摘要
Analgorithmforfacedescriptionandrecognitionbasedonmulti-resolutionwithmulti-scalelocalbinarypattern(multi-LBP)featuresisproposed.Thefacialimagepyramidisconstructedandeachfacialimageisdividedintovariousregionsfromwhichpartialandholisticlocalbinarypatter(LBP)histogramsareextracted.AllLBPfeaturesofeachimageareconcatenatedtoasingleLBPeigenvectorwithdifferentresolutions.ThedimensionalityofLBPfeaturesisthenreducedbyalocalmarginalignment(LMA)algorithmbasedonmanifold,whichcanpreservethebetween-classvariance.Supportvectormachine(SVM)isappliedtoclassifyfacialimages.ExtensiveexperimentsonORLandCMUfacedatabasesclearlyshowthesuperiorityoftheproposedschemeoversomeexistedalgorithms,especiallyontherobustnessofthemethodagainstdifferentfacialexpressionsandposturesofthesubjects.
出版日期
2012年01月11日(中国期刊网平台首次上网日期,不代表论文的发表时间)