欢迎来到天天文库
浏览记录
ID:33745836
大小:1.02 MB
页数:10页
时间:2019-02-28
《facial feature detection using adaboost with shape constraints》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库。
1、FacialfeaturedetectionusingAdaBoostwithshapeconstraintsDavidCristinacceandTimCootesDept.ImagingScienceandBiomedicalEngineeringUniversityofManchester,Manchester,M139PT,U.K.david.cristinacce@stud.man.ac.ukAbstractRecentlyafastandefficientfacedetectionmethodhasbeen
2、devised[11],whichreliesontheAdaBoostalgorithmandasetofHaarWaveletlikefea-tures.Anaturalextensionofthisapproachistousethesametechniquetolo-cateindividualfeatureswithinthefaceregion.However,wefindthatthereisinsufficientlocalstructuretoreliablylocateeachfeatureineve
3、ryimage,andthuslocalmodelscangivemanyfalsepositiveresponses.Wedemonstratethattheperformanceofsuchfeaturedetectorscanbesignificantlyimprovedbyusingglobalshapeconstraints.Wedescribeanalgorithmcapableofac-curatelyandreliablydetectingfacialfeaturesandpresentquantit
4、ativeresultsonbothhighandlowresolutionimagesets.1IntroductionThispaperaddressestheproblemoflocatingfacialfeatures(eyes,nose,mouthcornersandsoon)inimagesoffrontalfaces.Locatingsuchfeaturesisanimportantstageinmanyfacialimageinterpretationtasks(suchasfaceverificat
5、ion,facetrackingorfaceexpressionrecognition).WeadoptthefastandefficientfacefinderrecentlydescribedbyViolaandJones[11]tolocatetheapproximatepositionofeachfaceinanimage.Wethenusethesamemethod,trainedonregionsaroundfacialfeaturepoints,tolocateinteriorpointsontheface
6、.However,thereisofteninsufficientlocalstructurearoundeachfeaturetotrainreallyreliablefeaturefinders.Wefindthatwhensetwiththresholdssufficienttolocatethetruepositionreasonablyfrequently,suchdetectorsproducemanyfalsepositives.Toselectthemostsuitablecandidatesweusestat
7、isticalmodelsoftheconfigurationsofthepoints.Wefindthatcombiningfeaturedetectorswithsuchstatisticalshapemodelsgivesasignificantimprovementinboththereliabilityandtheoverallaccuracyofthefeaturedetectionsystem.Inthefollowingwedescribetheapproachinmoredetail,anddemons
8、trateitsappli-cationtofindingfeaturesintwodatasets.Thoughdemonstratedonfaces,theapproachisclearlyapplicabletoawidevarietyofimageinterpretationtasks.2BackgroundFacedetectionhasreceiv
此文档下载收益归作者所有