预览加载中，请您耐心等待几秒...

基于支持向量机和遗传算法的人脸识别研究.docx

预览
1/4
2/4
3/4
4/4

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于支持向量机和遗传算法的人脸识别研究 Abstract: Thispaperproposesaresearchtopiconfacerecognitionbasedonsupportvectormachineandgeneticalgorithm.Inrecentyears,facerecognitiontechnologyhasbecomeanimportantresearchtopicincomputervisionandimageprocessing.Supportvectormachine(SVM)isawidelyusedmachinelearningalgorithmforclassificationandregressionproblems.Geneticalgorithm(GA)isaheuristicalgorithminspiredbynaturalevolution,whichhasbeenappliedtooptimizationproblems.CombiningSVMandGAcanimprovetheperformanceoffacerecognition.ThispaperwillintroducethebasicconceptsofSVMandGA,andreviewrelatedworksonfacerecognitionbasedonSVMandGA.Finally,wewilldiscussthechallengesandfutureresearchdirectionsofthistopic. Keywords:facerecognition,supportvectormachine,geneticalgorithm. Introduction: Facerecognitionisatechnologythatcanautomaticallyidentifyindividualsbasedontheirfacialfeatures.Ithasbroadapplicationsinsecurity,surveillance,orhuman-computerinteraction.Withtherapiddevelopmentofcomputervisionandimageprocessing,alargenumberoffacerecognitionalgorithmshavebeenproposed,suchasPCA(PrincipalComponentAnalysis),LDA(LinearDiscriminantAnalysis),andneuralnetworks.Amongthesealgorithms,SVMhasbecomeapopularchoiceduetoitsgoodgeneralizationperformanceandabilitytohandlehigh-dimensionaldata.GAisametaheuristicalgorithmthatcanfindoptimalsolutionstooptimizationproblems. ThecombinationofSVMandGAcanovercomethelimitationsofSVMandimprovethefeatureselectionprocess.SVMcanbeusedtoclassifythefaceimages,whileGAcanbeusedtoselecttheoptimalsubsetoffeaturesthatcanmaximizetheclassificationaccuracy.Therefore,thisresearchtopicaimstoexploretheapplicationofSVMandGAinfacerecognition. BasicconceptsofSVM: SVMisasupervisedmachinelearningalgorithmthatcanperformclassificationandregressiontasks.ThegoalofSVMistofindthehyperplanethatcanseparatetwoclasseswiththemaximummargin.Themarginisdefinedasthedistancebetweenthehyperplaneandtheclosestdatapointsofeachclass.SVMcanalsohandlenon-linearlyseparabledatabyusingkernelfunctionsthatmapthedataintoahigh-dimensionalf