038303804 @default.
- W2895850631 hasAuthorship W2895850631A5039833478 @default.
- W2895850631 hasAuthorship W2895850631A5052313272 @default.
- W2895850631 hasAuthorship W2895850631A5060985527 @default.
- W2895850631 hasAuthorship W2895850631A5080594712 @default.
- W2895850631 hasAuthorship W2895850631A5090758673 @default.
- W2895850631 hasAuthorship W2895850631A5091239841 @default.
- W2895850631 hasConcept C127313418 @default.
- W2895850631 hasConcept C146849305 @default.
- W2895850631 hasConcept C153180895 @default.
- W2895850631 hasConcept C154945302 @default.
- W2895850631 hasConcept C159078339 @default.
- W2895850631 hasConcept C31972630 @default.
- W2895850631 hasConcept C41008148 @default.
- W2895850631 hasConcept C62649853 @default.
- W2895850631 hasConceptScore W2895850631C127313418 @default.
- W2895850631 hasConceptScore W2895850631C146849305 @default.
- W2895850631 hasConceptScore W2895850631C153180895 @default.
- W2895850631 hasConceptScore W2895850631C154945302 @default.
- W2895850631 hasConceptScore W2895850631C159078339 @default.
- W2895850631 hasConceptScore W2895850631C31972630 @default.
- W2895850631 hasConceptScore W2895850631C41008148 @default.
- W2895850631 hasConceptScore W2895850631C62649853 @default.
- W2895850631 hasLocation W28958506311 @default.
- W2895850631 hasOpenAccess W2895850631 @default.
- W2895850631 hasPrimaryLocation W28958506311 @default.
- W2895850631 hasRelatedWork W1491778359 @default.
- W2895850631 hasRelatedWork W1632903234 @default.
- W2895850631 hasRelatedWork W1869808405 @default.
- W2895850631 hasRelatedWork W2028628118 @default.
- W2895850631 hasRelatedWork W2031007444 @default.
- W2895850631 hasRelatedWork W2775464024 @default.
- W2895850631 hasRelatedWork W2783789044 @default.
- W2895850631 hasRelatedWork W2972973180 @default.
- W2895850631 hasRelatedWork W3211035526 @default.
- W2895850631 hasRelatedWork W4291701050 @default.
- W2895850631 isParatext "false" @default.
- W2895850631 isRetracted "false" @default.
- W2895850631 magId "2895850631" @default.
- W2895850631 workType "article" @default.