Matches in SemOpenAlex for { <https://semopenalex.org/work/W2806771124> ?p ?o ?g. }
- W2806771124 abstract "This paper proposes a novel two-stage method for the classification of hyperspectral images. Pixel-wise classifiers, such as the classical support vector machine (SVM), consider spectral information only; therefore they would generate noisy classification results as spatial information is not utilized. Many existing methods, such as morphological profiles, superpixel segmentation, and composite kernels, exploit the spatial information too. In this paper, we propose a two-stage approach to incorporate the spatial information. In the first stage, an SVM is used to estimate the class probability for each pixel. The resulting probability map for each class will be noisy. In the second stage, a variational denoising method is used to restore these noisy probability maps to get a good classification map. Our proposed method effectively utilizes both spectral and spatial information of the hyperspectral data sets. Experimental results on three widely used real hyperspectral data sets indicate that our method is very competitive when compared with current state-of-the-art methods, especially when the inter-class spectra are similar or the percentage of the training pixels is high." @default.
- W2806771124 created "2018-06-13" @default.
- W2806771124 creator A5004126693 @default.
- W2806771124 creator A5004818798 @default.
- W2806771124 creator A5019525818 @default.
- W2806771124 creator A5076353369 @default.
- W2806771124 date "2018-06-03" @default.
- W2806771124 modified "2023-10-06" @default.
- W2806771124 title "A two-stage method for spectral-spatial classification of hyperspectral images" @default.
- W2806771124 cites W1640336024 @default.
- W2806771124 cites W1680392829 @default.
- W2806771124 cites W1965309615 @default.
- W2806771124 cites W1976709621 @default.
- W2806771124 cites W1986850130 @default.
- W2806771124 cites W1988868707 @default.
- W2806771124 cites W1990953362 @default.
- W2806771124 cites W1992597617 @default.
- W2806771124 cites W1992719146 @default.
- W2806771124 cites W2000594266 @default.
- W2806771124 cites W2008094348 @default.
- W2806771124 cites W2009286595 @default.
- W2806771124 cites W2012061355 @default.
- W2806771124 cites W2012079387 @default.
- W2806771124 cites W2033603511 @default.
- W2806771124 cites W2037981501 @default.
- W2806771124 cites W2042597321 @default.
- W2806771124 cites W2048976066 @default.
- W2806771124 cites W2053154970 @default.
- W2806771124 cites W2056983531 @default.
- W2806771124 cites W2062271656 @default.
- W2806771124 cites W2063907334 @default.
- W2806771124 cites W2081160575 @default.
- W2806771124 cites W2087347434 @default.
- W2806771124 cites W2092762391 @default.
- W2806771124 cites W2098843744 @default.
- W2806771124 cites W2113464037 @default.
- W2806771124 cites W2122374500 @default.
- W2806771124 cites W2133458583 @default.
- W2806771124 cites W2136251662 @default.
- W2806771124 cites W2148603752 @default.
- W2806771124 cites W2158400785 @default.
- W2806771124 cites W2164278908 @default.
- W2806771124 cites W2164330327 @default.
- W2806771124 cites W2164437025 @default.
- W2806771124 cites W2167799103 @default.
- W2806771124 cites W2169253121 @default.
- W2806771124 cites W2172000360 @default.
- W2806771124 cites W2518831014 @default.
- W2806771124 cites W648869842 @default.
- W2806771124 hasPublicationYear "2018" @default.
- W2806771124 type Work @default.
- W2806771124 sameAs 2806771124 @default.
- W2806771124 citedByCount "0" @default.
- W2806771124 crossrefType "posted-content" @default.
- W2806771124 hasAuthorship W2806771124A5004126693 @default.
- W2806771124 hasAuthorship W2806771124A5004818798 @default.
- W2806771124 hasAuthorship W2806771124A5019525818 @default.
- W2806771124 hasAuthorship W2806771124A5076353369 @default.
- W2806771124 hasConcept C105795698 @default.
- W2806771124 hasConcept C115961682 @default.
- W2806771124 hasConcept C12267149 @default.
- W2806771124 hasConcept C146357865 @default.
- W2806771124 hasConcept C151730666 @default.
- W2806771124 hasConcept C153180895 @default.
- W2806771124 hasConcept C154945302 @default.
- W2806771124 hasConcept C159078339 @default.
- W2806771124 hasConcept C159620131 @default.
- W2806771124 hasConcept C160633673 @default.
- W2806771124 hasConcept C163294075 @default.
- W2806771124 hasConcept C165696696 @default.
- W2806771124 hasConcept C2777212361 @default.
- W2806771124 hasConcept C33923547 @default.
- W2806771124 hasConcept C38652104 @default.
- W2806771124 hasConcept C41008148 @default.
- W2806771124 hasConcept C86803240 @default.
- W2806771124 hasConcept C89600930 @default.
- W2806771124 hasConcept C99498987 @default.
- W2806771124 hasConceptScore W2806771124C105795698 @default.
- W2806771124 hasConceptScore W2806771124C115961682 @default.
- W2806771124 hasConceptScore W2806771124C12267149 @default.
- W2806771124 hasConceptScore W2806771124C146357865 @default.
- W2806771124 hasConceptScore W2806771124C151730666 @default.
- W2806771124 hasConceptScore W2806771124C153180895 @default.
- W2806771124 hasConceptScore W2806771124C154945302 @default.
- W2806771124 hasConceptScore W2806771124C159078339 @default.
- W2806771124 hasConceptScore W2806771124C159620131 @default.
- W2806771124 hasConceptScore W2806771124C160633673 @default.
- W2806771124 hasConceptScore W2806771124C163294075 @default.
- W2806771124 hasConceptScore W2806771124C165696696 @default.
- W2806771124 hasConceptScore W2806771124C2777212361 @default.
- W2806771124 hasConceptScore W2806771124C33923547 @default.
- W2806771124 hasConceptScore W2806771124C38652104 @default.
- W2806771124 hasConceptScore W2806771124C41008148 @default.
- W2806771124 hasConceptScore W2806771124C86803240 @default.
- W2806771124 hasConceptScore W2806771124C89600930 @default.
- W2806771124 hasConceptScore W2806771124C99498987 @default.
- W2806771124 hasLocation W28067711241 @default.
- W2806771124 hasOpenAccess W2806771124 @default.
- W2806771124 hasPrimaryLocation W28067711241 @default.
- W2806771124 hasRelatedWork W2038577255 @default.