Robust Face Recognition via Sparse Representation(16)

2020-12-12 23:01

WRIGHTET

AL.:ROBUSTFACERECOGNITIONVIASPARSEREPRESENTATION225

Fig.14.ROCcurvesforoutlierrejection.Verticalaxis:truepositiverate.Horizontalaxis:falsepositiverate.ThesolidredcurveisgeneratedbySRCwithoutliersrejectedbasedon(15).TheSCI-basedvalidationandSRCclassificationtogetherperformalmostperfectlyforupto30percentocclusion.(a)Noocclusion.(b)

Tenpercentocclusion.(c)Thirtypercent.(d)Fiftypercent.

Fig.15.Robusttrainingsetdesign.(a)Varyingillumination.Topleft:foursubsetsofExtendedYaleB,containingincreasinglyextremelightingconditions.Bottomleft:estimatedneighborlinessofthepolytopeconvðÆBÞforeachsubset.(b)Varyingexpression.Topright:fourfacialexpressionsintheARdatabase.Bottomright:estimatedneighborlinessofconvðÆBÞwhentakingthetrainingsetfromdifferentpairsofexpressions.

sincetheoccludingobjectcouldpotentiallybequitesimilartooneoftheothertrainingclasses.However,iftheocclusionisrandomanduncorrelatedwiththetrainingimages,asinSection4.3,theaveragebehaviormayalsobeofinterest.Infact,thesetwoconcerns,sufficiencyandrobustness,arecomplementary.Fig.15ashowstheestimatedneighbor-linessforthefoursubsetsoftheExtendedYaleBdatabase.Noticethatthehighestneighborliness,%1,330,isachievedwithSubset4,themostextremelightingconditions.Fig.15bshowsthebreakdownpointforsubsetsoftheARdatabasewithdifferentfacialexpressions.Thedatasetcontainsfourfacialexpressions,Neutral,Happy,Angry,andScream,picturedinFig.15b.Wegeneratetrainingsetsfromallpairsofexpressionsandcomputetheneighborlinessofeachofthecorrespondingpolytopes.ThemostrobusttrainingsetsareachievedbytheNeutralþHappyandHappyþScreamcombinations,whiletheleastrobustnesscomesfromNeutralþAngry.NoticethattheNeutralandAngryimagesarequitesimilarinappearance,while(forexample)HappyandScreamareverydissimilar.

Thus,bothforvaryinglighting(Fig.15a)andexpression(Fig.15b),trainingsetswithwidervariationintheimagesallowgreaterrobustnesstoocclusion.Designingatrainingsetthatallowsrecognitionunderwidelyvaryingconditionsdoesnothinderouralgorithm;infact,ithelpsit.However,thetrainingsetshouldnotcontaintoomanysimilarimages,asintheNeutral+AngryexampleinFig.15b.Inthelanguageofsignalrepresentation,thetrainingimagesshouldformanincoherentdictionary[9].

offeaturesused(inourfacerecognitionexample,approxi-mately100aresufficienttomakethedifferencenegligible).Moreover,occlusionandcorruptioncanbehandleduniformlyandrobustlywithinthesameclassificationframework.Onecanachieveastrikingrecognitionperfor-manceforseverelyoccludedorcorruptedimagesbyasimplealgorithmwithnospecialengineering.

Anintriguingquestionforfutureworkiswhetherthisframeworkcanbeusefulforobjectdetection,inadditiontorecognition.Theusefulnessofsparsityindetectionhasbeennoticedintheworkin[61]andmorerecentlyexploredin[62].Webelievethatthefullpotentialofsparsityinrobustobjectdetectionandrecognitiontogetherisyettobeuncovered.Fromapracticalstandpoint,itwouldalsobeusefultoextendthealgorithmtolessconstrainedcondi-tions,especiallyvariationsinobjectpose.Robustnesstoocclusionallowsthealgorithmtotoleratesmallposevariationormisalignment.Furthermore,inthesupplemen-taryappendix,whichcanbefoundontheComputerSocietyDigitalLibraryathttp://www.77cn.com.cn/10.1109/TPAMI.2008.79,wediscussouralgorithm’sabilitytoadapttononlineartrainingdistributions.However,thenumberoftrainingsamplesrequiredtodirectlyrepresentthedistributionoffaceimagesundervaryingposemaybeprohibitivelylarge.Extrapolationinpose,e.g.,usingonlyfrontaltrainingimages,willrequireintegratingfeaturematchingtechniquesornonlineardeformationmodelsintothecomputationofthesparserepresentationofthetestimage.Doingso,inaprincipledmanner,itremainsanimportantdirectionforfuturework.

5CONCLUSIONS

AND

DISCUSSIONS

Inthispaper,wehavecontendedboththeoreticallyandexperimentallythatexploitingsparsityiscriticalforthehigh-performanceclassificationofhigh-dimensionaldatasuchasfaceimages.Withsparsityproperlyharnessed,thechoiceoffeaturesbecomeslessimportantthanthenumber

ACKNOWLEDGMENTS

TheauthorswouldliketothankDr.HarryShum,Dr.XiaoouTangandmanyothersattheMicrosoftResearch,Asia,forhelpfulandinformativediscussionsonfacerecognition,duringtheirvisitthereinFall2006.Theyalso


Robust Face Recognition via Sparse Representation(16).doc 将本文的Word文档下载到电脑 下载失败或者文档不完整,请联系客服人员解决!

下一篇:平面设计合同范本

相关阅读
本类排行
× 注册会员免费下载(下载后可以自由复制和排版)

马上注册会员

注:下载文档有可能“只有目录或者内容不全”等情况,请下载之前注意辨别,如果您已付费且无法下载或内容有问题,请联系我们协助你处理。
微信: QQ: