人脸识别文献翻译中英双文复习课程文档格式.docx
《人脸识别文献翻译中英双文复习课程文档格式.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复习课程文档格式.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复习课程文档格式.docx](https://file1.bdocx.com/fileroot1/2022-10/25/c5b41765-1c66-4ca5-83c9-fff136fc1968/c5b41765-1c66-4ca5-83c9-fff136fc19681.gif)
人脸识别文献翻译中英双文复习课程@#@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.Somepreliminaryexperimentationalsorevealsthatitisadvantageoustoincludetheareaofskinjustbeneaththeeyes.Thereasonbeingthatinsomecasestheeyebrowscancloselymatchthetemplate,particularlyifthereareshadowsintheeye-sockets,buttheareaofskinbelowtheeyeshelpstodistinguishtheeyesfromeyebrows(theareajustbelowtheeyebrowscontaineyes,whereastheareabelowtheeyescontainsonlyplainskin).@#@Awindowispassedoverthetestimagesandtheabsolutedifferencetakentothatoftheaverageeyeimageshownabove.Theareaoftheimagewiththelowestdifferenceistakenastheregionofinterestcontainingtheeyes.Applyingthesameprocedureusingasmallertemplateoftheindividualleftandrighteyesthenrefineseacheyeposition.@#@Thisbasictemplate-basedmethodofeyelocalization,althoughprovidingfairlypreciselocalizations,oftenfailstolocatetheeyescompletely.However,weareabletoimproveperformancebyincludingaweightingscheme.@#@Eyelocalizationisperformedonthesetoftrainingimages,whichisthenseparatedintotwosets:
@#@thoseinwhicheyedetectionwassuccessful;@#@andthoseinwhicheyedetectionfailed.Takingthesetofsuccessfullocalizationswecomputetheaveragedistancefromtheeyetemplate(Figure4-2top).Notethattheimageisquitedark,indicatingthatthedetectedeyescorrelatecloselytotheeyetemplate,aswewouldexpect.However,brightpointsdooccurnearthewhitesoftheeye,suggestingthatthisareaisofteninconsistent,varyinggreatlyfromtheaverageeyetemplate.@#@@#@Figure4-2–Distancetotheeyetemplateforsuccessfuldetections(top)indicatingvarianceduetonoiseandfaileddetections(bottom)showingcrediblevarianceduetomiss-detectedfeatures.@#@Inthelowerimage(Figure4-2bottom),wehavetakenthesetoffailedlocalizations(imagesoftheforehead,nose,cheeks,backgroundetc.falselydetectedbythelocalizationroutine)andonceagaincomputedtheaveragedistancefromtheeyetemplate.Thebrightpupilssurroundedbydarkerareasindicatethatafailedmatchisoftenduetothehighcorrelationofthenoseandcheekboneregionsoverwhelmingthepoorlycorrelatedpupils.Wantingtoemphasizethedifferenceofthepupilregionsforthesefailedmatchesandminimizethevarianceofthewhitesoftheeyesforsuccessfulmatches,wedividethelowerimagevaluesbytheupperimagetoproduceaweightsvectorasshowninFigure4-3.Whenappliedtothedifferenceimagebeforesummingatotalerror,thisweightingschemeprovidesamuchimproveddetectionrate.@#@Figure4-3-Eyetemplateweightsusedtogivehigherprioritytothosepixelsthatbestrepresenttheeyes.@#@4.2TheDirectCorrelationApproach@#@Webeginourinvestigationintofacerecognitionwithperhapsthesimplestapproach,knownasthedirectcorrelationmethod(alsoreferredtoastemplatematchingbyBrunelliandPoggio)involvingthedirectcomparisonofpixelintensityvaluestakenfromfacialimages.Weusetheterm‘DirectCorrelation’toencompassalltechn