Matches in SemOpenAlex for { <https://semopenalex.org/work/W939394776> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W939394776 endingPage "47" @default.
- W939394776 startingPage "44" @default.
- W939394776 abstract "Most subspace methods for the face recognition, such as linear discriminant analysis, discriminant eigenfeatures and fisherface cannot work in the situation of only one training image available per person, while the eigenface technique suffers a great performance drop. A novel method is used to automatically select some important local areas of a face image for face recognition with single training image per person. The SOM output space is studied from a novel view, where some enlightening ideas from the automatic text analysis field are introduced into the face recognition to evaluate the weights of different local areas of face images. The extracted weight information is then used to select some important lo cal facial features for the recognition. Experiments on both the FERET and ORL face database show that the proposed method is more efficient than its non-weighted counterpart while keeping the recognition accuracy acceptable. Moreover, the experiment points out that the most important local area to recognition maybe not those common supposed local areas, such as ear, nose or mouse." @default.
- W939394776 created "2016-06-24" @default.
- W939394776 creator A5050081230 @default.
- W939394776 creator A5055439924 @default.
- W939394776 creator A5065451795 @default.
- W939394776 date "2005-02-01" @default.
- W939394776 modified "2023-09-24" @default.
- W939394776 title "基于“SOM脸”的选择性单训练样本人脸识别" @default.
- W939394776 hasPublicationYear "2005" @default.
- W939394776 type Work @default.
- W939394776 sameAs 939394776 @default.
- W939394776 citedByCount "0" @default.
- W939394776 crossrefType "journal-article" @default.
- W939394776 hasAuthorship W939394776A5050081230 @default.
- W939394776 hasAuthorship W939394776A5055439924 @default.
- W939394776 hasAuthorship W939394776A5065451795 @default.
- W939394776 hasConcept C104906051 @default.
- W939394776 hasConcept C144024400 @default.
- W939394776 hasConcept C153180895 @default.
- W939394776 hasConcept C154945302 @default.
- W939394776 hasConcept C2779304628 @default.
- W939394776 hasConcept C31510193 @default.
- W939394776 hasConcept C31972630 @default.
- W939394776 hasConcept C32834561 @default.
- W939394776 hasConcept C36289849 @default.
- W939394776 hasConcept C41008148 @default.
- W939394776 hasConcept C4641261 @default.
- W939394776 hasConcept C69738355 @default.
- W939394776 hasConcept C88799230 @default.
- W939394776 hasConceptScore W939394776C104906051 @default.
- W939394776 hasConceptScore W939394776C144024400 @default.
- W939394776 hasConceptScore W939394776C153180895 @default.
- W939394776 hasConceptScore W939394776C154945302 @default.
- W939394776 hasConceptScore W939394776C2779304628 @default.
- W939394776 hasConceptScore W939394776C31510193 @default.
- W939394776 hasConceptScore W939394776C31972630 @default.
- W939394776 hasConceptScore W939394776C32834561 @default.
- W939394776 hasConceptScore W939394776C36289849 @default.
- W939394776 hasConceptScore W939394776C41008148 @default.
- W939394776 hasConceptScore W939394776C4641261 @default.
- W939394776 hasConceptScore W939394776C69738355 @default.
- W939394776 hasConceptScore W939394776C88799230 @default.
- W939394776 hasIssue "1" @default.
- W939394776 hasLocation W9393947761 @default.
- W939394776 hasOpenAccess W939394776 @default.
- W939394776 hasPrimaryLocation W9393947761 @default.
- W939394776 hasVolume "37" @default.
- W939394776 isParatext "false" @default.
- W939394776 isRetracted "false" @default.
- W939394776 magId "939394776" @default.
- W939394776 workType "article" @default.