人脸识别文献翻译中英双文Word文档下载推荐.docx

人脸识别文献翻译中英双文Word文档下载推荐.docx

《人脸识别文献翻译中英双文Word文档下载推荐.docx》由会员分享，可在线阅读，更多相关《人脸识别文献翻译中英双文Word文档下载推荐.docx（9页珍藏版）》请在冰豆网上搜索。

人脸识别文献翻译中英双文@#@人脸识别文献翻译（中英双文）@#@4Two-dimensionalFaceRecognition@#@4.1FeatureLocalization@#@Beforediscussingthemethodsofcomparingtwofacialimageswenowtakeabrieflookatsomeatthepreliminaryprocessesoffacialfeaturealignment.Thisprocesstypicallyconsistsoftwostages:

@#@facedetectionandeyelocalization.Dependingontheapplication,ifthepositionofthefacewithintheimageisknownbeforehand（foracooperativesubjectinadooraccesssystemforexample）thenthefacedetectionstagecanoftenbeskipped,astheregionofinterestisalreadyknown.Therefore,wediscusseyelocalizationhere,withabriefdiscussionoffacedetectionintheliteraturereview.@#@Theeyelocalizationmethodisusedtoalignthe2Dfaceimagesofthevarioustestsetsusedthroughoutthissection.However,toensurethatallresultspresentedarerepresentativeofthefacerecognitionaccuracyandnotaproductoftheperformanceoftheeyelocalizationroutine,allimagealignmentsaremanuallycheckedandanyerrorscorrected,priortotestingandevaluation.@#@Wedetectthepositionoftheeyeswithinanimageusingasimpletemplatebasedmethod.Atrainingsetofmanuallypre-alignedimagesoffacesistaken,andeachimagecroppedtoanareaaroundbotheyes.Theaverageimageiscalculatedandusedasatemplate.@#@Figure4-1Theaverageeyes.Usedasatemplateforeyedetection.@#@Botheyesareincludedinasingletemplate,ratherthanindividuallysearchingforeacheyeinturn,asthecharacteristicsymmetryoftheeyeseithersideofthenose,provideausefulfeaturethathelpsdistinguishbetweentheeyesandotherfalsepositivesthatmaybepickedupinthebackground.Althoughthismethodishighlysusceptibletoscale（i.e.subjectdistancefromthecamera）andalsointroducestheassumptionthateyesintheimageappearnearhorizontal.Somepreliminaryexperimentationalsorevealsthatitisadvantageoustoincludetheareaofskinjust@#@successfulmatches,wedividethelowerimagevaluesbytheupperimagetoproduceaweightsvectorasshowninFigure4-3.Whenappliedtothedifferenceimagebeforesummingatotalerror,thisweightingschemeprovidesamuchimproveddetectionrate.@#@Figure4-3-Eyetemplateweightsusedtogivehigherprioritytothosepixelsthatbestrepresenttheeyes.@#@4.2TheDirectCorrelationApproach@#@Webeginourinvestigationintofacerecognitionwithperhapsthesimplestapproach,knownasthedirectcorrelationmethod（alsoreferredtoastemplatematchingbyBrunelliandPoggio）involvingthedirectcomparisonofpixelintensityvaluestakenfromfacialimages.Weusetheterm‘DirectCorrelation’toencompassalltechniquesinwhichfaceimagesarecompareddirectly,withoutanyformofimagespaceanalysis,weightingschemesorfeatureextraction,regardlessofthedistancemetricused.Therefore,wedonotinferthatPearson’scorrelationisappliedasthesimilarityfunction（althoughsuchanapproachwouldobviouslycomeunderourdefinitionofdirectcorrelation）.WetypicallyusetheEuclideandistanceasourmetricintheseinvestigations（inverselyrelatedtoPearson’scorrelationandcanbeconsideredasascaleandtranslationsensitiveformofimagecorrelation）,asthispersistswiththecontrastmadebetweenimagespaceandsubspaceapproachesinlatersections.@#@Firstly,allfacialimagesmustbealignedsuchthattheeyecentersarelocatedattwospecifiedpixelcoordinatesandtheimagecroppedtoremoveanybackgroundinformation.Theseimagesarestoredasgrayscalebitmapsof65by82pixelsandpriortorecognitionconvertedintoavectorof5330elements（eachelementcontainingthecorrespondingpixelintensityvalue）.Eachcorrespondingvectorcanbethoughtofasdescribingapointwithina5330dimensionalimagespace.Thissimpleprinciplecaneasilybeextendedtomuchlargerimages:

@#@a256by256pixelimageoccupiesasinglepointin65,536-dimensionalimagespaceandagain,similarimagesoccupyclosepointswithinthatspace.Likewise,similarfacesarelocatedclosetogetherwithintheimagespace,whiledissimilarfacesarespacedfarapart.CalculatingtheEuclideandistanced,betweentwofacialimagevectors（oftenreferredtoasthequeryimageq,andgalleryimageg）,wegetanindicationofsimilarity.Athresholdisthenappliedtomakethefinalverificationdecision.@#@4.2.1VerificationTests@#@Theprimaryconcerninanyfacerecognitionsystemisitsabilitytocorrectlyverifyaclaimedidentityordetermineaperson'@#@smostlikelyidentityfromasetofpotentialmatchesinadatabase.Inordertoassessagivensystem’sabilitytoperformthesetasks,avarietyofevaluationmethodologieshavearisen.Someoftheseanalysismethodssimulateaspecificmodeofoperation（i.e.securesiteaccessorsurveillance）,whileothersprovideamoremathematicaldescriptionofdatadistributioninsomecl