000087372 001__ 87372
000087372 005__ 20180317092053.0
000087372 02470 $$2DAR$$a11578
000087372 02470 $$2ISI$$a000250087900007
000087372 037__ $$aARTICLE
000087372 245__ $$aOrthogonal Neighborhood Preserving Projections: A projection-based dimensionality reduction technique
000087372 269__ $$a2007
000087372 260__ $$c2007
000087372 336__ $$aJournal Articles
000087372 520__ $$aThis paper considers the problem of dimensionality reduction by orthogonal projection techniques. The main feature of the proposed  techniques is that they  attempt to preserve both the intrinsic neighborhood geometry of the data samples and the global geometry. In particular we propose a method, named Orthogonal Neighborhood Preserving Projections, which works by first building an ``affinity'' graph for the data, in  a way that is similar to the method of   Locally  Linear  Embedding (LLE). However, in contrast with the  standard LLE where the mapping between the input and the reduced spaces is implicit, ONPP employs  an explicit linear mapping between the two. As a result, handling new data samples becomes straightforward, as this amounts to a simple linear transformation. We show how to define kernel variants of ONPP, as well as how to apply the method in a supervised setting. Numerical experiments are reported to illustrate the performance of ONPP and to compare it with a few competing methods.
000087372 6531_ $$aLTS4
000087372 6531_ $$aLinear Dimensionality Reduction
000087372 6531_ $$aFace Recognition
000087372 6531_ $$aData Visualization
000087372 700__ $$0240462$$aKokiopoulou, Effrosyni$$g170201
000087372 700__ $$aSaad, Yousef
000087372 773__ $$j29$$k12$$q2143-2156$$tIEEE Transactions on Pattern Analysis and Machine Intelligence
000087372 8564_ $$s4050641$$uhttps://infoscience.epfl.ch/record/87372/files/ONPP_tpami_revision_ys.pdf$$zn/a
000087372 909CO $$ooai:infoscience.tind.io:87372$$particle$$pSTI
000087372 909C0 $$0252393$$pLTS4$$xU10851
000087372 937__ $$aEPFL-ARTICLE-87372
000087372 970__ $$aKokiopoulou2006_1475/LTS
000087372 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000087372 980__ $$aARTICLE