基于計算機視覺的人證同一性研究.pdf

1、浙江工業(yè)大學(xué)碩士學(xué)位論文基于計算機視覺的人證同一性研究姓名：孫軍申請學(xué)位級別：碩士專業(yè)：計算機應(yīng)用技術(shù)指導(dǎo)教師：湯一平20120320THERESEARCHOFPERSoNANDIDCARDSIDENTITYBASEDoNCoT訌PUTERVISIONABSTRACTWiththerapiddevelopmentofscienceandtechnology，thesocialactivitiestendtobemorgfrequent，

2、theneedsofhavingastable，fast，accuratepersonalauthenticationandquerysystembecomelargerandlarger；howevercurrently，faceverificationhastheproblemssuchaslowefficiencyofauthentication，pooraccuracyandtheinadequateuseofinformati

3、on，etc；tothissituation，basedonthebiometricinformationinthesecondgenerationIDcardThispaperproposeonekindoffaceverificationdeviceandsystembasedoncomputervisionThispaperusingfacerecognitionforidentityverification，facerecogn

4、itionasanimportantandcomplexmodelinbiometricsrecognition，謝tllit’Sadvantagesofnoninterference，goodconcealmentandenvironmentfriendly，isbeingwidelyconcemedofandresearchedbyscholarsintheworldThispaperwillcombinethefacerecogn

5、itiontechnologyandinformationofthesecondgenerationIDcardforfaceverificationItsmaincontentshavethreeaspectsasfollow：1Thispaperusingmodule2DPCAalgorithmforfacefeatureextract，improvetheselectionofeigenvectorandthesolutionof

6、theaverageofcharacteristicmatricesinmodule2DPCAalgorithmThefeaturesextractedbyimprovedmodule2DPCAalgorithmCanrepresentfaceessentialfeature，theexperimentprovedOuralgorithmhasmoreeffectivetofaceauthentication2Inthispaperto

7、theproblemofinterferenceonfaceauthenticationbythelightofcomplexenvironment，weimprovethealgorithmbybomhardwareandsoftware，ontheaspectofhardware，wedesignakindofuniformlightequipment謝tlltheinclinedplane，thisdeviceCansimulat

8、ethelightenvironmentwhenshootingtheIDCard；ontheaspectofsothvare，weprocessimagebyilluminationcompensationmethodtofurtherreducetheimpactofenvironmentallightonthefaceauthentication3InfacerecognitionsystembasedonNationalIDCa