Matches in SemOpenAlex for { <https://semopenalex.org/work/W1510577029> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W1510577029 abstract "Linear discriminant analysis (LDA) is a widely-used feature extraction method in classification. However, the original LDA has limitations due to the assumption of a unimodal structure for each cluster, which is not satisfied in many applications such as facial image data when variations, e.g. angle and illumination, can significantly influence the images. In this paper, we propose a novel method called hierarchical LDA (h-LDA), which takes into account hierarchical subcluster structures of the data in the LDA formulation and algorithm. We develop a theoretical basis of hierarchical LDA by identifying its relation to two-way multivariate analysis of variance (MANOVA) based on the data model and variance decomposition. Furthermore, an efficient algorithm for a regularized version of h-LDA (h-RLDA) is presented using the QR decomposition and the generalized SVD. To validate the effectiveness of the proposed method, we compare face recognition performance among h-RLDA, LDA, PCA, and TensorFaces. Our experiments show that h-RLDA produces better prediction accuracy than other methods. When only a small subset of features are used (reduced dimensionality), the superiority of h-RLDA over other methods becomes more significant. It is also shown that h-RLDA is a computationally much more efficient alternative to TensorFaces. Index Terms Dimension reduction, Feature extraction, Generalized singular value decomposition, QR decomposition, Hierarchical clustering, Undersampled problem, Regularization, Face recognition, Classification" @default.
- W1510577029 created "2016-06-24" @default.
- W1510577029 creator A5047863978 @default.
- W1510577029 creator A5047912015 @default.
- W1510577029 creator A5048375813 @default.
- W1510577029 date "2008-01-01" @default.
- W1510577029 modified "2023-09-27" @default.
- W1510577029 title "Linear Discriminant Analysis for Subclustered Data" @default.
- W1510577029 cites W1480376833 @default.
- W1510577029 cites W1663973292 @default.
- W1510577029 cites W1971784203 @default.
- W1510577029 cites W1977271127 @default.
- W1510577029 cites W1985852691 @default.
- W1510577029 cites W2012352340 @default.
- W1510577029 cites W2024165284 @default.
- W1510577029 cites W2027077102 @default.
- W1510577029 cites W2046649434 @default.
- W1510577029 cites W2056003151 @default.
- W1510577029 cites W2085535170 @default.
- W1510577029 cites W2088169690 @default.
- W1510577029 cites W2100115174 @default.
- W1510577029 cites W2112440119 @default.
- W1510577029 cites W2121647436 @default.
- W1510577029 cites W2131691213 @default.
- W1510577029 cites W2135346934 @default.
- W1510577029 cites W2145977092 @default.
- W1510577029 cites W2146820706 @default.
- W1510577029 cites W2159017231 @default.
- W1510577029 cites W2164552042 @default.
- W1510577029 cites W2799061466 @default.
- W1510577029 cites W1867773974 @default.
- W1510577029 hasPublicationYear "2008" @default.
- W1510577029 type Work @default.
- W1510577029 sameAs 1510577029 @default.
- W1510577029 citedByCount "0" @default.
- W1510577029 crossrefType "journal-article" @default.
- W1510577029 hasAuthorship W1510577029A5047863978 @default.
- W1510577029 hasAuthorship W1510577029A5047912015 @default.
- W1510577029 hasAuthorship W1510577029A5048375813 @default.
- W1510577029 hasConcept C153180895 @default.
- W1510577029 hasConcept C154945302 @default.
- W1510577029 hasConcept C22789450 @default.
- W1510577029 hasConcept C27438332 @default.
- W1510577029 hasConcept C2776135515 @default.
- W1510577029 hasConcept C33923547 @default.
- W1510577029 hasConcept C41008148 @default.
- W1510577029 hasConcept C52622490 @default.
- W1510577029 hasConcept C69738355 @default.
- W1510577029 hasConcept C70518039 @default.
- W1510577029 hasConcept C73555534 @default.
- W1510577029 hasConcept C92835128 @default.
- W1510577029 hasConceptScore W1510577029C153180895 @default.
- W1510577029 hasConceptScore W1510577029C154945302 @default.
- W1510577029 hasConceptScore W1510577029C22789450 @default.
- W1510577029 hasConceptScore W1510577029C27438332 @default.
- W1510577029 hasConceptScore W1510577029C2776135515 @default.
- W1510577029 hasConceptScore W1510577029C33923547 @default.
- W1510577029 hasConceptScore W1510577029C41008148 @default.
- W1510577029 hasConceptScore W1510577029C52622490 @default.
- W1510577029 hasConceptScore W1510577029C69738355 @default.
- W1510577029 hasConceptScore W1510577029C70518039 @default.
- W1510577029 hasConceptScore W1510577029C73555534 @default.
- W1510577029 hasConceptScore W1510577029C92835128 @default.
- W1510577029 hasLocation W15105770291 @default.
- W1510577029 hasOpenAccess W1510577029 @default.
- W1510577029 hasPrimaryLocation W15105770291 @default.
- W1510577029 hasRelatedWork W1997335117 @default.
- W1510577029 hasRelatedWork W2160817396 @default.
- W1510577029 hasRelatedWork W2165228095 @default.
- W1510577029 hasRelatedWork W2168155150 @default.
- W1510577029 hasRelatedWork W2331749527 @default.
- W1510577029 hasRelatedWork W2734406139 @default.
- W1510577029 hasRelatedWork W2762471879 @default.
- W1510577029 hasRelatedWork W2809360195 @default.
- W1510577029 hasRelatedWork W2925174069 @default.
- W1510577029 hasRelatedWork W2944556810 @default.
- W1510577029 hasRelatedWork W2945934224 @default.
- W1510577029 hasRelatedWork W2970477786 @default.
- W1510577029 hasRelatedWork W3016988317 @default.
- W1510577029 hasRelatedWork W3095271557 @default.
- W1510577029 hasRelatedWork W3137823125 @default.
- W1510577029 hasRelatedWork W3148632146 @default.
- W1510577029 hasRelatedWork W3176010308 @default.
- W1510577029 hasRelatedWork W3182945651 @default.
- W1510577029 hasRelatedWork W1867773974 @default.
- W1510577029 hasRelatedWork W3002427060 @default.
- W1510577029 isParatext "false" @default.
- W1510577029 isRetracted "false" @default.
- W1510577029 magId "1510577029" @default.
- W1510577029 workType "article" @default.