Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093800646> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3093800646 endingPage "107724" @default.
- W3093800646 startingPage "107724" @default.
- W3093800646 abstract "Abstract The deep learning feature is the best for face recognition nowadays, but its performance exhibits unsatisfactorily under severe illumination variations. The main reason is that the deep learning feature was trained by the internet face images with variations of large pose/expression and slight/moderate illumination, which cannot well tackle severe illumination variations. Inspired by the fact that the deep learning feature can cope well with slight/moderate varying illumination, this paper proposes an illumination recovery model to transform severe varying illumination to slight/moderate varying illumination. The illumination recovery model enables the illumination of the severe illumination variation image close to that of the reference image with slight/moderate varying illumination. The reference image generated from the severe illumination variation image is termed as the generated reference image (GRI), which is obtained by normalizing singular values of the logarithm version of the severe illumination variation image to have unit L2-norm. The gradient descent algorithm is employed to address the proposed illumination recovery model, to obtain the generated reference image based illumination recovery image (GRIR). GRIR preserves better face inherent information than GRI such as the face color. Experimental results indicate that the proposed GRIR can efficiently improve the performance of the deep learning feature under severe illumination variations." @default.
- W3093800646 created "2020-10-29" @default.
- W3093800646 creator A5013511890 @default.
- W3093800646 creator A5029691902 @default.
- W3093800646 creator A5038657591 @default.
- W3093800646 creator A5038794080 @default.
- W3093800646 creator A5039792198 @default.
- W3093800646 creator A5054925527 @default.
- W3093800646 creator A5064763991 @default.
- W3093800646 date "2021-03-01" @default.
- W3093800646 modified "2023-10-16" @default.
- W3093800646 title "Face illumination recovery for the deep learning feature under severe illumination variations" @default.
- W3093800646 cites W1977527736 @default.
- W3093800646 cites W2006793117 @default.
- W3093800646 cites W2055024227 @default.
- W3093800646 cites W2081872746 @default.
- W3093800646 cites W2098951409 @default.
- W3093800646 cites W2109486640 @default.
- W3093800646 cites W2118328928 @default.
- W3093800646 cites W2123921160 @default.
- W3093800646 cites W2146772029 @default.
- W3093800646 cites W2303542150 @default.
- W3093800646 cites W2546490901 @default.
- W3093800646 cites W2765946592 @default.
- W3093800646 cites W2779166865 @default.
- W3093800646 cites W2809969884 @default.
- W3093800646 cites W2894205709 @default.
- W3093800646 cites W2906361233 @default.
- W3093800646 cites W2999057796 @default.
- W3093800646 cites W2999903067 @default.
- W3093800646 cites W3101998545 @default.
- W3093800646 doi "https://doi.org/10.1016/j.patcog.2020.107724" @default.
- W3093800646 hasPublicationYear "2021" @default.
- W3093800646 type Work @default.
- W3093800646 sameAs 3093800646 @default.
- W3093800646 citedByCount "14" @default.
- W3093800646 countsByYear W30938006462021 @default.
- W3093800646 countsByYear W30938006462022 @default.
- W3093800646 countsByYear W30938006462023 @default.
- W3093800646 crossrefType "journal-article" @default.
- W3093800646 hasAuthorship W3093800646A5013511890 @default.
- W3093800646 hasAuthorship W3093800646A5029691902 @default.
- W3093800646 hasAuthorship W3093800646A5038657591 @default.
- W3093800646 hasAuthorship W3093800646A5038794080 @default.
- W3093800646 hasAuthorship W3093800646A5039792198 @default.
- W3093800646 hasAuthorship W3093800646A5054925527 @default.
- W3093800646 hasAuthorship W3093800646A5064763991 @default.
- W3093800646 hasConcept C108583219 @default.
- W3093800646 hasConcept C138885662 @default.
- W3093800646 hasConcept C144024400 @default.
- W3093800646 hasConcept C153180895 @default.
- W3093800646 hasConcept C154945302 @default.
- W3093800646 hasConcept C2776401178 @default.
- W3093800646 hasConcept C2779304628 @default.
- W3093800646 hasConcept C31972630 @default.
- W3093800646 hasConcept C36289849 @default.
- W3093800646 hasConcept C41008148 @default.
- W3093800646 hasConcept C41895202 @default.
- W3093800646 hasConceptScore W3093800646C108583219 @default.
- W3093800646 hasConceptScore W3093800646C138885662 @default.
- W3093800646 hasConceptScore W3093800646C144024400 @default.
- W3093800646 hasConceptScore W3093800646C153180895 @default.
- W3093800646 hasConceptScore W3093800646C154945302 @default.
- W3093800646 hasConceptScore W3093800646C2776401178 @default.
- W3093800646 hasConceptScore W3093800646C2779304628 @default.
- W3093800646 hasConceptScore W3093800646C31972630 @default.
- W3093800646 hasConceptScore W3093800646C36289849 @default.
- W3093800646 hasConceptScore W3093800646C41008148 @default.
- W3093800646 hasConceptScore W3093800646C41895202 @default.
- W3093800646 hasLocation W30938006461 @default.
- W3093800646 hasOpenAccess W3093800646 @default.
- W3093800646 hasPrimaryLocation W30938006461 @default.
- W3093800646 hasRelatedWork W1504288058 @default.
- W3093800646 hasRelatedWork W1899364738 @default.
- W3093800646 hasRelatedWork W1955116508 @default.
- W3093800646 hasRelatedWork W2103413230 @default.
- W3093800646 hasRelatedWork W2136321227 @default.
- W3093800646 hasRelatedWork W2355490025 @default.
- W3093800646 hasRelatedWork W2663901905 @default.
- W3093800646 hasRelatedWork W2773120646 @default.
- W3093800646 hasRelatedWork W2908959303 @default.
- W3093800646 hasRelatedWork W43171467 @default.
- W3093800646 hasVolume "111" @default.
- W3093800646 isParatext "false" @default.
- W3093800646 isRetracted "false" @default.
- W3093800646 magId "3093800646" @default.
- W3093800646 workType "article" @default.