Adaptive fingerprint pore modeling and extraction

Adaptive fingerprint pore modeling and extraction

ID:40706514

大小:3.28 MB

页数:12页

时间:2019-08-06

Adaptive fingerprint pore modeling and extraction  _第1页
Adaptive fingerprint pore modeling and extraction  _第2页
Adaptive fingerprint pore modeling and extraction  _第3页
Adaptive fingerprint pore modeling and extraction  _第4页
Adaptive fingerprint pore modeling and extraction  _第5页
资源描述:

《Adaptive fingerprint pore modeling and extraction 》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、ARTICLEINPRESSPatternRecognition43(2010)2833–2844ContentslistsavailableatScienceDirectPatternRecognitionjournalhomepage:www.elsevier.com/locate/pr$AdaptivefingerprintporemodelingandextractionQijunZhao,DavidZhang,LeiZhang,NanLuoBiometricsResearchCentre,DepartmentofComputing,The

2、HongKongPolytechnicUniversity,HungHom,Kowloon,HongKongarticleinfoabstractArticlehistory:SweatporesonfingerprintshaveproventobediscriminativefeaturesandhaverecentlybeenReceived30October2009successfullyemployedinautomaticfingerprintrecognitionsystems(AFRS),wheretheextractionofRece

3、ivedinrevisedformfingerprintporesisacriticalstep.Mostoftheexistingporeextractionmethodsdetectporesbyusinga15December2009staticisotropicporemodel;however,theirdetectionaccuracyisnotsatisfactoryduetothelimitedAccepted20February2010approximationcapabilityofstaticisotropicmodelstov

4、arioustypesofpores.ThispaperpresentsadynamicanisotropicporemodeltodescribeporesmoreaccuratelybyusingorientationandscaleKeywords:parameters.AnadaptiveporeextractionmethodisthendevelopedbasedontheproposeddynamicAutomaticfingerprintrecognitionanisotropicporemodel.Thefingerprintimag

5、eisfirstpartitionedintowell-defined,ill-posed,andPoreextractionbackgroundblocks.AccordingtothedominantridgeorientationandfrequencyoneachforegroundPoremodelsblock,alocalinstantiationofappropriateporemodelisobtained.Finally,theporesareextractedbyBiometricsfilteringtheblockwiththead

6、aptivelygeneratedporemodel.Extensiveexperimentsareperformedonthehighresolutionfingerprintdatabasesweestablished.Theresultsdemonstratethattheproposedmethodcandetectporesmoreaccuratelyandrobustly,andconsequentlyimprovethefingerprintrecognitionaccuracyofpore-basedAFRS.&2010Elsevier

7、Ltd.Allrightsreserved.1.IntroductionrequirementslimittheuseofLevel3featuresinconventionalAFRS.ThankstotheadvancesinimagingtechniquesandthedemandforFingerprintisthemostwidelyusedbiometriccharacteristicformoresecurebiometricsystems,recentlyresearchershavebeenpersonalidentificatio

8、nbecauseofitsuniquenessandstabilitypayingmoreandmoreattention

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。